Pseudolife-MCP

简体中文 · 日本語 · 한국어 · Português (BR) · Español

Persistent long-term memory for Claude Code, Codex, and other MCP clients.

An MCP server that gives coding agents a long-term memory that persists across sessions — surviving context compactions and fresh tasks. Your coding agent is the intelligence; this server is its memory on disk.

What you get:

• Associative memory with honest forgetting — a flat similarity store ranked by hybrid dense-plus-lexical retrieval, with contradiction detection and supersession. (The measured verdict: a preregistered ablation campaign found the previous 8-band continuum tied a flat store on every gate, so the simpler structure ships; the continuum remains one config line away.)

• Canonical facts, not vibes — one current value per entity.attribute slot (or a member set, for slots that hold many concurrent values); corrections supersede rather than silently overwrite, and the full version history survives.

• Dreams — a bundled extractor (or a Claude model via your Max plan) consolidates the memory stream into facts and a knowledge graph while you're not looking.

• Lessons from its own work — successes, dead-ends, and your corrections become do/avoid guidance surfaced at the start of every session.

• A web console to watch it think — the Cortex Console above, plus cited world facts, session episodes, and document RAG.

Measured, with receipts — the full 500-question LongMemEval sweep, all six question types, and every number ships with its committed run artifact:

Equal accuracy to naive RAG across the whole benchmark on ~73% of the context, and a large edge at knowing when it doesn't know: on BEAM-100K's abstention questions the fact spine scores 0.950 against naive RAG's 0.775, unchanged under two independent judges. It loses where an answer has to be aggregated across sessions. Graded by a local, byte-reproducible judge (the cross-judge check names its second judge) — compare within rows, never against GPT-judged leaderboards.

Retired 2026-08-25 (#188): the 0.936 knowledge-update headline. It was measured on the 2026-07-30 bench stack (Qwen3.6-27B answerer and judge). Re-running the same 78 questions after the 2026-08-17 migration to Qwen3.8-27B puts the cascade at 0.846, below the naive-RAG control — which lands on 0.859 on both stacks. The cascade serves the fact-spine answer unless that channel says "I don't know", so it measures the answerer's abstention behaviour as much as the memory: 32/78 abstentions at 46/46 commit precision on the old stack, 22/78 at 0.839 on the new one. The 500-question table above is on the older judge and has not been re-judged, so read its cascade row as an upper bound.

Full tables, the per-type breakdown, both stacks side by side, and every artifact: Benchmarks.

Quickstart

Two commands. No Docker, no database to set up, no container runtime:

pip install "pseudolife-mcp[lite]"
claude mcp add --scope user pseudolife-memory -- pseudolife-mcp

Codex instead of Claude Code — same shape:

pip install "pseudolife-mcp[lite]"
codex mcp add pseudolife-memory -- pseudolife-mcp

Then in either coding agent: "remember that my staging box is haze-02" → the agent calls memory_store; next session, "which box is staging?" → memory_search finds it. Browse everything at the Cortex Console: http://127.0.0.1:8765/ui/.

The first session auto-starts the daemon, which provisions an embedded PostgreSQL 18 (pgvector included, via pg0-embedded) under a stable per-user data dir and downloads the embedding model (~1.2 GB, one-time). It is a real Postgres bank, not a cut-down one: pseudolife-mcp backup writes a standard owner-free pg_dump archive (plus a state archive, 7-day rotation) that restores into any PostgreSQL 18 target regardless of role — the Docker tier included — so outgrowing lite is a dump/restore, not a migration project (backups). Windows needs an ASCII-only data path (PSEUDOLIFE_MCP_DATA_DIR).

What lite gives you, and the one thing it doesn't

The gap, stated plainly. Lite ships no extractor, so the dream pass still runs, prunes, and advances its cursor, but writes no canonical facts: on this path memory_fact_set is the only cortex writer. Everything else above works. Nothing about this is silent — curl http://127.0.0.1:8765/health reports "extractor": "none", and the stdio shim says the same on stderr at session start.

Any OpenAI-compatible endpoint closes it. The daemon inherits the environment it starts from, so two variables are the whole fix — with a local Ollama:

export PSEUDOLIFE_DREAM_BASE_URL=http://localhost:11434/v1
export PSEUDOLIFE_DREAM_MODEL=qwen2.5:7b
pseudolife-mcp serve

$env:PSEUDOLIFE_DREAM_BASE_URL = "http://localhost:11434/v1"
$env:PSEUDOLIFE_DREAM_MODEL    = "qwen2.5:7b"
pseudolife-mcp serve

/health then reports "extractor": "configured". One gotcha: a daemon that is already running keeps the environment it started with, and the shim reattaches to it rather than spawning a new one — stop the old daemon first. A hosted endpoint works too, and costs you the zero-egress property: memory text leaves the machine. Extractor tiers, quality, and the trade-offs: Dreaming.

Related MCP server: agent-mem0

Durable tier — Docker (recommended for a long-lived bank)

Everything above plus the bundled extractor, external volumes, health-checked services, and backup/rollback tooling. Requires Docker and at least one MCP-capable coding agent — Claude Code, Codex, and Gemini CLI are wired end-to-end; anything else gets paste-ready config (provider matrix). One command from clone to first memory:

git clone https://github.com/Pseudogiant-xr/Pseudolife-MCP.git
cd Pseudolife-MCP
ops/install.sh          # Linux / macOS
ops\install.ps1         # Windows (pwsh 7+)
# Codex: add --client codex / -Client codex
# Both:  add --client both  / -Client both
# Gemini: add --client gemini — or several: --client claude,codex,gemini
# Other MCP agents (Cursor, Windsurf, Zed, ...): --client generic

The installer asks which agents to wire (multi-select, with a capability matrix showing exactly what each one gets — session briefing, per-turn discipline, standing file), runs the preflight (one exact fix line per missing prerequisite), then asks which dream extractor should consolidate memories —

• sidecar — the bundled local CPU model; no Claude plan needed, works for everyone, and keeps every memory on the box (~11.8 GB image);

• sonnet-only — the lightest install: a Claude model via a CLI shim (claude-opus-5 by default; the mode name is historical. Needs a logged-in Max-plan claude CLI); the sidecar image is never built or pulled (~11.8 GB lighter; dreams pause while the shim is down);

• sonnet-fallback — the Claude shim primary, the bundled sidecar as automatic fallback (Max-plan CLI plus the ~11.8 GB image) —

then brings the stack up, installs the selected clients' session hooks (where the client has a hook system), registers the MCP transport (the stdio shim by default, with a per-provider writer id; direct HTTP via --transport http), and health-checks the daemon — finishing with a per-agent ladder of what got wired and what that agent's platform cannot support. Where a session-hook briefing exists (Claude, Codex off-Windows) no standing-file edit is needed; for hook-less providers (Gemini CLI, generic agents, Codex on Windows) the installer offers to append the standing block instead — there it is the briefing. --instructions append always writes the block from examples/CLAUDE.memory.md into ~/.claude/CLAUDE.md / ~/.codex/AGENTS.md / ~/.gemini/GEMINI.md (useful for subagent visibility even with hooks). Idempotent — re-run any time; --extractor <mode> switches extractor setups. Non-interactive example: ops/install.sh --extractor sidecar --client codex. Linux (Docker Engine): your user must be in the docker group — sudo usermod -aG docker $USER, then log out/in (the preflight checks this).

Image sizes, the Windows WSL2 memory cap, and what the installer automates: the containerized install below.

ops/preflight.sh --client codex    # or ops\preflight.ps1 -Client codex
docker volume create pseudolife-mcp-bank
docker volume create pseudolife-mcp-state
docker compose -f ops/docker-compose.yml up -d --build   # first build, once

# ...or pull the prebuilt images instead of building (releases >= 0.14.0):
docker compose -f ops/docker-compose.yml -f ops/docker-compose.ghcr.yml pull pseudolife-pg pseudolife-daemon
docker compose -f ops/docker-compose.yml -f ops/docker-compose.ghcr.yml up -d

# Verify, then wire the transport into one or both clients.
curl http://127.0.0.1:8765/health

# Stdio shim (the installer's default — per-session episode identity).
# PSEUDOLIFE_MCP_NO_SPAWN=1 makes the shim wait for the container instead
# of spawning a host fallback that can shadow the Docker bank after a
# reboot; set it on Docker-tier registrations like these.
pip install pseudolife-mcp
claude mcp add --scope user pseudolife-memory --env PSEUDOLIFE_MCP_NO_SPAWN=1 -- pseudolife-mcp
codex mcp add pseudolife-memory --env PSEUDOLIFE_MCP_NO_SPAWN=1 -- pseudolife-mcp

# ...or direct HTTP (no pip package needed; fine for single-session setups):
claude mcp add --transport http --scope user pseudolife-memory http://127.0.0.1:8765/mcp
codex mcp add pseudolife-memory --url http://127.0.0.1:8765/mcp

# Reinforce the protocol-level memory loop with a global standing instruction:
cat examples/CLAUDE.memory.md >> ~/.claude/CLAUDE.md
cat examples/CLAUDE.memory.md >> ~/.codex/AGENTS.md
# (PowerShell: Add-Content "$env:USERPROFILE\.claude\CLAUDE.md" (Get-Content examples\CLAUDE.memory.md -Raw))

Optional knobs live in ops/.env (cp ops/.env.example ops/.env — the install/update scripts scaffold it too; every value is commented, a missing file runs entirely on defaults).

What this is

A memory engine exposed over MCP. There's no chat UI and no LLM doing the thinking — your coding agent is the intelligence; these are tools it calls to store and recall what matters. (Models are bundled as plumbing: baked embedding weights for retrieval, and the optional CPU extractor sidecar that consolidates memories into facts while you sleep.)

Where it sits among the common approaches to agent memory — each column is a fair tool for what it's for; this table is about what question each one answers, not who's wrong:

Auto-journaling records what the agent did; Pseudolife curates what it learned. Both are useful — they answer different questions. Named alternatives — Mem0, Zep/Graphiti, Letta, Cognee, memU, Memori — and the cases where one of them is the better pick: Comparison.

It layers several complementary stores: the associative store (a flat embedding store ranked by cosine similarity fused with a BM25 lexical pool (on by default), with contradiction detection and supersession; an 8-tier banded layout is available as an opt-in preset); the cortex (slot-keyed canonical facts — one current value per entity.attribute, or a member set for set-valued slots — with provenance tiers and contender parking instead of silent overwrites); a typed knowledge graph over those facts with a closed relation vocabulary and on-read inference; the world cortex (durable cited facts about external reality, age-decayed trust); procedural lessons learned from the agent's own work; and a ChromaDB reference bank for document RAG. The canonical layers in depth: the memory model; the graph and multi-hop recall: retrieval.

State lives in Postgres (the durable source of truth) behind a single long-lived daemon; every session attaches through a thin stdio shim (installer default — per-session identity) or directly over HTTP (single-session setups). The result: Claude can pick up where it left off, correct itself when facts change, and reason over relationships — without you re-explaining context each session.

Documentation

This README is the front door — install, wiring, and the basic loop. The deep material lives in the user guide:

Plus evals/README.md (full benchmark methodology) and CONTRIBUTING.

Tools exposed

The surface was consolidated 2026-07-02 (55 → 32 tools; now 35 with memory_toolset and the set-slot pair): lifecycle families became verb-dispatched tools (memory_dream, memory_forget, memory_graph_review), and dump/introspection views moved to the Cortex Console (REST) — the manifest is agent context every session, so it stays lean.

Each tool returns plain JSON. See pseudolife_memory/mcp_server.py for docstrings — those are what Claude reads to decide when to call which tool. The five recall-path tools return compact entries by default (result payloads are agent context on every retrieval); pass verbose=true for full metadata. Full-table dumps and topology views live in the Cortex Console (/api/*) and the pseudolife-mcp briefing CLI.

Toolset tiers. Three visibility tiers — minimal (9 tools), core (22), full (35) — filtered per principal at tools/list; a principal (the named bearer-token identity, or the writer id for single-token installs) steps its own tier up or down with memory_toolset before calling a hidden tool. Defaults, per-client mapping, and weak-model deployments: Configuration — toolset tiers.

Architecture

One memory daemon owns the bank and serves MCP over streamable HTTP at /mcp; every Claude Code session (and any LAN agent) attaches to it. Postgres 18 + pgvector (in Docker on the durable tier; the lite tier runs the same Postgres embedded, no container) is the durable source of truth — the in-memory store is a write-through cache hydrated at startup (a small weights.pt persists only counters — there are no MLP weights).

The daemon runs either containerized (recommended — portable, no host Python) or as a host process. Claude Code attaches through a thin torch-free stdio shim (the installer default — per-session identity, needed for concurrent sessions) or directly over HTTP (simpler for a single session):

Claude session A ─┐  stdio shim (installer default) or HTTP
Claude session B ─┼───────────────────► pseudolife-mcp daemon ─► Postgres (Docker)
LAN agent ────────┘  or stdio shim         (single writer)        pgvector
                     (per session)         host proc OR Docker

This kills two v0.1 hazards by construction: a single writer means concurrent sessions can't clobber each other, and entries are transactional so a crash can't wipe the bank. On top of the associative store sit the canonical layers — cortex, world facts, lessons, temporal/HLC stamps (the memory model) — joined to a typed knowledge graph walkable via memory_graph and multi-hop memory_recall (retrieval & the graph).

Install — containerized (any OS)

What the durable tier installer above does, by hand. The whole stack — Postgres and the memory daemon — runs in Docker. No host Python, no torch install, no version skew; the daemon image bakes in CPU-only torch and the embedding weights — Qwen/Qwen3-Embedding-0.6B (the default retrieval backbone since schema v25) plus all-MiniLM-L6-v2 (kept baked for the ONNX-parity test path) — so it runs identically on Windows / macOS / Linux. Requires only Docker; built once: ~5.0 GB daemon image (measured 2026-07-29 on the deployed build) + ~0.6 GB Postgres + ~11.8 GB extractor sidecar (measured 2026-08-20 with the v3 multi-task bake; skip the sidecar entirely with the installer's sonnet-only mode). The ~12.6 GB and ~10.4 GB figures published before 2026-07-29 are retired: both were inflated by a CUDA torch build that a dependency-resolution bug pulled into the image (see the CHANGELOG); the daemon has always been CPU-only.

git clone https://github.com/Pseudogiant-xr/Pseudolife-MCP.git
cd Pseudolife-MCP

# 1. One-time: create the two persistent volumes (bank + daemon state).
docker volume create pseudolife-mcp-bank
docker volume create pseudolife-mcp-state

# 2. Build + start all three services (Postgres, extractor, then the daemon).
docker compose -f ops/docker-compose.yml up -d --build

Or skip the ~5 GB daemon build entirely and pull the prebuilt images (releases ≥ 0.14.0):

docker compose -f ops/docker-compose.yml -f ops/docker-compose.ghcr.yml pull pseudolife-pg pseudolife-daemon
docker compose -f ops/docker-compose.yml -f ops/docker-compose.ghcr.yml up -d

The extractor sidecar is not published and still builds locally; updates on the pull path are pull + up -d, not ops/update.ps1.

Upgrading from a pre-rename install (volumes ops_pseudolife_pgdata / ops_pseudolife_data)? Don't rename those volumes — keep pointing at them by creating ops/.env with PSEUDOLIFE_BANK_VOLUME=ops_pseudolife_pgdata and PSEUDOLIFE_STATE_VOLUME=ops_pseudolife_data before up. See the compose header.

Windows: cap Docker Desktop's WSL2 VM, which otherwise claims up to ~50% of host RAM — how much the stack actually needs, the ops/wslconfig.example template, and the daemon container's own memory cap: Configuration — Windows / WSL2 memory.

The daemon serves MCP at http://127.0.0.1:8765/mcp and restarts with Docker — no logon task needed. First build downloads the model into the image (once); every container start after that is offline and fast. Wire Claude Code in via the stdio shim (installer default) or directly over HTTP (both below). Where the data actually lives, and how to back it up: Configuration — data layout.

Host-process install (Windows, for GPU / dev): run Postgres in Docker but the daemon on host Python — for hacking on the daemon or running the embedder on a local GPU. Steps, the pseudolife-mcp CLI modes, and the logon autostart task: Configuration — host-process install.

Updating

Lite tier: one command, bank untouched:

pip install -U "pseudolife-mcp[lite]"

Docker tier: after a git pull (or local code change), redeploy the daemon only — safely, without touching Postgres or the extractor:

.\ops\update.ps1        # Windows

./ops/update.sh         # Linux / macOS

It backs up the bank (pg_dump + a state-volume tar), tags a rollback image (when a previous one exists — it says so loudly when there isn't), rebuilds + recreates only the daemon, and waits for /health. It never runs down -v. (Host-process install: just restart the daemon — pip install -e . is editable.) Build cache is pruned automatically after every healthy deploy; see Docker disk retention for the weekly Scheduled Task and the manual .vhdx compact. Never run docker system prune --volumes, which deletes volumes.

Two upgrades are not automatic, because neither can be done safely in place. Both have a step-by-step runbook — backup, dry run, apply, verify, roll back — and a fresh install needs neither:

• A bank older than 0.11.0 (schema v25): every embedding column moved from vector(384) to vector(1024), so the daemon refuses to start rather than half-migrate. Re-embed offline with ops/migrate_embeddings.py — the v25 migration runbook.

• A Docker-tier bank created before 2026-08-14 (PostgreSQL 16 → 18): a Postgres major bump cannot reuse the old data volume. Run pwsh ops/migrate-pg18.ps1 — the PostgreSQL 18 migration runbook.

Wire into your coding agent

Plugin (hooks + commands). With the daemon running, two commands inside Claude Code wire the session hooks (briefing + episode identity), the memory-loop instructions, and the /dream + /memory-status commands:

/plugin marketplace add Pseudogiant-xr/Pseudolife-MCP
/plugin install pseudolife-memory@pseudolife-mcp

The plugin replaces the settings.json hook and the CLAUDE.md block below — the same standing instructions arrive as session context from the daemon. It deliberately does not bundle the MCP server: Claude Code loads a plugin server alongside any user-registered one with no deduplication, which doubled every session's tool namespace next to the installer's registration — so the transport is registered exactly once, by ops/install.* (stdio shim by default — per-session episode identity) or the one-liner below. Details, non-default ports/tokens, and migration: plugin/README.md.

Manual transport registration. The installer's default (shim mode) registers a thin stdio shim — one shim process per session, so every session carries its own tier-1 identity. The same wiring by hand:

pip install pseudolife-mcp    # daemon in Docker; add [lite] for the pip tier
claude mcp add --scope user pseudolife-memory --env PSEUDOLIFE_MCP_NO_SPAWN=1 -- pseudolife-mcp

PSEUDOLIFE_MCP_NO_SPAWN=1 belongs on Docker-tier registrations: the shim then waits for the container instead of spawning a host-side fallback whose port bind can race a still-booting Docker and shadow the real bank. On the [lite] pip tier drop the --env — there the spawn fallback is the zero-config path.

Direct HTTP works too — the daemon serves MCP over HTTP natively (no shim, no host command, nothing OS-specific; concurrent sessions then share one episode identity, so it fits single-session setups best):

claude mcp add --transport http --scope user pseudolife-memory http://127.0.0.1:8765/mcp

(--scope user registers it for every project; drop it to register for the current project only.) Or write the equivalent JSON yourself — into ~/.claude.json under the top-level mcpServers key for user scope, or into a .mcp.json at a project root for project scope:

{
  "mcpServers": {
    "pseudolife-memory": {
      "type": "http",
      "url": "http://127.0.0.1:8765/mcp"
    }
  }
}

For a token-protected daemon, add a headers key to that Claude JSON entry: "headers": { "Authorization": "Bearer <your-token>" }.

Codex — the installer's default (shim mode) wires the same stdio shim, so a Codex session gets its own tier-1 identity instead of inheriting a concurrent Claude session's episode:

pip install pseudolife-mcp
codex mcp add pseudolife-memory --env PSEUDOLIFE_MCP_NO_SPAWN=1 -- pseudolife-mcp

(Same Docker-tier note as the Claude wiring above: keep PSEUDOLIFE_MCP_NO_SPAWN=1 when the daemon runs in Docker; drop it on the [lite] pip tier.)

The HTTP one-liner works too (no pip package needed):

codex mcp add pseudolife-memory --url http://127.0.0.1:8765/mcp

Or add the equivalent user-level entry to ~/.codex/config.toml:

[mcp_servers.pseudolife-memory]
url = "http://127.0.0.1:8765/mcp"
bearer_token_env_var = "PSEUDOLIFE_MCP_TOKEN"

For that Codex HTTP configuration, export PSEUDOLIFE_MCP_TOKEN in the environment that launches Codex. The token stays out of config.toml, and Codex reads it when connecting. This is unnecessary for the default stdio shim.

Gemini CLI — same shape (-s user matters: Gemini defaults to project scope; the -e env gives Gemini sessions their own write attribution, and the same Docker-tier PSEUDOLIFE_MCP_NO_SPAWN=1 note as above applies):

pip install pseudolife-mcp
gemini mcp add -s user -e PSEUDOLIFE_WRITER_ID=gemini -e PSEUDOLIFE_MCP_NO_SPAWN=1 pseudolife-memory pseudolife-mcp

Or HTTP, no pip package needed:

gemini mcp add -s user -t http pseudolife-memory http://127.0.0.1:8765/mcp

Any other MCP-capable agent (Cursor, Windsurf, Zed, Copilot CLI, …) — add the generic mcpServers entry to that tool's MCP config (ops/install.sh --client generic prints both shapes ready to paste):

{
  "mcpServers": {
    "pseudolife-memory": {
      "command": "pseudolife-mcp",
      "env": {
        "PSEUDOLIFE_WRITER_ID": "mcp-client",
        "PSEUDOLIFE_MCP_NO_SPAWN": "1"
      }
    }
  }
}

What each agent gets — and what its platform can't support (hooks, per-turn discipline): the provider matrix.

Verify: run claude mcp list, codex mcp list, or gemini mcp list (the server should report connected), then ask the agent to "store a memory that this install works" and check it appears in the Stream tab of the Console at http://127.0.0.1:8765/ui/.

Preferring stdio (this is what the installer wires by default, for per-session identity)? A thin torch-free shim proxies stdio to the daemon: stdio shim · LAN sharing · backups & restore rehearsal.

Recommended agent setup (CLAUDE.md / AGENTS.md)

The server's value depends entirely on the agent using it well — this step is what makes the memory loop actually fire. The MCP server advertises the core loop through protocol-level instructions, and the session hook (one command, below) delivers the full block every session — plugin users and hook users need nothing more. If you want it in a standing file instead — or additionally, for subagent visibility (subagents read CLAUDE.md but not hook output) — append it to Claude's global ~/.claude/CLAUDE.md, Codex's global ~/.codex/AGENTS.md, Gemini's global ~/.gemini/GEMINI.md, or a per-project CLAUDE.md / AGENTS.md:

cat examples/CLAUDE.memory.md >> ~/.claude/CLAUDE.md
cat examples/CLAUDE.memory.md >> ~/.codex/AGENTS.md
cat examples/CLAUDE.memory.md >> ~/.gemini/GEMINI.md

Add-Content "$env:USERPROFILE\.claude\CLAUDE.md" (Get-Content examples\CLAUDE.memory.md -Raw)
Add-Content "$env:USERPROFILE\.codex\AGENTS.md" (Get-Content examples\CLAUDE.memory.md -Raw)

For hook-less providers this standing block is not a nice-to-have — it is the session briefing. AGENTS.md is the cross-vendor standard for standing agent instructions (Linux Foundation-governed; read by Codex, Copilot, Cursor, Gemini CLI, Zed, and 30+ others), so a per-project AGENTS.md carrying the block reaches almost every agent at once. Claude Code is the holdout — it reads CLAUDE.md — but a CLAUDE.md whose first line is @AGENTS.md imports the shared file, so one copy serves every tool.

The block (examples/CLAUDE.memory.md) teaches the loop: RECALL at the start (memory_search / memory_lesson_search / memory_fact_get / memory_world_search), CAPTURE as you go (memory_store with an honest origin, memory_fact_set for canonical facts, memory_world_set for cited external facts, source="status" for verbose logs so they stay out of the dream), REFLECT at the end (memory_outcome — the dream distils these signals into the lessons surfaced at your next session start).

One command — ops\install-hook.ps1 -Client codex (Windows, PowerShell 7) or ops/install-hook.sh --client codex (Linux/macOS) — installs the SessionStart briefing hook for the selected client (what your memory is unsure about + lessons from past work + verified world facts + where we left off, injected at every session start) and, for the Claude client, a UserPromptSubmit discipline hook: a static one-line memory reminder on every turn — recall before reviewing code, docs, or PRs, then compare memory against the files; status questions are memory questions; log outcomes. (Codex is excluded from the per-turn hook: its per-prompt hook support is unverified, and every new Codex hook needs a manual trust review.) The installer backs up ~/.claude/settings.json or ~/.codex/hooks.json and is idempotent. The manual hook JSON, the briefing budget flags, and how session episodes open/close/resume without any hooks: Episodes & sessions.

Codex hooks are experimental and off by default (and not available on Windows — use the standing AGENTS.md block there). Writing hooks.json is not enough on its own; first enable the hook engine in ~/.codex/config.toml:

[features]
codex_hooks = true

Codex hook trust: Codex also skips every new or changed hook until you review and trust its exact definition. After installing the Codex hook, start Codex, open /hooks, review the definition from ~/.codex/hooks.json, and approve it. Until then, MCP tools still work and the server-level instructions still load, but the richer session briefing is not injected.

Usage patterns

At session start — loads what you've worked on before, persistent across compactions:

memory_search("project context for X")

During work — store real decisions; skip fleeting chatter (the shipped store gate is permissive, so deliberate, durable claims only):

memory_store("Decided to use stdio transport for the MCP because no port conflicts", source="pseudolife")

When corrected — marks the old fact superseded and stores the correction; both surface in future retrieval, the new one ranked higher:

memory_supersede(
  "Provider interface uses synchronous calls",
  "Provider interface uses async calls — sync version was the v0.7 prototype only"
)

Hygiene — hard-delete (at least one filter is required for scope memory, preventing accidental wholesale deletion); for "keep the history but mark it wrong" use memory_supersede instead:

memory_forget(scope="memory", source="test-noise")
memory_forget(scope="fact", entity="test-entity")

Discovering what's in the bank: open the Cortex Console — sources, tags, episodes, and full-table views all live there. Going deeper: reranking, BM25, abstention, and trace debugging · episodes + tags · canonical facts, contenders, world facts, lessons · the consolidation workflow.

Dreaming — consolidating memories into facts

A dream distils the recent associative stream into canonical cortex facts while you're not looking: pull unconsolidated memories → extract (entity, attribute, value) → advance a cursor so nothing is reprocessed. Extraction is pluggable:

The stack ships tier 2 preconfigured (the bespoke Gemma 4 E4B extractor fine-tune in a llama.cpp sidecar, internal-only). The sweep cadence, pointing dreams at a bigger local model or at Claude Sonnet with automatic sidecar fallback, the full-corpus deep dream graph pass, and the privacy/cost trade-offs: Dreaming.

Benchmarks

The headline is the whole benchmark, not a slice: all six LongMemEval question types, 500 questions, oracle variant, run end to end through the memory (qwen-27b extraction under the v25 embedding backbone, BM25-on turn retrieval). Single pass, graded by the local Qwen3.6-27B bench judge (2026-08-03):

The cascade is a serving policy, not a fourth pipeline: answer from the consolidated facts when that channel commits, fall back to raw-turn RAG when it abstains. Overall this is a wash on accuracy at ~73% of the context — 0.690 vs 0.688 is one question in 500 on a single pass, and nobody should read it as a win. The fact spine alone answers at ~13% of RAG's token budget, at a large accuracy cost outside the types it is built for. The structure is per type:

The consolidated spine helps where a fact changes and where the answer sits inside one session; it loses where the answer must be aggregated across sessions or ordered in time, because per-fact consolidation is exactly what discards that structure. BEAM-100K reproduces the same shape independently, and adds the one decisive win: on its abstention questions the fact-spine arm scores 0.950 against naive RAG's 0.775, identical under the local judge and under an independent Opus-class judge. Setup, caveats, both bench stacks side by side, and the evidence that extraction quality is the dominant factor: Benchmarks; full methodology: evals/README.md.

Retrieval itself was re-measured on the same corpus before the v25 backbone swap (150 questions, 74,183 haystack turns, 299 gold turns; pure recall — no reader, no judge): Qwen/Qwen3-Embedding-0.6B reaches R@10 0.809 against bge-base-en-v1.5's 0.742 and the previously-shipped all-MiniLM-L6-v2's 0.572, and beats bge-base head-to-head +32/−12 at k=10 (p=0.004). Artifacts: embedder-recall-shootout-20260727.json, embedder-recall-qwen-vs-bge-20260728.json.

Cortex Console (web UI)

An operator dashboard served by the daemon itself — point a browser at http://127.0.0.1:8765/ui/ (the /health and /mcp endpoints are unchanged; the console is additive). It's a read-mostly instrument panel for seeing and steering the memory a human otherwise can't observe: Observatory (health, per-layer counts, the memory store's capacity meter, dream gauges), Cortex (canonical facts with provenance, version-history timelines, inline Accept/Discard for contested slots), World / Lessons / Episodes, Stream (live search with rerank/BM25 toggles and a ranking-trace debugger), Graph (interactive force-directed visualiser, with a review drawer that can Accept/Reject merges or — for a source file and its own bare concept, band.py ↔ band — record an implements edge instead of forcing merge-or-dismiss; proposals a background dream has already judged carry a verdict chip — accept/reject/leave with confidence, the model's reason in the tooltip — as a lead, never a decision), and Console (every safe config.yaml scalar with live-vs-restart badges, diff-preview, and atomic save).

Auth mirrors /mcp: /ui (static shell) and /health are open; /api/* requires the same PSEUDOLIFE_MCP_TOKEN bearer when one is set (the console prompts for it and stores it locally). No build step, no CDN, fully offline — vanilla ES modules + vendored OFL fonts served straight from the daemon. Developing the UI? A fixture-backed dev server (no Postgres, no torch) renders the real frontend against canned data: python -m pseudolife_memory.web.devserver → http://127.0.0.1:8770/ui/.

Capabilities at a glance

Troubleshooting

Start with curl http://127.0.0.1:8765/health — it reports the schema version, storage backend, auth state, and persist_errors (non-zero means writes are failing to reach Postgres; check docker logs pseudolife-mcp-daemon).

• The cortex stays empty (canonical facts never appear on their own). /health reporting "extractor": "none" means no extractor is configured, so the dream writes no facts and memory_fact_set is the only cortex writer — expected on the lite tier. Point the daemon at an OpenAI-compatible endpoint (Quickstart) or use the Docker tier's bundled sidecar. "extractor": "disabled" instead means dreaming itself is switched off in config.

• Lite daemon refuses to start on Windows with a message about the data path: the embedded Postgres runtime needs an ASCII-only data directory. Set PSEUDOLIFE_MCP_DATA_DIR to one (e.g. C:\pseudolife-data) — Configuration.

• First build is slow / big. The daemon image (~5.0 GB, several minutes to build) bakes in CPU torch and the embedding weights (Qwen3-Embedding-0.6B plus MiniLM); the extractor sidecar adds a ~5.3 GB model download on its first build. Every start after that is offline and fast — if a rebuild is re-downloading models, the Docker layer cache was pruned.

• Daemon unreachable after wsl --shutdown (Windows): the host port forward is gone — docker restart pseudolife-mcp-daemon re-establishes it.

• Docker eating RAM (Windows): the WSL2 VM (Vmmem) claims up to ~50% of host memory by default. Copy ops/wslconfig.example to %USERPROFILE%\.wslconfig, tune memory=, then wsl --shutdown.

• Port already in use: the stack binds 127.0.0.1:8765 (daemon) and 127.0.0.1:5433 (Postgres). Change the host side in ops/docker-compose.yml if either collides.

• Console shows "offline" / Unauthorized: "offline" means the daemon isn't reachable (see above); a 401 prompt means it runs with PSEUDOLIFE_MCP_TOKEN — paste that token into the Console's Token dialog.

• The coding agent doesn't see the tools: claude mcp list or codex mcp list should show pseudolife-memory ✓ connected. If not, re-check the URL (http://127.0.0.1:8765/mcp — the /mcp path matters) and the bearer header when a token is set. The daemon preloads the embedder on a warmup thread at start (~5–10 s); a very early first call can race it and take a few seconds.

Uninstall

Lite tier: remove the MCP registration (claude mcp remove pseudolife-memory / codex mcp remove pseudolife-memory), then pip uninstall pseudolife-mcp. If you also want the bank gone, delete the per-user data directory (%LOCALAPPDATA%\pseudolife-mcp on Windows, ~/.local/share/pseudolife-mcp on Linux, ~/Library/Application Support/pseudolife-mcp on macOS — or wherever PSEUDOLIFE_MCP_DATA_DIR points). Back it up first: pseudolife-mcp backup works on lite too.

Docker tier — deletion is deliberate at every step:

# 1. Optional: take a final backup first (ops/backup.ps1 or ops/backup.sh).
# 2. Stop and remove the containers (volumes survive this).
docker compose -f ops/docker-compose.yml down
# 3. Remove the MCP registration.
claude mcp remove pseudolife-memory
codex mcp remove pseudolife-memory
gemini mcp remove pseudolife-memory -s user
# 4. Only when you're sure: delete the data volumes (THIS is the memory).
docker volume rm pseudolife-mcp-bank pseudolife-mcp-state

Host-process installs: also unregister the logon task (Unregister-ScheduledTask -TaskName "Pseudolife-MCP Daemon") and remove the SessionStart briefing hook — plus, Claude client, the UserPromptSubmit discipline hook — from ~/.claude/settings.json and/or ~/.codex/hooks.json (a timestamped .bak-* sits next to each edited file).

Testing

pip install -e .[dev], then pytest tests/. The suite covers every layer, from the MemoryService surface to the Cortex Console REST API; model-heavy pieces are stubbed so it stays fast and offline. The PG-backed suites each target a throwaway per-run pseudolife_memory_test_<pid> database on the bundled dev container (never your real bank; concurrent runs can't collide), dropped on exit, and skip cleanly without Postgres. Full dev setup: CONTRIBUTING.

What's not built yet

• Reflection via MCP sampling — would let the dream borrow Claude itself as the extractor; Claude Code doesn't yet support it.

• Cross-machine sync — memory lives on one PC's disk; syncing via rclone / syncthing is left as an exercise.

• Automated world-knowledge ingestion — populating the world cortex from the live web needs a web-fetch tool the standalone server doesn't ship; an agent with web access can automate the fetch+cite step today via memory_world_set.

Support

Solo-maintained, best-effort. One person builds, tests, and runs this; there is no support contract and no response-time commitment. That said, issues are read and most get an answer.

• Something is broken → open a bug report. The form asks for your /health output, schema version, install tier, and client, because those four answer most questions before any back-and-forth.

• Something is missing → open a feature request. Say what you were trying to do, not only what to add.

• A security problem → do not open a public issue. Use GitHub's private vulnerability reporting — SECURITY.md. Memory integrity specifically: security posture.

• Sending a patch → CONTRIBUTING and CODE_OF_CONDUCT. The bar is "surgical, tested, and explained", not "big".

If you need someone to call, Comparison — use something else if names vendors who sell support.

License

Apache-2.0 — see LICENSE and NOTICE.