keymem is an MCP memory server that lets an agent store, recall, navigate, correct, and manage associative long-term memories in a local key graph.
Recall existing knowledge with short keyword queries, returning ranked key clusters plus a passive top memory with validity and connected keys.
Browse key vocabulary when recall misses, then drill into ranked memory handles under a key.
Walk the graph deliberately through Key → Memory → Key chains: read key handles, read full memories, and follow connected keys.
Save durable facts with 3–6 atomic keys, key types, namespaces, TTL, decay profiles, related-memory links, and provenance; batch-save multiple facts.
Confirm freshness only with explicit user evidence, authoritative sources, or direct observation, while tracking aging/stale validity.
Correct outdated facts with versioned predecessor preservation, dismiss wrong key associations, or permanently forget memories.
Benefit from Hebbian path reinforcement, cross-lingual key merging, local/OpenAI embeddings, and local JSON storage with no external database.
The associative memory layer for LLM agents — recall by association, not just similarity.
Most agent memory is a vector store. It surfaces what sounds like your query — and misses everything your query is connected to.
keymem stores memories in a key graph instead. A search for "Newton" can still reach "strawberries" — Newton → apple → fruit → strawberry. The path lives in the graph, not in embedding space. It runs locally as an MCP server, so any MCP-compatible agent gets human-like associative recall with no external database.
Works with: Claude Desktop · Claude Code · any MCP-compatible LLM agent
Vector-store memory retrieves by embedding similarity. That works until the thing you need isn't similar to the words you typed:
Query: "Newton"
Similarity search finds: "Newton discovered gravity" ✅
Similarity search misses: "user likes strawberries" ❌A person makes the leap anyway — Newton reminds them of the apple, apples are fruit, they like strawberries. keymem makes that same leap because the path exists in the key graph: Newton → apple memory → fruit key → strawberry memory. No embedding distance connects "Newton" and "strawberry"; a chain of shared keys does.
This is the core idea: memories are not islands ranked by distance. They are nodes in an N:M key/value graph that an agent can walk.
Related MCP server: Logica Mind
Key Space (concepts) Value Space (memories)
[apple] ────────┬─────────→ ↑ same memory
[gravity] ────────┘
│
[apple] ────────┼─────────→ "apples are red fruit"
[fruit] ──────┬─┘
[red] ──────┤
│
[fruit] ──────┼─────────→ "user likes strawberries"
[strawberry]────┘Memories live in a Value Space, reached through a separate Key Space — one memory reachable via many keys, one key leading to many memories.
recall("Newton") returns matching key clusters such as [Newton] and [apple] plus one passive Top-1 memory under the strongest key. That memory carries matched_key, validity, and connected_keys, so the agent can answer immediately or continue through read_key(fruit).
The default MCP flow remains Key → Memory → Key, but its first Key → Memory hop is completed in one call. Only one memory enters context automatically; later hops remain deliberate.
The animation at the top shows this on a real store: three recall() calls walk from a profile key to a verification philosophy, loading three memories (~2.4k tokens). The branches the agent skipped are still one call away, and auto-expanding the same 12-memory hub would have cost ~8k tokens. The graph knows the roads; the agent decides the steps. Source: docs/demo/chain-walk.html.
keymem is an MCP server (a CLI), not a library. Run it with
npx -y keymem(recommended — always the latest) or install the command globally withnpm i -g keymem. Do not add it to your app withnpm i keymemas a dependency: it bundlesopenai,zod, and the MCP SDK, so inside an existing project it just duplicates those trees (and can clash with your app'szod/openaiversions). Thenpm i keymemline npm shows on the package page is for libraries — it doesn't apply here.
# Optional global install (npx needs none). This puts a `keymem` command on PATH that
# MCP clients can spawn. Run bare, it starts a stdio MCP server and waits for a client —
# so point your MCP config at `keymem` (or just use `npx -y keymem` as shown below).
npm i -g keymemAdd to claude_desktop_config.json:
OpenAI embeddings:
{
"mcpServers": {
"keymem": {
"command": "npx",
"args": ["-y", "keymem"],
"env": {
"OPENAI_API_KEY": "your-openai-api-key"
}
}
}
}Local embeddings (no API key required) — bge-m3 recommended:
{
"mcpServers": {
"keymem": {
"command": "npx",
"args": ["-y", "keymem"],
"env": {
"EMBEDDING_BACKEND": "local",
"LOCAL_EMBEDDING_MODEL": "bge-m3"
}
}
}
}
bge-m3(multilingual, recommended) auto-downloads ~570MB on first run, then caches. OmitLOCAL_EMBEDDING_MODELfor the lighter default (fast-multilingual-e5-large). Cross-encoder reranking is part of the core recall path and downloads a second model on first use; set"KEYMEM_RERANK": "false"only to disable it.
The repo is also a plugin marketplace, so one install wires up everything: the MCP server
(daemon-backed shim), the UserPromptSubmit hook that passively surfaces related memories on every
prompt, and the keymem skill carrying the recall/remember protocol.
Claude Code:
/plugin marketplace add donggyun112/keymem
/plugin install keymem@keymemCodex CLI:
codex plugin marketplace add donggyun112/keymem
codex plugin add keymem@keymemCodex prompts once to trust the hook; approve it or the push path stays silent. The plugin defaults
to local bge-m3 embeddings (auto-downloads ~570MB on first run, no API key). For OpenAI
embeddings, use the manual setup below instead — plugin MCP servers only see the env they declare.
The synchronous hook waits up to 9 seconds for /inject (set KEYMEM_HOOK_TIMEOUT_MS to tune it);
local embedding and reranking can add several seconds to prompts that trigger recall.
# OpenAI embeddings
claude mcp add keymem -e OPENAI_API_KEY=your-key -- npx -y keymem
# Local embeddings (no API key required) — bge-m3 recommended (auto-downloads ~570MB on first run)
claude mcp add keymem -e EMBEDDING_BACKEND=local -e LOCAL_EMBEDDING_MODEL=bge-m3 -- npx -y keymem# OpenAI embeddings
codex mcp add keymem --env OPENAI_API_KEY=your-key -- npx -y -p keymem@latest keymem-shim
# Local embeddings (no API key required)
codex mcp add keymem --env EMBEDDING_BACKEND=local --env LOCAL_EMBEDDING_MODEL=bge-m3 -- npx -y -p keymem@latest keymem-shimUse the keymem-shim entry point (not bare keymem): it runs the shared daemon the push-path hook
talks to. For the hook, add to ~/.codex/config.toml:
[[hooks.UserPromptSubmit]]
[[hooks.UserPromptSubmit.hooks]]
type = "command"
command = "node /absolute/path/to/keymem/hooks/keymem-hook.mjs"
timeout = 10Codex only forwards the env vars declared in its MCP entry, so pass every KEYMEM_* /
SUPER_MEMORY_* override with --env.
That's it — recall and remember work immediately. The agent calls recall before its first reply, navigates with read_key/read_memory, and saves with remember.
For reliable proactive saving in Claude Code, add the following to ~/.claude/CLAUDE.md (MCP prompts are not automatically applied as persistent Claude Code instructions):
## keymem
- Before the first reply and whenever the topic changes, call `recall` silently with short noun-keyword queries.
- Before ending every reply, check whether this turn revealed a durable fact: a name, preference, decision, correction, project fact, or goal.
- If it did, call `remember` or `remember_batch` silently in the same turn with 3-6 diverse keys. A durable fact left unsaved is a bug.
- Use `correct` when existing information changes. Save nothing only when the turn revealed nothing durable.
- Treat `read_memory` as retrieval, not confirmation. Use its `validity.status`: qualify `aging`, and never assert `stale` as current without checking an external source or asking the user.
- Call `confirm_memory` only after an explicit current user assertion, an authoritative current source, or direct observation — never merely because a read succeeded.
- Never mention memory lookup or saving to the user.In Codex, put the same block in ~/.codex/AGENTS.md. (The plugin install ships this as the keymem
skill instead, so you can skip it there.)
For other MCP clients, include the memory_system_prompt MCP prompt in the agent's persistent system instructions. It mandates 3 blind recall() calls before the first reply — appropriate when there's no hook surfacing anything passively. If you do wire up a UserPromptSubmit-equivalent push path yourself, set KEYMEM_HOOK_INSTALLED=true so the prompt reacts to what was surfaced instead of blind-guessing on top of it (this is set automatically by the plugin's .mcp.json).
git clone https://github.com/donggyun112/keymem
cd keymem
pnpm installCreate .env:
OPENAI_API_KEY=your-openai-api-key
OPENAI_EMBEDDING_MODEL=text-embedding-3-smallOr use local embeddings (no API key required):
EMBEDDING_BACKEND=local
LOCAL_EMBEDDING_MODEL=fast-multilingual-e5-large # default; best fit for Korean/multilingual keyspnpm dev
# or:
pnpm build
pnpm startRequirements:
Node.js 20+
pnpm for local development
OpenAI API key for OpenAI embeddings, or fastembed for local embeddings
N:M key/value graph — memories and the concepts that index them are separate spaces, linked many-to-many. One memory is reachable through many keys; one key leads to many memories.
Agent-driven Key → Memory → Key navigation — the agent walks the graph deliberately instead of collapsing it into one opaque similarity search.
Associative multi-hop recall — reach memories no embedding distance would connect, by following chains of shared keys.
Confirmation-aware freshness — reads learn useful paths without certifying old content; explicit evidence refreshes facts across four decay profiles.
One-step versioning — a correction retains its immediate predecessor and records what it superseded.
Key types — concept keys match by similarity; name/proper_noun keys match exactly, so "동건" never matches "뉴턴" just for being short.
Cross-lingual key merging (IDF) — 파이썬 and Python collapse into one canonical cluster instead of fragmenting the key space.
Hebbian link learning — the path an agent actually traverses gets reinforced ("fire together, wire together"), so useful associations become easier to reach.
Hybrid retrieval (optional direct mode) — Kiwi BM25 over keys and content + key embeddings + Reciprocal Rank Fusion, with depth/confirmation-freshness modulation and configurable multi-hop expansion.
Cross-encoder reranking (core default) — bge-reranker-v2-m3 re-scores the passive Top-1 pool and compatibility direct-mode candidates.
Local-first — all data in a local JSON graph; no external database. OpenAI or fully-local embeddings (auto-downloaded).
Every memory has a depth score 0.0 → 1.0, but retrieval and confirmation are separate:
Stage | Depth | Behavior |
Shallow |
| Little explicit confirmation; minimal ranking boost. |
Medium |
| Repeatedly confirmed; moderate ranking boost. |
Deep |
| Strongly confirmed; maximum ranking boost, but still correctable and age-sensitive. |
read_memory() increments access metadata and may reinforce the traversed key edge, but it does
not change depth, last_confirmed_at, confirmation_count, or freshness. Only
confirm_memory(memory_id, evidence) refreshes validity and increases depth +0.05; accepted
evidence is an explicit current user assertion, an authoritative current source, or direct
observation. A successful read alone is never confirmation.
Freshness decays from last_confirmed_at according to the memory's decay_profile:
Profile | Default half-life | Intended use |
| 7 days | Fast-changing state such as temporary plans or availability |
| 90 days | General facts; the default |
| 365 days | Slowly changing facts |
| No decay | Deliberately timeless or immutable facts |
Every memory view includes a validity payload with freshness, status (fresh, aging, or
stale), age_days, last_confirmed_at, confirmation_count, decay_profile,
verification_recommended, and verification_required. fresh means freshness is at least
0.5; aging is at least 0.125 but below 0.5; stale is below 0.125 and must not be
asserted as current without verification. Decay is soft: it lowers ranking through
0.2 + 0.8 × freshness and never deletes a memory. TTL remains the only automatic expiry mechanism.
For example, save a temporary plan with remember(..., decay_profile:"transient"); after the user
explicitly says it is still current, call confirm_memory(memory_id, evidence:"user"). Do not
confirm merely because read_memory returned it.
Not all keys should behave the same. Names shouldn't match semantically — "동건" shouldn't match "뉴턴" just because they're both short Korean words.
Type | Matching | Use Case |
| Embedding similarity ≥ threshold (0.28 OpenAI / 0.60 local) | Topics, categories, attributes |
| Exact match only | Person names |
| Exact match only | Brands, places |
Name/proper_noun keys also get an IDF penalty (×0.5) when they become hub keys connected to many memories, preventing them from polluting unrelated searches.
"user lives in Seoul" (depth: 0.4 → weakened to 0.12, preserved)
↑ superseded by
"user moved to Busan" (depth: 0.0, new)keymem retains the immediate predecessor instead of overwriting it. The superseded record is
excluded from active retrieval regardless of its depth, and the new version becomes current. A
later correction prunes the grandparent, so provenance is one step rather than a full-history
archive.
Add key "파이썬" → finds existing "Python" (similarity 0.87 > threshold 0.85)
→ reuses existing key instead of creating duplicatePrevents key space fragmentation. The same concept across languages or phrasing stays unified.
The default MCP API crosses from Key Space to one Value while preserving explicit graph navigation:
recall(query, context) returns ranked key clusters and the Top-1 memory under the strongest key. The raw context ranks memories within that key.
The memory is a passive preview with validity, matched_key, and every connected_keys[].key_id. It does not increment access/depth, reinforce links, learn aliases, or confirm freshness.
The agent checks which facts the question needs. It can use the preview when those facts are present; otherwise it follows a connected key for a missing fact with read_key(key_id, missing_fact_query) or recalls that fact directly. It stops when the evidence is complete or no promising path remains. Later memories are not automatically injected.
read_memory(memory_id, via_key_id) remains the explicit full-read path. It updates access metadata and reinforces only the traversed edge; it does not confirm or deepen the memory.
Semantically merged keys are preserved as aliases on one canonical key cluster (for example Python + 파이썬). The recommended bge-m3 profile enables conservative short-key merging by default; override or disable it with KEYMEM_SHORT_KEY_MERGE. A key linked to at least three active memories is surfaced as a hub with is_hub, memory_count, and specificity metadata rather than being hidden by IDF. Override the hub threshold with KEYMEM_KEY_HUB_MIN_LINKS.
recallInject)MemoryGraph.recall() is a one-call ranked retrieval path used by recallInject() and available to library callers. It combines two candidate paths with Reciprocal Rank Fusion (RRF_K = 60):
Kiwi BM25: lexical search over memory keys and content, using the official kiwi-nlp WASM tokenizer in Node. Korean morphology is tokenized locally; no Python process is required.
Key matching: query embeddings match concept keys; exact names and aliases provide literal entry points. Key links lead to candidate memories.
Memory bodies have no embeddings. Cross-encoder reranking remains enabled and scores query–content pairs directly. Graph expansion, depth, and confirmation freshness still affect ranking. The default MCP recall tool uses explicit key navigation, so agents can drive later hops deliberately.
Reading a full memory is a write, not just a read. In the default flow, recall() and read_key() are read-only; read_memory(memory_id, via_key_id) reshapes the selected path:
The traversed via_key_id → memory_id link is reinforced (+0.1, capped at 3.0).
A full read increments access metadata but changes neither depth nor last_confirmed_at, so it
never refreshes freshness. Freshness continues to decay as elapsed time grows. Evidence-backed
confirm_memory() increases depth and refreshes freshness by advancing last_confirmed_at.
Reinforcement is scoped to the key the agent actually traversed — not every key attached to the memory. This is the literal Hebbian rule ("fire together, wire together") and prevents unrelated associations from growing when the memory is reached through a different concept. Weights are clamped to [0.1, 3.0].
Link weights feed back into read_key() ranking, so repeatedly selected paths become easier to reach. recall()/recallInject() retain the previous matched-link reinforcement and explored-link decay behavior.
│ Key Space │
│ [name] [동건] [programming] [python] [fruit] [red] │
│ ↓ ↓ ↓ ↓ ↓ ↓ │
│ [vec] [exact] [vec] [vec] [vec] [vec] │
│ N:M links
↓
│ Value Space │
│ "user's name is Donggeon" depth: 0.85 (deep) │
│ "user likes Python" depth: 0.30 (medium) │
│ "user likes strawberries" depth: 0.05 (shallow) │Default MCP navigation:
Embed the query and match canonical key concepts plus exact aliases.
Return key clusters with memory_count, is_hub, and specificity; do not return memory content.
Rank a selected key's memory handles by link weight, depth, and confirmation freshness in read_key().
Return full content and adjacent key clusters from read_memory(); reinforce the traversed edge only when via_key_id is supplied.
Repeat read_key(next_key_id) to walk the graph deliberately.
recall() algorithm (hybrid, configurable 1–5 hops; default 2; used internally by recallInject()):
Tokenize the query and memory keys/content with Kiwi, then retrieve BM25 candidates.
Match concept keys with query embeddings and literal name/alias matches, then follow their memory links.
Fuse lexical and key-path ranks with RRF (RRF_K = 60).
Apply depth and confirmation freshness, and expand through shared keys and explicit related_to links for the configured hops.
Rerank candidates with the cross-encoder and return ranked results. Matched-link reinforcement and explored-link decay retain their existing behavior.
Only keys retain embedding vectors. Existing memory-body vectors are ignored on load and omitted after the next successful save; key vectors, memory text, links, and history are retained. Back up the store before upgrading if you need to reopen it with an older release.
Duplicate detection compares normalized memory text exactly, within the existing namespace and active-memory rules. Paraphrases are separate records. Automatic confirmation requires normalized utterance and body text to match exactly. New memories do not gain links or contradiction flags from body-vector similarity; supply keys and explicit relationships, and use correct for changed facts. Existing explicit links and recorded contradictions remain readable.
Embedding thresholds apply to keys, not memory bodies. getThresholdProfile() in src/embedding.ts supplies model-specific defaults; use KEYMEM_KEY_RECALL, KEYMEM_KEY_MERGE, KEYMEM_KEY_AUTOLINK (auto-key alias promotion), and KEYMEM_SHORT_KEY_MERGE to tune key routing and canonicalization. An uncalibrated model falls back to the BGE profile with a warning.
Legacy body-cosine settings (KEYMEM_CONTENT_RECALL, KEYMEM_CONTENT_RECALL_SHORT, KEYMEM_MEMORY_DEDUP, KEYMEM_CONTRADICTION, KEYMEM_MIN_SCORE, KEYMEM_GATE_Z, and KEYMEM_KEY_GATE) no longer control memory retrieval or writes. BM25 scores, key cosine scores, RRF ranks, and cross-encoder scores are different scales; do not reuse an old body-cosine threshold as a lexical relevance threshold.
Env var | Default | Description |
|
| Auto-key self-healing: learn missing search terms from real usage. Set |
|
| Routing-confirmed selections of a |
|
| Lowest query↔key cosine eligible for routing-confirmation learning. Repeated selections through the same key can teach a below-gate query alias; this confirms routing only, never content freshness. Lower (e.g. |
|
| Max learned aliases promoted per key. |
|
| Seconds before a never-hit learned alias is pruned by the daemon's automatic TTL sweep (30 days). |
|
| How often the daemon sweeps expired memories/aliases on its own. The stdio path sweeps once at startup instead (no long-running loop to schedule against). |
|
| Half-life in days for |
|
| Half-life in days for the default |
|
| Half-life in days for |
For cross-language recall, retain multilingual keys and aliases (for example 딸기 and strawberry). Lexical body search alone does not translate queries.
The tool set contains 10 tools:
Tool | Description |
| Return ranked keys plus one passive Top-1 memory with |
| Browse a namespace's active key vocabulary, hubs first, when recall has no entry hit. |
| List ranked memory IDs and metadata connected to one key. Pass the original query for relevance ordering; supports pagination for hubs. |
| Read full memory content, connected keys, and |
| Refresh freshness and deepen a current memory after explicit user evidence, an authoritative source, or direct observation. A read alone is not evidence. |
| Save memory with key concepts, optional TTL, and a |
| Versioned update. The immediate predecessor is preserved but inactive; omitted TTL/profile inherit from it. |
| Negative feedback: the fact is fine, this key should not have surfaced it. Weakens that one edge (floored, never severed) and cancels its pending alias learning |
| Permanently delete |
| Save multiple memories; each item accepts |
TTL-expired memories and key/memory/link counts are no longer agent-facing tools: the daemon
sweeps expired memories itself (once at startup, then every KEYMEM_CLEANUP_INTERVAL_MS; the
stdio path sweeps once at startup), and the key/memory/link stats are already passively injected
into SERVER_INSTRUCTIONS on every turn — a separate memory_stats() call was pure duplication.
Scores carry score_kind. Key recall exposes key_relevance from key cosine or bounded lexical relevance. content_relevance is bounded BM25 (s / (1 + s)), not cosine. read_key uses within_key_rank, with cross-encoder relevance when available and bounded lexical relevance otherwise. Direct recall uses rrf_fused_rank; RRF rank_score is a rank-fusion value, not a similarity probability.
A system prompt template is also available via the memory_system_prompt MCP prompt — include it to instruct the agent to recall silently, use diverse keys, and never mention the memory system to users.
BGE-M3 (recommended, multilingual) — auto-downloaded: set LOCAL_EMBEDDING_MODEL=bge-m3 (aliases: bgem3, baai/bge-m3, fast-bge-m3). On first use the model is fetched automatically if missing — quantized ONNX (~570MB, from onnx-community/bge-m3-ONNX) plus the tokenizer/config (from BAAI/bge-m3) — and cached under ~/.keymem/models/bge-m3. No manual download needed:
EMBEDDING_BACKEND=local
LOCAL_EMBEDDING_MODEL=bge-m3
# optional — point at an existing model dir to skip the download (backward compatible):
# LOCAL_EMBEDDING_MODEL_PATH=/absolute/path/to/model-dir # dir with model.onnx + tokenizer files
# LOCAL_EMBEDDING_MODEL_FILE=model.onnx # optional; default is model.onnx
# optional: KEYMEM_EMBED_THREADS=4 # ONNX intra-op threads (default: a quarter of the machine, max 6)First run downloads ~570MB once, then reuses the cache. If
LOCAL_EMBEDDING_MODEL_PATHalready holds the model it is used as-is with no download (a partial dir is self-healed — only missing files are fetched). Online-API backends (OpenAI) and fastembed built-ins are unaffected.
bge-m3 runs on its own ONNX session, not through fastembed. Inputs use their actual token length. Its vector-space fingerprint is
local:bge-m3+nopad; a fingerprint change triggers key-vector migration. Earlier padding/latency and retrieval measurements in BENCHMARKS.md describe the previous body-embedding engine.
Cross-encoder reranking (core): the default recall MCP tool's Top-1 path re-scores the candidate pool under its strongest key with bge-reranker-v2-m3. recall()/recallInject() results are reranked too. The model (~570MB, quantized) auto-downloads on first use and caches under ~/.keymem/models/reranker.
# optional: KEYMEM_RERANK=false # disable the core reranker
# optional: KEYMEM_RERANK_MODEL_PATH=/dir # use an existing model directory
# optional: KEYMEM_RERANK_POOL=30 # candidates re-scored (default 30)
# optional: KEYMEM_RERANK_THREADS=4 # ONNX intra-op threads (default: a quarter of the machine, max 6)On by default. If the model cannot load, recall falls back to fused ranking. Query decomposition remains the caller's responsibility.
Task-conditioned evidence selection: expanded recall stays associative, but comparison-shaped
queries are projected at the final evidence boundary so both named entities receive task-relevant
support. KeyMem derives the comparison dimension after removing the entity names (for example,
nationality or founded), keeps the graph candidate pool and association scores intact, and
preserves the original associative winner for reinforcement. This is on by default; disable it with
KEYMEM_TASK_EVIDENCE_SELECTION=false.
Reranker not-found gate (KEYMEM_RERANK_MIN_SCORE): in recall()/recallInject(), reject the complete result when the top cross-encoder logit is below this floor.
KEYMEM_RERANK_MIN_SCORE=0 # reject when top rerank logit < 0 (bge-reranker-v2-m3 scale)⚠️ Caveats. (1) Unset by default — no gate. (2) The logit scale is model-dependent;
0(≈ sigmoid 0.5) suitsbge-reranker-v2-m3(measured: same-language found ≈ +3.9, not-found ≈ −5 to −6) — recalibrate for other rerankers. (3) Trusted for SAME-LANGUAGE only. Cross-lingual relevance logits run low even when relevant (KR query ↔ EN memory ≈ −5.4), so the gate auto-bypasses on a script mismatch (KR↔Latin) to avoid false-rejecting cross-lingual hits — which means cross-lingual content must be reachable via bilingual keys (["Jiwoo","지우"]), and cross-lingual not-found precision is a known limitation. Leave this off if you can't tag bilingual keys.
Prefix behavior: BGE-M3 does not use
passage:/query:prefixes — embeddings are passed through as-is. All other local models (e5, BGE-en, MiniLM) continue to use prefixes unchanged.
Multilingual key embeddings:
bge-m3remains supported. Historical model comparisons do not establish the quality or not-found behavior of the current Kiwi BM25 architecture.
If OPENAI_API_KEY is not set and EMBEDDING_BACKEND is unset, the server automatically uses the local fastembed backend.
For English-only use or lower local resource usage, set LOCAL_EMBEDDING_MODEL=fast-bge-base-en-v1.5 or fast-bge-small-en-v1.5.
Switching backends is safe. The graph records an embedding fingerprint (backend + model id) identifying the vector space its embeddings live in. On startup, if the current backend's fingerprint or dimension differs from what is stored, the graph auto-migrates — every key is re-embedded with the new backend while content, links, depth, and access history are preserved (a
graph.json.bak.*backup is written first). The fingerprint matters because two models can share a dimension yet produce incompatible vectors (e.g.fast-multilingual-e5-largeandbge-m3are both 1024-d); a dimension check alone would miss that swap and silently corrupt every similarity. Disable withKEYMEM_AUTO_MIGRATE=false. Re-embedding via OpenAI incurs one-time API cost proportional to your key count.Migrating a pre-fingerprint (legacy) graph across same-dimension models. A graph written before fingerprinting has no recorded vector space, so a same-dimension model swap off it cannot be detected automatically. Set
KEYMEM_FORCE_REEMBED=truefor one startup to re-embed unconditionally and stamp the fingerprint; remove it afterward (left on, it re-embeds on every start). This is exactly the one-shot needed when moving an existing e5 graph to bge-m3.
All data is local. No external database required.
~/.keymem/
└── graph.json # canonical keys, aliases, memories, weighted linksSet KEYMEM_DATA_DIR to use a different storage directory.
Linking a memory to its source conversation. When you save a memory, keymem stamps the active host session onto its source (host_session / host_agent / host_turn) for provenance. keymem does not expose a tool to read those transcripts back — it only reads them internally to resolve the active session. Locations are auto-detected per OS and honour the agents' env overrides:
Claude Code — ~/.claude/projects/**/{session_id}.jsonl ($CLAUDE_CONFIG_DIR)
Codex — ~/.codex/sessions/**/rollout-*-{session_id}.jsonl ($CODEX_HOME)
Access is gated. Because transcripts are local, potentially sensitive history, keymem only reads them to stamp provenance when trusted as the owner's personal local agent — i.e. a recognized host injected its session env (CLAUDE_CODE_SESSION_ID / CODEX_THREAD_ID), or you explicitly opt in with KEYMEM_TRANSCRIPT_ACCESS=true. Otherwise (a plain server, a remote deployment, a non-owner/custom agent) memories are saved without a host link. Set KEYMEM_TRANSCRIPT_ACCESS=false to force-disable even under a host agent.
The active session is found two ways:
Deterministic — the host injects its session id into every MCP server it spawns, and keymem reads it directly: Claude Code → CLAUDE_CODE_SESSION_ID, Codex → CODEX_THREAD_ID (which equals the rollout file's session id). The link is exact, with no guessing.
Heuristic fallback — for hosts that don't expose a session id (e.g. Claude Desktop), keymem uses the most-recently-modified transcript (with a staleness guard).
Historical measurements of the previous body-embedding engine: on HotpotQA bridge questions (real external multi-hop data, gold labels, no LLM judge — and
keys generated blind by independent subagents that never saw the question or answer), the
key-graph retrieves both gold supporting paragraphs 63% of the time vs 53% for flat
semantic retrieval and 35% for lexical (+10pp / +28pp) — the connected-but-dissimilar case
it's built for. (Honest: my own hand-derived keys inflated this to 78/60; on non-multi-hop
"comparison" questions the graph slightly hurts; it's retrieval-recall, not answer accuracy.)
The read path is also O(1) (read_memory p50 ~45ms → ~0.01ms @ 500 memories). Full methodology
and caveats: BENCHMARKS.md. These scores do not validate the current Kiwi BM25 + key-embedding engine; no production quality scores have been established for it.
Linear scan — suitable for personal use (~10k memories). FAISS/ChromaDB integration planned for larger scale.
Later-hop round trips — recall completes the first Key → Memory hop, but following a connected key to another memory still requires read_key → read_memory.
Hub breadth — broad keys can connect many memories. read_key() paginates hubs; the agent must choose whether to continue paging or follow a more specific adjacent key.
Agent quality matters — key selection on remember affects retrieval quality. System prompt tuning is important.
Lexical coverage — Kiwi BM25 does not translate or detect paraphrases by itself. Multilingual keys, key embeddings, and reranking help route and rank candidates, but cannot guarantee missing candidates are recovered.
Threshold calibration — thresholds are tuned per embedding model. A new/uncalibrated model falls back to the BGE profile (with a warning); recalibrate via the KEYMEM_* env overrides.
pnpm test # unit tests (fast, no model download)
tsx test/scenarios.ts # 21 end-to-end behavioral checks (local e5)
tsx test/robustness.ts # threshold overrides + Hebbian pollution bounds
tsx test/migration.ts # backend/dimension switch auto-migration (no brick)
tsx test/nhop.ts # N-hop chained traversal (recall hops parameter)
tsx test/depth-noise.ts # deep-hop noise bounds + relative score floor
tsx test/live-multilingual.ts # interactive multilingual recall demo
# Manual retriever-quality check (NOT part of pnpm test):
EMBEDDING_BACKEND=local npx tsx test/retriever-quality.live.ts
# For bge-m3: also set LOCAL_EMBEDDING_MODEL=bge-m3 LOCAL_EMBEDDING_MODEL_PATH=/abs/dirscenarios.ts and robustness.ts exercise the real local embedding backend (direct/associative/cross-lingual recall, versioning, depth growth, dedup, TTL, Hebbian learning, namespace isolation). Key-threshold recalibration and retrieval quality require fresh runs after an engine or model change; historical passing results do not validate this architecture.
FAISS/ChromaDB for scale
Coding agent profile (different key strategies for code context)
Memory export/import
Multi-user support
donggyun112 — github.com/donggyun112
Repository: donggyun112/keymem · Issues & PRs welcome.
MIT © donggyun112
Browse the vocabulary of one namespace when recall has no hit or you need an entry point. Returns active key clusters with hubs first, then by linked-memory count. This is index metadata only; continue with read_key(key_id, query, namespace) and read_memory(memory_id, via_key_id, namespace).
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | ||
| offset | No | ||
| hubs_only | No | ||
| namespace | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden and does disclose meaningful behavior: results are active key clusters ordered hubs-first then by linked-memory count, and it is index metadata only, not memory content. It omits pagination behavior, default limits, and what occurs for an unknown/empty namespace, which keeps it short of a 5.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Three tight sentences, front-loaded with purpose, then return shape, then next steps. Nothing is redundant and there is no filler.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
There is no output schema and no annotations, so the description must stand alone; it orients the agent well on intent and follow-up calls but leaves parameter behavior (paging, hubs_only) unexplained for a four-parameter tool. Adequate for choosing the tool, incomplete for invoking it precisely.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, so the description must compensate, but it never explains limit, offset, hubs_only, or the namespace argument. The phrase 'hubs first' hints at the hubs concept but does not clarify the hubs_only flag or paging semantics, leaving all four parameters undocumented.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
States a specific verb (browse) and resource (the vocabulary / key clusters of one namespace), and contrasts it with recall by describing itself as the fallback entry point. An agent can distinguish it from recall, read_key and read_memory without opening any schema.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicit triggering condition: use it when recall returns no hit or you need an entry point, naming recall as the alternative it complements. It also routes the agent forward with read_key(key_id, query, namespace) and read_memory(memory_id, via_key_id, namespace), so the workflow position is unambiguous.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Confirm that a memory is still current using explicit present evidence. Never call this merely because read_memory returned the content. Use only after a current user assertion, an authoritative current source, or direct observation. Refreshes validity but does not change content or key links. An exact normalized restatement passed as recall's context is already auto-confirmed there (check memories[0].auto_confirmed) — this tool is for evidence recall can't see: read_memory results, authoritative sources, or direct observation.
| Name | Required | Description | Default |
|---|---|---|---|
| source | No | ||
| evidence | Yes | ||
| memory_id | Yes | ||
| namespace | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden and does disclose the key behavioral trait: it 'refreshes validity but does not change content or key links', which tells the agent this is a targeted write rather than a content mutation. It does not state permission requirements, idempotency/rate behavior, or what a successful confirmation returns, so it falls short of fully covering a no-annotation mutation tool.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Four sentences, all load-bearing and front-loaded: purpose first, then the do-not, then the allowed triggers, then the mutation scope, then the sibling nuance. Slightly dense in the middle, but no sentence is filler.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a 4-param mutation tool with no annotations and no output schema, the description covers purpose, gating conditions, and side effects well, and even explains a relevant piece of a sibling's return payload. The remaining gap is the undocumented namespace and source object, plus no statement of the confirmation result.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, so the description must compensate. It effectively maps the evidence enum to its three values (current user assertion = user, authoritative current source = authoritative_source, direct observation = observation), but adds nothing about memory_id, namespace, or the nested source object's expected shape.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The first sentence gives a specific verb (confirm), resource (a memory), and the condition of validity ('still current'), and the final sentence distinguishes it from the sibling auto-confirm path in recall. An agent can tell this apart from read_memory, recall, correct, and dismiss without opening any schema.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
It states explicit exclusions ('Never call this merely because read_memory returned the content'), states the enabling conditions ('only after a current user assertion, an authoritative current source, or direct observation'), and names the alternative path (recall's auto-confirm via memories[0].auto_confirmed) plus exactly when this tool is still needed.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Update outdated information. Use when user corrects you or info changes (e.g. moved cities, changed job). Old version is preserved but weakened — never lost. Omit keys to keep the same search terms. Omit decay_profile and ttl_seconds to preserve the predecessor's policies; provide either to replace that policy. related_to links the updated memory to other memory IDs.
| Name | Required | Description | Default |
|---|---|---|---|
| keys | No | ||
| source | No | ||
| content | Yes | ||
| key_types | No | ||
| memory_id | Yes | ||
| related_to | No | ||
| ttl_seconds | No | ||
| decay_profile | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden and delivers meaningful behavior: the old version is 'preserved but weakened — never lost,' establishes a non-destructive update pattern, and explains the defaulting semantics of omitted fields. It omits return format and any auth/permission behavior, but the core mutation semantics are well disclosed.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is dense and front-loaded, leading with purpose then immediately covering behavior and parameter defaults in tight sentences. Every clause carries information, though it reads as a run-on paragraph rather than separated concerns.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For an 8-parameter mutation tool with no annotations or output schema, it covers the essential behaviors (predecessor preservation, field defaults) an agent needs. Gaps remain around the undocumented source/key_types params and the response shape, but the critical decision-relevant behavior is present.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0% across 8 parameters, so the description must compensate. It explains the non-obvious semantics of keys, decay_profile, ttl_seconds, and related_to, but leaves source, key_types, content, and memory_id undocumented, so roughly half the parameters remain unexplained.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description opens with a specific verb+resource ('Update outdated information') and the examples ('moved cities, changed job') make the corrective-update intent concrete. It does not, however, explicitly differentiate itself from siblings like remember/confirm_memory, leaving that distinction to the reader.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
It states a clear trigger condition ('Use when user corrects you or info changes') with illustrative examples, which is solid context for selection. It stops short of naming when-not-to-use or the alternative tools (e.g. remember for new facts, forget for removal).
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Tell keymem a recalled memory was surfaced by the WRONG key — the fact may be fine, it just should not have come up for this query. Pass the memory_id and the key_id it arrived under (recall returns both). Weakens that one key->memory link so the pairing ranks lower next time, and cancels any pending alias learning for it. The memory itself, its other keys, and its content are untouched, and the link is floored rather than severed, so nothing becomes unreachable. Use correct() when the fact changed and forget() when it is simply wrong.
| Name | Required | Description | Default |
|---|---|---|---|
| key_id | Yes | The key the memory was recalled under. | |
| memory_id | Yes | ||
| namespace | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden and does so thoroughly: it discloses that only one key->memory link is weakened, that ranking is lowered next time, that pending alias learning is cancelled, that the memory/other keys/content are untouched, and that the link is floored rather than severed so nothing becomes unreachable. That is unusually complete disclosure of effect and reversibility.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Although multi-sentence, it is front-loaded with the core purpose and each sentence adds a distinct, non-redundant fact (what changes, what does not, how to choose between siblings). No filler.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a mutation-style tool with no annotations and no output schema, the description covers effect, reversibility, and sibling disambiguation well. The only gap is the unexplained namespace parameter, which is a minor omission given how much else is disclosed.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is only 33%, so the description must compensate. It adds real meaning for memory_id and key_id, including the helpful hint that recall returns both, but the third parameter (namespace) is undocumented in both the description and the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description opens with a specific verb+resource and a precise scope: 'Tell keymem a recalled memory was surfaced by the WRONG key.' It immediately clarifies the semantics (fact may be fine, just wrong pairing), which distinguishes it sharply from the correct() and forget() siblings.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
It explicitly routes the agent: 'Use correct() when the fact changed and forget() when it is simply wrong,' and separately distinguishes the case where 'the fact may be fine, it just should not have come up for this query.' Both when-to-use and alternatives are named.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Permanently delete a memory. Only use for completely wrong information. For outdated info, use correct() instead — it preserves history.
| Name | Required | Description | Default |
|---|---|---|---|
| memory_id | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, description carries full burden. It states 'permanently delete' indicating destructive action, but does not mention side effects, irreversibility, or authorization requirements. Adequate but not detailed.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences, no unnecessary words, front-loaded with the key action. Highly concise and well-structured.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple delete tool with one parameter and no output schema, the description covers purpose and usage guidance well. Lacks detail on parameter format or behavior, but overall sufficient for an agent to understand its role.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 0% and there is one parameter (memory_id). The description does not explain the parameter, but the name is self-explanatory. Baseline is 3 for a single parameter; no additional value from description.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool deletes a memory permanently and is for wrong information. It distinguishes from correct(), but does not explicitly mention that it takes a memory_id parameter, which is inferred from context.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicitly states when to use (completely wrong information) and when not to (outdated info), and recommends an alternative tool (correct()). Provides clear decision criteria.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
List the memories stored under one key (concept), ranked. Returns the canonical key, its aliases, and hub metadata plus ranked memory IDs, metadata, and validity — never memory content. Pass a focused query for the missing fact and the active namespace when known: handles are then ranked by content relevance, which is essential for hubs. Each memory's score is content_relevance × link_weight × depth_factor × freshness_factor when query is passed (link_weight × depth_factor × freshness_factor otherwise); content_relevance is normalized lexical relevance or reranker relevance, never body-vector cosine; scores are only meaningful within this one key's ranking. Call read_memory(memory_id, via_key_id=key_id, namespace) on the selected handle to inspect the fact and reinforce the path; reading does not confirm that its content is current. Use limit/offset to page without flooding context.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | ||
| query | No | ||
| key_id | Yes | ||
| offset | No | ||
| namespace | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full behavioral burden and does disclose key traits: what is never returned ('never memory content'), the exact scoring formula, that scores are only meaningful within one key's ranking, and that reading does not establish content currency. It leaves out permission/auth requirements and any rate or pagination limits beyond the limit/offset hint.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The response contract is front-loaded in the first sentence, but the piece is one dense paragraph with inline formula notation that is heavy for a selection-time read. Every sentence is informative, yet the scoring algebra could be terser or deferred.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Despite no output schema and no annotations, the description specifies the return shape, the meaning of scores, and the follow-up call pattern, which is enough for an agent to invoke it correctly. Minor gaps remain around permissions and how ranking behaves with no query beyond the factor substitution shown.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 0% for 5 parameters, so the description must compensate, and it largely does: it explains query's effect on ranking, when to pass namespace, and that limit/offset page results 'without flooding context.' key_id is only implicitly characterized as the concept key rather than defined in detail, so it is not quite complete.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
States a precise verb+resource+scope: 'List the memories stored under one key (concept), ranked,' and enumerates the returned fields (canonical key, aliases, hub metadata, ranked memory IDs). It distinguishes itself from read_memory by clarifying read_key returns handles and 'never memory content,' while read_memory inspects the fact.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Gives clear conditional guidance: pass a focused query and the active namespace when known, then call read_memory on the selected handle to inspect the fact. It also warns that 'reading does not confirm that its content is current,' implying confirm_memory. It does not, however, explicitly exclude the other list/recall siblings (recall, browse_keys), so routing is not fully disambiguated.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Read the full content and validity of one stored memory (selected via read_key). Returns the memory and all connected key clusters so exploration can continue Key → Memory → Key. Pass via_key_id from the selected key: the read records access and only that traversed edge is Hebbian-reinforced. Reading does not change content depth or confirm that the content is current.
| Name | Required | Description | Default |
|---|---|---|---|
| memory_id | Yes | ||
| namespace | No | ||
| via_key_id | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden and does so well: it discloses that reading records access, that only the traversed edge is Hebbian-reinforced, and that reading neither changes content depth nor confirms the content is current. These are non-obvious side effects and non-effects that an agent could not infer from the name or schema.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Front-loaded with the core action, then the traversal workflow, then the side-effect caveats. Sentences are dense but each adds information; slightly long but no filler.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
No output schema exists, and the description does describe the return ('the memory and all connected key clusters'), which is the key missing piece. It omits explanation of the namespace parameter, leaving one gap for a 3-param tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 0%, so the description must compensate. It richly explains via_key_id and its reinforcement behavior, but memory_id (the required param) and namespace are left entirely undocumented in both schema and description, so it only partially covers the semantics gap.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
States a specific verb and resource ('Read the full content and validity of one stored memory') and immediately clarifies the input selector ('selected via read_key'), which distinguishes it from the read_key sibling. An agent knows this fetches a memory object, not a key.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
It tells the agent to obtain the id from read_key and pass via_key_id from the selected key, giving a clear workflow context (Key → Memory → Key). It does not state explicit when-not-to-use conditions or name alternative retrieval tools like recall or related, so it falls short of a 5.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Search long-term memory for what is already known about the user, project, or topic — call this before your first reply and whenever the topic shifts. Always pass the active namespace when known. Returns {status, query, namespace, keys, memories}: ranked key clusters plus one passive Top-1 memory selected under the top key. The memory includes validity, matched_key, and connected_keys, each with a relevance score (cosine of that key to your query/context, sorted high→low). Before answering, check whether the Top-1 memory supplies every fact the question needs. If a fact is missing, follow an unvisited connected key that fits that fact with read_key(key_id, missing_fact_query, namespace), then read_memory on a relevant handle; recheck and continue only while a required fact and promising path remain. If no connected key fits, recall the missing fact directly. Do not add hops to a complete single-fact answer. Passive recall never reinforces links or changes access, depth, aliases, or confirmation — except: when context exactly matches the normalized full text of the returned memory, it is auto-confirmed (memories[0].auto_confirmed: true) without a separate confirm_memory call. An empty result includes empty keys/memories and nearest_keys.
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | ||
| top_k | No | ||
| context | No | The raw user utterance or sentence this lookup serves. Keep query as short noun keywords; pass the sentence here — it drives content matching, which measures higher on sentence-shaped cues. | |
| explain | No | When true, also return namespace_memory_count; status distinguishes found, no_match, and empty_namespace. | |
| max_chars | No | Truncate the returned memory's content to this length. | |
| namespace | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations to lean on, the description carries the full load and does so richly: it discloses that passive recall never reinforces links or alters access/depth/aliases/confirmation, spells out the one auto-confirm exception, and describes the empty-result shape. This is exactly the behavioral context an agent needs for a memory tool.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Purpose is front-loaded in the first sentence and return shape follows, with no filler sentences. It is dense and long for a tool description, embedding a full hop-following policy, but each clause is actionable rather than decorative.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With six parameters, 50% schema coverage, and no output schema, the description still supplies the return structure ({status, query, namespace, keys, memories}), the Top-1/passive-recall model, and the follow-up protocol. An agent has everything needed to invoke and chain it correctly.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 50% (query, top_k, namespace lack schema descriptions), so the description must compensate and largely does: it explains namespace usage ('Always pass the active namespace when known') and the special context semantics that trigger auto_confirmed. It does not clarify top_k or query beyond the schema's context note.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
States a specific verb and resource with scope: 'Search long-term memory for what is already known about the user, project, or topic.' It is clearly distinguished from siblings because it names read_key, read_memory, and confirm_memory and assigns each a different role in the flow.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Gives explicit triggers ('call this before your first reply and whenever the topic shifts') and explicit stop conditions ('Do not add hops to a complete single-fact answer'). It also routes the agent to named alternatives (read_key, read_memory) with the condition that selects each.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
MANDATORY END-OF-TURN GATE: before replying, save every durable fact newly revealed this turn (names, preferences, decisions, corrections, project facts, goals). A durable fact left unsaved is a bug; save silently in the same turn. Save nothing only after consciously confirming that nothing durable appeared. Before writing, recall() the topic in the same namespace and reuse returned canonical concepts or aliases. Use 3-6 diverse ATOMIC concept keys of 1-2 words each, never memory-specific phrases (use 'Nexora' and 'portfolio', not 'Nexora portfolio'); 3+-word keys are flagged in hints.phrase_keys and are measurably 91% unreachable singletons. CROSS-LINGUAL: register both language forms together (for example '포트폴리오' and 'portfolio'). Shared broad keys become navigable hubs. namespace groups memories by project/context; ttl_seconds sets expiry; decay_profile selects transient, standard (the default), stable, or permanent confirmation freshness; related_to adds explicit memory links; source attaches provenance and is auto-stamped with the server session, a timestamp, and — when a host agent (Claude Code, Codex) transcript is active — host_session/host_agent/host_turn. The response may include hints.near_keys (existing concepts your keys nearly duplicate — prefer reusing those concepts) and hints.language_note (add the missing-language variants).
| Name | Required | Description | Default |
|---|---|---|---|
| keys | Yes | ||
| source | No | ||
| content | Yes | ||
| key_types | No | ||
| namespace | No | ||
| related_to | No | ||
| ttl_seconds | No | ||
| decay_profile | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations at all, the description carries the burden of behavioral disclosure. It clearly states the tool is a write operation that modifies memory, and it explains the side effects: unsaved durable facts are bugs, keys become hubs, and hints may return near-duplicate keys. It also documents decay_profile semantics and source auto-stamping. However, it does not explain what the response contains beyond hints, whether the call is idempotent, or whether there are any rate limits or confirmation behaviors (e.g., confirm_memory). A 3 is fair — it covers the core mutation behavior but not all consequences.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is dense and front-loaded with the mandatory gate, but it is quite long — roughly 170 words — and mixes policy (what to save), style guidance (key naming rules), parameter semantics, and hint-handling instructions in one block. Every sentence adds information, but the structure is a single wall of text with no paragraph breaks, which makes it harder to scan. The urgency tone ('MANDATORY', 'bug') is justified but adds noise.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a complex, high-stakes memory-write tool with 8 parameters, no annotations, and no output schema, the description covers the essential behavioral contract: when to call, what to save, how to structure keys, how to handle cross-lingual facts, and what hints may come back. It is somewhat incomplete in that it does not explain key_types at all, does not describe the success/failure response body, and assumes the agent knows what 'canonical concepts' means from recall's description. Still, it provides far more operational context than most tool definitions.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, so the description must compensate for all 8 parameters. It explains keys (atomic, 1-2 words, diverse), content (durable facts), namespace (groups memories by project/context), ttl_seconds (sets expiry), decay_profile (transient/standard/stable/permanent), related_to (explicit memory links), and source (provenance, auto-stamped). Only key_types is not explicitly explained, and it is an optional advanced field. This is strong compensation despite one gap.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly identifies the tool as a memory-save operation with a mandatory end-of-turn gate, specifying that durable facts must be saved silently before replying. It distinguishes itself from recall/read_memory/browse_keys by focusing on writing new facts, and from remember_batch by describing single-turn single-item saving. However, it never explicitly says 'saves facts to memory' in a simple verb+resource form — the purpose is conveyed through instructions rather than a direct statement.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description gives explicit when-to-use guidance: before every reply, save every durable fact newly revealed, and save nothing only after consciously confirming nothing durable appeared. It differentiates from remember_batch by framing this as the per-turn single-item save path, and it tells the agent to recall() the same namespace and reuse canonical concepts — an explicit integration with sibling tools. This is strong operational guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
MANDATORY END-OF-TURN GATE: when a turn reveals multiple durable facts, save them silently before replying. A durable fact left unsaved is a bug. Recall each topic first, reuse canonical concept-level keys (ATOMIC, 1-2 words each — never phrases), and register cross-lingual forms together. Each item: {content, keys, key_types?, namespace?, ttl_seconds?, decay_profile?, related_to?}; decay_profile defaults to standard. Returns saved IDs and is more efficient than multiple remember() calls.
| Name | Required | Description | Default |
|---|---|---|---|
| items | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations the description carries the full burden, and it does disclose useful traits: the save is silent, it returns saved IDs, and decay_profile defaults to standard. It omits failure modes, permission/auth needs, and key-collision behavior, leaving meaningful gaps for a mutating tool.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Front-loads the mandate, then moves to key guidance and the field signature. The emphatic 'A durable fact left unsaved is a bug' is arguably padding, but the rest of the sentences each carry actionable content.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a tool with no output schema and no annotations, it covers purpose, trigger, alternatives, item fields, and the return value (saved IDs). Only the semantics of a few item fields are missing, which is minor given the rest of the coverage.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, so the description must compensate. It enumerates the item fields and adds genuine guidance for 'keys' (atomic, 1-2 words, never phrases; register cross-lingual forms together) and the decay_profile default, but leaves 'source', 'key_types', and 'ttl_seconds' unexplained and just restates the rest of the schema signature.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description states a specific action (save multiple durable facts silently at end of turn) and explicitly differentiates from the sibling 'remember' by calling this 'more efficient than multiple remember() calls'. The core purpose is clear, though the heavy prescriptive framing partially buries it.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
It gives an explicit trigger ('when a turn reveals multiple durable facts') and names the alternative ('more efficient than multiple remember() calls'), plus a prerequisite ('Recall each topic first'). It never states the converse exclusion (single fact → use remember), so it stops short of a full 5.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
v0.30.0cleanup_expiredlist_memoriesmemory_statsrecall7 fields changedInput schema / properties / injectRemoved value: -{
- "type": "boolean"
-}Input schema / properties / inject_explore_shallowRemoved value: -{
- "type": "boolean"
-}Input schema / properties / inject_max_charsRemoved value: -{
- "type": "number"
-}Input schema / properties / inject_min_rel_scoreRemoved value: -{
- "type": "number"
-}Input schema / properties / inject_prefer_depthRemoved value: -{
- "type": "boolean"
-}Input schema / properties / inject_top_kRemoved value: -{
- "type": "number"
-}Input schema / properties / max_charsAdded value: +{
+ "description": "Truncate the returned memory's content to this length.",
+ "type": "number"
+}relatedv0.29.0browse_keysconfirm_memorycorrect2 fields changedInput schema / properties / decay_profileAdded value: +{
+ "enum": [
+ "transient",
+ "standard",
+ "stable",
+ "permanent"
+ ],
+ "type": "string"
+}Input schema / properties / ttl_secondsAdded value: +{
+ "type": "number"
+}dismissread_keyread_memoryrecall2 fields changedInput schema / properties / contextAdded value: +{
+ "description": "The raw user utterance or sentence this lookup serves. Keep query as short noun keywords; pass the sentence here — it drives content matching, which measures higher on sentence-shaped cues.",
+ "type": "string"
+}Input schema / properties / explainAdded value: +{
+ "description": "When true, also return namespace_memory_count; status distinguishes found, no_match, and empty_namespace.",
+ "type": "boolean"
+}rememberremember_batch1 field changedInput schema / properties / items / items / properties / decay_profileAdded value: +{
+ "enum": [
+ "transient",
+ "standard",
+ "stable",
+ "permanent"
+ ],
+ "type": "string"
+}v0.17.1read_keyread_memoryrecall2 fields changedInput schema / properties / inject_max_charsAdded value: +{
+ "type": "number"
+}Input schema / properties / inject_min_rel_scoreAdded value: +{
+ "type": "number"
+}rememberv0.14.10get_conversationv0.14.8cleanup_expiredcorrectforgetget_conversationlist_memoriesmemory_statsread_keyread_memoryrecallrelatedrememberremember_batchScored across 10 tools
The read path (recall → read_key → read_memory) is a coherent pipeline with distinguishable roles, and the mutation tools (remember, correct, forget, dismiss, confirm_memory) have distinct intents. However, the boundaries are subtle enough that descriptions must repeatedly explain how each differs from its neighbors (e.g. dismiss vs correct vs forget, read_key vs read_memory), which signals real potential for misselection. remember vs remember_batch is a clean single/batch pair.
There is a mix of bare verbs (recall, correct, dismiss, forget, remember) and verb_noun names (read_memory, read_key, confirm_memory, browse_keys, remember_batch). Both are readable and individually clear, but the conventions are not uniform, and the noun target varies (key vs memory) across similar read operations.
Ten tools is well within a reasonable range for a memory subsystem and each tool maps to a real operation. The only mild redundancy is remember vs remember_batch, where the batch variant is an efficiency convenience rather than a distinct capability.
The surface covers the core memory lifecycle: recall/search, browse, key and memory reads, write, update (correct), delete (forget), confirmation, and link feedback (dismiss). Gaps are minor — no namespace listing/management, key merging, or export/stats operations — but these are workarounds, not blockers, for the primary recall/remember workflow.
Graph memory for AI agents: entities, cause-effect links, cross-session recall, time travel.
Long-term memory and a knowledge graph for AI agents: recall, notes, secrets and data sources.
Shared long-term memory for AI agents: save and recall context as a searchable knowledge graph.
Persistent memory and knowledge graphs for AI agents. Hybrid search, context checkpoints, and more.
