Krusch Context MCP
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Krusch Context MCP remember our decision to use SQLite locally and Postgres in production"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Krusch Context MCP

Persistent working memory for AI coding agents in 5 MCP verbs (
~350schema tokens), backed by built-innode:sqliteWAL + PorterFTS5+ local1024dembeddings (PostgreSQL 16 + pgvectoroptional). Stores architectural decisions and invariants with SHA-256 line-span drift detection and$0.00zero-LLMRaw-RAGindexing, scoring90.26%accuracy and95.77%evidence recall across1,540ACL 2024 SnapLoCoMoquestions (81.50%@$1.35on model-matchedGPT 5.6 Lunaacross600DolphinBenchtasks;91.17%uploaded submissionUUID c047b063queued; all self-run in my lab with raw SHA-256 logs published, no third-party reproduction yet).
π Architecture & Benchmark Papers: Beyond Flat Vector RAG: What Makes
krusch-context-mcpSpecial (docs/WHAT_MAKES_IT_SPECIAL.md) Β· Paper #27: Return on Memory (DolphinBench&LoCoMo) (PDF) Β· Paper #26: Open-Weights Memory Ablations ($0.00).
Krusch Context MCP gives AI coding agents (Cursor, Claude Code, Windsurf, Antigravity) persistent working memory across sessions. It captures architectural decisions, invariants, lessons, and bug diagnoses, warns on near-duplicate memories, maintains temporal lineage when facts are superseded or invalidated, and audits diffs against active constraints.
π¬ 90-Second Narrated Walkthrough (1080p)

βΆοΈ Stream 1080p HD Walkthrough (
01:31, with audio) Β· Interactive Player onkrusch.devΒ· Local MP4 (15.6 MiB) Β· Closed Captions (.srt)
Related MCP server: io.github.cdnsteve/sugar
π« What This Is Not
Not a codebase AST or Git indexer: Code symbol search, call graphs, and Git DAG traversal belong in
krusch-gitor your IDE's native search.Not a 61-tool cafeteria: Collapsed to strictly 5 canonical verbs (~350 prompt tokens) for boring reliability.
Not a cloud SaaS platform: Runs 100% locally on your machine with zero external cloud dependencies.
Not a monolithic domain suite: Legal compliance (
krusch-law), document ingestion (krusch-nexus), and contract graphs (krusch-biz) live in separate companion repositories.
β‘ 30-Second Quickstart
Ask your coding agent (Claude Code, Codex, Cursor, Windsurf, or Antigravity):
Read https://raw.githubusercontent.com/kruschdev/krusch-context-mcp/main/INSTALL.md and set up krusch-context-mcp on this machine.Or run once inside your project repository (requires Node.js >= 22.0.0):
npx krusch-context-mcp initThis command will:
Validate Node >= 22.0.0 and initialize
.agent/context.dbvianode:sqlite.Clear stale MCP tool schemas from local IDE caches.
Create your project
.envwith sensible defaults.Seed initial project context and run a diagnostic health check.
Print copy-paste JSON configurations for Cursor, Claude Code, and Claude Desktop.
π¬ 5-Minute External Engineer Verification (Zero Docker, Zero API Keys)
Verify the production SQLite engine, all 155 unit and contract tests, and the cryptographic zero-leakage benchmark verifiers locally in under a minute with zero external services or API keys:
git clone https://github.com/kruschdev/krusch-context-mcp.git
cd krusch-context-mcp
npm ci
# 1. Run all 155 unit & contract tests on built-in node:sqlite (zero Docker, zero API keys)
npm test
# 2. Run the 5-part static engine, JS Proxy oracle-trap, and SHA-256 audit-log verifiers
npm run bench:beam:verify
npm run bench:beam:verify:longFull dataset-level reproduction steps (including frozen
0o444SQLite manifests and raw SHA-256 receipts) are documented inbenchmarks/LOCOMO_EMPIRICAL_REPORT.mdandbenchmarks/BEAM_EMPIRICAL_REPORT.md.
π οΈ The 5-Verb Agent Loop
Krusch Context MCP exposes strictly 5 canonical verbs designed to fit into standard coding workflows:
Verb | Short Alias | Purpose |
|
| Pulls active memories, steering rules, and project state briefings within a strict |
|
| Writes episodic facts and steering nuggets. Detects near-duplicates ( |
|
| Updates stale knowledge ( |
|
| Pre-commit auditor that checks proposed diffs against active project invariants (max 1β3 findings). Trigger defaults to |
|
| Reports storage mode, memory counts by closed taxonomy, and 30-day TTL decay review. |
π€ Recommended Agent Protocol
Coding agents should interact with memory at specific lifecycle boundaries:
βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
β 1. SESSION START β
β Agent calls retrieve(query: '*', include_state: true) β
β -> Obtains active invariants, recent decisions, blockers β
ββββββββββββββββββββββββββββββββ¬βββββββββββββββββββββββββββββββ
β
ββββββββββββββββββββββββββββββββΌβββββββββββββββββββββββββββββββ
β 2. DURING WORK β
β Agent calls remember(content: '...', category: '...') β
β -> If near-duplicate returned, agent calls revise(...) β
ββββββββββββββββββββββββββββββββ¬βββββββββββββββββββββββββββββββ
β
ββββββββββββββββββββββββββββββββΌβββββββββββββββββββββββββββββββ
β 3. PRE-COMMIT / PRE-EDIT β
β Agent calls nudge(trigger: 'pre_commit') β
β -> Audits code against active invariants (max 3 findings)β
βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββπ‘οΈ Safe Memory Writes: Closed Taxonomy & Deduplication
To prevent memory hallucination and database pollution:
Closed Taxonomy: Every write must use one of 5 categories:
decision: Architectural choices, design directions, trade-offs.invariant: Non-negotiable rules (e.g., "Use node:sqlite, zero native compiles").bug: Solved defects, regressions, and root-cause analyses.lesson: Tactical insights and framework discoveries.blocker: Active dependencies or external obstacles.
Near-Duplicate Detection: If a proposed memory matches an existing active record ($\ge 0.85$ cosine similarity), the memory is saved with a warning proposing
revise(action: 'supersede', target_id: ...). This protects contrasting rules (e.g., "Allow CORS" vs "Do not allow CORS") while flagging twin facts.Compulsory Invalidation Reasons: Calling
revise(action: 'invalidate')strictly requires a non-emptyreason.Focused Audits:
nudgecaps findings at 3 with concrete evidence, rejectingevery_turntriggers to eliminate auditor nagware.Span-Grounded Provenance & Drift Self-Healing: Passing
provenance: { file, locator, quoted_sentence }toremembercomputes a normalized SHA-256anchor_hashand line range (start_line..end_line). On subsequentretrieve(include_state: true)calls, the engine verifies the span on disk, automatically healing line numbers when code shifts above it, or flagging[DRIFTED]when the underlying code changes.
π§ Embedding Reality & Offline Mode
Zero-GPU Default: If neither Ollama nor an API key is present, the engine runs 100% offline using deterministic keyword extraction, recency scoring, and heuristic tag indexing.
Local Ollama (Optional): Set
OLLAMA_URL="http://127.0.0.1:11434"withEMBED_MODEL="snowflake-arctic-embed2"(8,192-token context,1024dims, ~664 MBVRAM, asymmetricquery:retrieval via/api/embed; also supportsqwen3-embeddingMRL1024d,nomic-embed-text, and legacybge-large).Remote Cloud (Optional): Set
OPENROUTER_API_KEY="sk-..."withEMBED_MODEL="baai/bge-large-en-v1.5"(or any1024-dim OpenRouter embedding model) for zero-local-VRAM embeddings.
π When Do You Need PostgreSQL?
Use SQLite (Default): Perfect for single developers, local IDE sessions, and projects with thousands of decisions, featuring compact
Float32Arraybinary vector blobs (4 KB/row) and an external-content Porter-stemmedFTS5lexical index. Zero Docker, zero setup.Use PostgreSQL (
STORAGE_MODE=postgres): Required only when scaling to multi-agent swarms across different machines needing centralized persistence and server-side pgvector HNSW indexing.
π Migration from v1.6 / v1.7
Tool Aliases: Legacy tool names (
add_memory,search_memory,compile_state,supersede_memory,invalidate_memory,proactive_nudge) are automatically aliased to the 5 verbs with a deprecation notice.Database Path: v1.7 used
.agent/memory.db. v1.8+ uses.agent/context.db. Runnpx krusch-context-mcp initto migrate.See docs/MIGRATION.md for the complete mapping table.
π§© Sibling Architecture
βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
β AI Coding Agent (Cursor / Claude) β
ββββββββββββββββββββββββββββββββ¬βββββββββββββββββββββββββββββββ
β
βββββββββββββββββ΄ββββββββββββββββ
βΌ βΌ
βββββββββββββββββββββββββββββββ βββββββββββββββββββββββββββββββ
β krusch-context-mcp (v2.0) β β krusch-git (External) β
β Project Memory & Steering β β Codebase RAG & AST Search β
β (5 Canonical Verbs) β β (7 Specialized Tools) β
ββββββββββββββββ¬βββββββββββββββ βββββββββββββββββββββββββββββββ
β
βΌ
βββββββββββββββββββββββββββββββ
β .agent/context.db β
β (node:sqlite, Node β₯22) β
βββββββββββββββββββββββββββββββOther specialized tools (krusch-nexus, krusch-law, krusch-biz) run as independent MCP servers in their own repositories.
π» IDE Configuration
Cursor (.cursor/mcp.json)
{
"mcpServers": {
"krusch-context": {
"command": "npx",
"args": ["-y", "krusch-context-mcp"]
}
}
}Claude Code
claude mcp add krusch-context -- npx -y krusch-context-mcpClaude Desktop (claude_desktop_config.json)
{
"mcpServers": {
"krusch-context": {
"command": "npx",
"args": ["-y", "krusch-context-mcp"]
}
}
}π External Benchmarks & 3-Category Verification Taxonomy
Ecosystem Verification Taxonomy: Evaluated across 335,000+ traces and 14 external benchmark suites in my lab, with published SHA-256 audit logs and reproducible evaluation artifacts, separating (1) Maintainer-Reviewed & Merged Upstream (
github-actions[bot]CI-Verified) such asRouteWorks/RouterArenaPR #169 (merged by@yl231intomain @ 844e93b;0.7263CI score across8,400/8,400live receipts, leaderboard table row queued for next batch ranking refresh), (2) Uploaded & Queued Leaderboard Submissions ondolphinbench.ai(status: "queued"awaiting leaderboard acceptance, led byUUID c047b063at91.17%[547/600@$24.54] and open-weights stockUUID 288671adat54.17%[325/600@$0.00]), and (3) Self-Run Clean-Room Evaluations (Published SHA-256 Audit Logs; Third-Party Reproduction: None Yet) inkrush420/sovereign-g4-benchmarks. No outside party has re-run theLoCoMo,DolphinBench, orBEAMevaluations yet; reproduction issues are welcome.
Official DolphinBench (91.17% Queued UUID c047b063 @ $24.54, 90.67% Clean-Room Grounded v0.3 @ $30.54 & 57.33% Open-Weights @ $0.00): Return on Memory
Evaluating all 600/600 multi-app workspace tasks across 13,539 conversational sessions (1,500,265 o200k_base tokens) under the official openai/gpt-5.6-sol judge (28 official 600-task evaluations = 16,800 official openai/gpt-5.6-sol traces across 6 model families: 8 uploaded & queued on dolphinbench.ai + 20 clean-room controls = 28/28 submission.validate passed), my byte-identical 0o444 read-only frozen Zero-LLM Raw-RAG (256/32-token windows) + Porter-FTS5 BM25 + snowflake-arctic-embed2 (1024d) 4-Way RRF node:sqlite store ($0.00 ingestion) achieves 91.17% (547/600 @ $24.54, Gemini 4 Argon Low, uploaded dolphinbench.ai submission UUID c047b063, status: "queued" awaiting leaderboard acceptance; exceeds current 70.67% published leaderboard entry in independent 600/600 evaluation), 90.67% (544/600 @ $30.54, Argon Low + Grounded v0.3, self-run clean-room evaluation with highest Riley slice 181/200 = 90.50% and published SHA-256 audit logs; Argon Low Oracle@2 = 94.67% [568/600], Argon Oracle@4 = 96.83% [581/600], Global Oracle@28 = 98.33% [590/600]), 81.50% (489/600 @ $1.35, 1.57x faster, +10.83 pp > published 70.67% Mem0 entry @ 71.1x lower cost) model-matched on OpenAI GPT 5.6 Luna (High + Grounded) (81.33% Std.), and 57.33% (344/600 @ $0.00, Wave-6 krush420/gemma4-31b-sre-lora + Grounded, highest open-weights score in self-run 28-run evaluation; 56.67% Stock + Grounded; 54.17% [325/600] stock submission UUID 288671ad uploaded & queued on dolphinbench.ai; $0.00 Open-Weights Oracle@17 = 83.17% [499/600]):
Agent Reader + Memory Substrate | Overall ( | Persona Breakdown ( | Checks / Key Delta | Total Cost |
|
|
|
|
|
|
|
|
|
|
|
|
| Mech |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
Current Published Leaderboard Entry: |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| Scaling & domain controls: |
|
|
|
|
|
|
Four Return on Memory Scaling Laws & 4-Vertex Pareto Frontier: (1)
98.33%(590/600:Morgan 196,Alex 199,Riley 195)Global Oracle@28retrieval sufficiency (<= 1.67%zero-LLM Raw-RAG indexing miss) across the frozen0o444SQLite store (94.67%[568/600]Argon Low Oracle@2,96.83%[581/600]Argon Oracle@4, and83.17%[499/600]$0.00Open-WeightsOracle@17(+12.50 ppabove published70.67%Mem0entry)) and controlled memory-vs.-reader attribution via model-matchedGPT 5.6 Luna (High)at81.50%(489/600Grounded) /81.33%(488/600Std.) @$1.35(52.0%[+10.67 pp, $p = 5.96 \times 10^{-9}$] of my+20.50 pplead over the70.67%publishedMem0baseline comes purely from$0.00Raw-RAG memory,48.0%[+9.83 pp] fromArgon Low), establishing a 4-vertex100%Sovereign Raw-RAGPareto frontier ($0.00[57.33%gemma4-31b-sre-lora/54.17%Stock] β$1.10[76.67%Luna Low] β$1.35[81.50%Luna High + Grounded] β$24.54[91.17%Argon Low]); (2)4.19xsuperlinearLBF=4+multiplier (89.33%[67/75]Argon Lowvs.21.33%[16/75]30B&Gemma 4 31BStock,16.75xvs.8B); (3) Scale-dependent Goldilocks reasoning &+22.00 pp/+18.83 pp($p = 1.35 \times 10^{-16}$) post-training domain specialization (2Γ2Thinking Γ Search$\Delta\Delta = +3.17\text{ pp}, p = 0.0320$ on Argon;+2.17 ppthinking lift,+2.50 ppGrounded lift, &+3.17 ppWave-6 QLoRA+DPO lift onGemma 4 31B); and (4) Flatter corpus-entropy decay (-4.00 ppArgon Low + Grounded v0.3[94.5%β90.5%, highestRileyslice181/200] /-7.00 ppArgon Low/-3.50 ppArgon MediumMorganβRileyvs.-10.00 pponMem0[78.0%β68.0%,-12.00 pptoAlex66.0%] and-32.50 pponMiniMax M3 + Hindsight).Verified Upstream Queue & Open Artifacts:
8sovereign submission.ziparchives (Argon LowUUIDc047b063-822c-49fb-8b36-27c3763d6ca7[91.17%/547/600], SHA-25680a199a60aef65f0d963d0402a2e3b0af99b82ed63e2f422001234b6ed770f0b;Argon MediumUUID29389157-b01b-42b5-8193-17d9a496f580[89.17%], SHA-2569a7fa41fb3d1cf5f71f0c3cf74a0c97f8f39d50e26a7dd484c323f7719ecb7a0; uploaded & queued open-weights stockGemma 4 31BUUID288671ad-afe0-40a3-93af-b834c9bbd306[54.17%/325/600], SHA-2562a23c2a023473a6642f5a61f1d99ff569f3d50ac53e60576f8195eef659c254b; plus30b_wave4,30b_stock,120b_wave4,120b_stock, and8b_wave4) holdstatus: "queued"ondolphinbench.aiawaiting maintainer merge (dolphinbench.ai/leaderboard/results.jsoncurrently lists the13commercial cloud baselines), and all28/28official archives (8queued flagships +20clean-room controls) passedsubmission.validate(error_code: null). Read Paper #27 (HTML) Β· Paper #27 (PDF) Β· Paper #26 (Local AI Ablation) Β·49SHA-256 Hugging Face Audit Logs across64files (48raw JSON +1live PR #169 receipt bundle,95/95ecosystem gates) (krush420/sovereign-g4-benchmarks).
Official Snap LoCoMo (ACL 2024, 1,540/1,540 QA Probes)
Zero-gaming, clean-room evaluation across all
10multi-month conversations (5,882turns,1,515256/32-token Raw-RAG windows) and1,540/1,540standard Category 1β4 QA probes (snap-research/locomoSHA-25679fa87e9...ea698ff4) using the unmodifiedSovereignMemoryStore(0o444read-only frozen SQLite stores,$0.00/0-LLM ingestion via localsnowflake-arctic-embed21024d+ Porter FTS5 4-Way RRF) and verbatimmem0ai/mem0@aae5989eANSWER_PROMPT_ZEP+ACCURACY_PROMPT(gpt-4o-minitemperature=0.0judge):argon_matched(9,983meancl100ktokens,3.01Γcompression):90.26%(1,390/1,540) judged accuracy (94.17%Single-Hop,92.83%Temporal,84.04%Multi-Hop,65.62%Open-Domain),95.77%ground-truthdia_idevidence recall (98.87%Single-Hop,97.98%Temporal),63.97%official Porter-stemmed token F1,181.8 msmedian local retrieval, and+19.86 ppover LivingBrain / SuperLocalMemory V3.3's zero-LLM mode (70.4%) (trace_argon_matched.jsonlSHA-25668363e5f7c6cf733b42681c6e73911b129e71a43a41ac385cf56daf96a80d70d).argon_tight(4,465meancl100ktokens,6.73Γcompression,<0.5Γpeer token budget):89.68%(1,381/1,540) judged accuracy,91.05%dia_idrecall (96.37%Single-Hop,95.25%Temporal),63.11%official F1,186.4 msmedian retrieval, and92.66%(1,427/1,540)Oracle@2across both frozen runs (trace_argon_tight.jsonlSHA-256e48f3cc00f690eda2d8345283fc822f05527eb95844aa923001f74a2b82f87f1;5/5zero-leakage &BlindMappingGuardchecks passed; full report).
Official ICLR 2026 BEAM (100Kβ10M Tokens, 2,000/2,000 Probes)
Closed-system full-suite evaluation across all
100conversations (~178.34Mtokens) and2,000/2,000questions (100K,500K,1M,10Msplits) onnode:sqlite+snowflake-arctic-embed2(8Kctx) in a fixed~8Kprompt budget: reaches92.58%(100K) &93.00%(10MIE) recall (78.67%4-split weighted), exhibits zero E2E QA degradation from100Kβ1M(70.60%β71.82%β72.86%onhermes3), and outperforms cloudpast.dev(openai/gpt-5.6-luna) on Contradiction Resolution across all4/4splits and on10MMulti-Session Reasoning across both cross-family referees (29.54%/38.33%vs.28.17%) with10/10zero-leakage verification (full report).
π Documentation & Specifications
Canonical Tool Reference: Generated directly from live schemas (
npm run docs:generate).Architecture & Failure Modes: 2-page specification covering schemas, indexes, and
v2.0.0multi-scale retrieval invariants.Setup & Operations Guide: Zero-Docker setup and optional configurations.
Migration Guide: Step-by-step v1.5 β v1.6 β v1.7 β v1.8 β v1.9.0 β v2.0.0 mapping.
Episodic Memory Guide: Deep dive into the closed taxonomy and lifecycle.
Changelog: Version release notes.
Official Snap LoCoMo Empirical Report: Clean-room
1,540/1,540-probe ACL 2024 evaluation (90.26%matched /89.68%tight /92.66%Oracle@2,95.77%dia_idrecall,$0.00zero-LLM ingest) and JSON receipts (benchmarks/locomo/).Official ICLR 2026 BEAM Empirical Report: Full
100-conversation (~178.34M-token),2,000/2,000-probe methodology, per-ability tables, and10/10zero-leakage verification gates.Official DolphinBench Whitepapers & Clean-Room Audit Logs: Paper #27 (HTML), Paper #27 (PDF), Paper #26, and all
28OfficialDolphinBenchruns (16,800officialgpt-5.6-soltraces across6model families,8uploaded & queued ondolphinbench.ai+20clean-room controls =28/28submission.validatepassed, led by91.17%[547/600@$24.54] uploadeddolphinbench.aisubmissionUUID c047b063-822c-49fb-8b36-27c3763d6ca7[status: "queued"awaiting leaderboard acceptance; exceeds current70.67%published leaderboard entry in independent600/600evaluation],90.67%[544/600@$30.54] self-run clean-roomArgon Low + Grounded v0.3[highestRileyslice181/200 = 90.50%, published SHA-256 audit logs],89.17%Argon MediumqueuedUUID 29389157-b01b-42b5-8193-17d9a496f580, &57.33%[344/600@$0.00] Wave-6krush420/gemma4-31b-sre-lora+Grounded[highest open-weights score in self-run 28-run evaluation;56.67%Stock+Grounded;54.17%(325/600) stock submissionUUID 288671ad-afe0-40a3-93af-b834c9bbd306uploaded & queued ondolphinbench.ai];Global Oracle@28 = 98.33%,$0.00Oracle@17 = 83.17%;49SHA-256 Hugging Face audit logs across64files) inkrush420/sovereign-g4-benchmarks.Evaluation Baseline Notes: Preliminary benchmark fixtures and token-budget metrics.
π§ͺ Testing
# Run full unit & contract test suite (155 tests, 100% SQLite, zero Docker)
npm test
# Check storage and memory health
npm run healthLicense
MIT Β© kruschdev
Available Tools
5 toolskrusch_context_healthBRead-onlyIdempotent
Operational health check, memory counts by closed taxonomy, storage mode, and 30-day TTL decay review.
Inputs: project.
krusch_context_nudgeAIdempotent
Invariant auditor and alignment feedback loop. Checks proposed code diffs or actions against active project invariants, and adjusts rule weights based on developer feedback.
Inputs: code, hook, action, project, +4 more.
krusch_context_rememberB
Unified write API for episodic memory and persistent steering nuggets. Includes automatic near-duplicate detection and provenance tracking.
Inputs: content (required), key, tags, force, +3 more.
krusch_context_retrieveARead-onlyIdempotent
Universal context retrieval tool. Pulls active project memories, steering rules, and state briefings respecting token budget limits.
Inputs: query (required), mode, project, category, +2 more.
krusch_context_reviseADestructiveIdempotent
Unified knowledge revision API. Supports temporal superseding (updating stale knowledge with lineage) and explicit invalidations (revoking obsolete rules with mandatory reason).
Inputs: action (required), key, reason, content, +4 more.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelogβ¦
TDQS
Scored across 5 tools
Retrieve (read), remember (write new), nudge (audit), and health (ops) are clearly distinct. The only soft boundary is remember vs revise, since both mutate knowledge, but descriptions differentiate creating new memories from superseding/invalidating existing ones.
All tools share a consistent krusch_context_* namespace with a single descriptive suffix, making the set predictable. Minor deviation: retrieve/remember/revise/nudge are verbs but health is a noun, breaking the verb-based pattern slightly.
Five tools is well-scoped for a context/memory server: one per lifecycle concern (read, write, revise, audit, health). Each tool earns its place with no redundancy or bloat.
The surface covers the core memory lifecycle: retrieval, creation with dedup, temporal revision/invalidation, invariant auditing, and health inspection. Minor gaps remain, such as an explicit forget/delete operation or a targeted memory search/listing tool.
Maintenance
Related MCP Connectors
Shared memory for coding agents. Stop re-explaining your codebase every session.
Shared, scoped, reviewable team memory for AI coding agents.
Persistent, inspectable memory for AI agents with lineage, correction, and a hosted MCP endpoint.
Persistent engineering memory designed to follow developers across coding agents.
Related MCP Servers
- AlicenseAqualityBmaintenancePersistent memory for AI coding agents, storing decisions, bug fixes, conventions, and discoveries in a local SQLite database and automatically recalling them when relevant. Works with Claude Code, Codex, Cursor, Gemini CLI, and other MCP-compatible agents.224MIT
- FlicenseNot gradedqualityAmaintenanceEnables AI coding agents to read and write persistent local memory during sessions, storing and semantically searching project decisions, preferences, error patterns, guidelines, and cross-project standards from SQLite stores on the user's machine. An optional companion server also exposes an autonomous task queue for executing queued work.-
- FlicenseNot gradedqualityAmaintenanceEnables AI coding agents to read and write persistent memory directly during sessions, storing decisions, preferences, error patterns, research, and cross-project guidelines in local SQLite databases. Supports semantic search so relevant project and global context can be recalled by meaning, fully offline and without API keys.-
- FlicenseNot gradedqualityAmaintenanceEnables AI coding agents to store, search, and recall persistent project-specific and cross-project context β decisions, preferences, error patterns, and guidelines β from a local-first SQLite memory store with semantic search, so knowledge survives across sessions. An optional companion task server lets agents queue and autonomously execute work using that same memory.-