Offre à un client IA une mémoire vectorielle auto-apprenante pour stocker des patterns, effectuer des recherches sémantiques et améliorer le classement grâce aux retours d'expérience.
Aussi connu sous ruvnet/agentdb
- Étoiles
- 99
- Outils
- —
- Téléchargements, 30 jours
- —
- Dernière version
- —
- Dernier commit
- 11 nov. 2026
- Licence
- MIT
Qu'est-ce que AgentDB MCP ?
Offre à un client IA une mémoire vectorielle auto-apprenante pour stocker des patterns, effectuer des recherches sémantiques et améliorer le classement grâce aux retours d'expérience.
Résumé généré à partir du README du projet
À propos du MCP server AgentDB
AgentDB permet aux développeurs qui construisent des applications intelligentes de fournir aux agents IA un conteneur cognitif auto-apprenant. Il fonctionne comme une mémoire vectorielle sous forme de fichier unique qui stocke des patterns, des skills et du raisonnement causal au sein d'un fichier .rvf. Contrairement aux bases de données vectorielles standard qui ne stockent que des embeddings, ce système utilise un bandit Thompson Sampling pour observer quels résultats un agent utilise réellement, lui permettant d'améliorer la qualité de recherche jusqu'à 36 % uniquement grâce aux retours d'expérience.
Les utilisateurs peuvent l'intégrer en tant que bibliothèque npm pour des applications Node.js personnalisées ou utiliser le MCP server pour connecter 41 outils spécialisés directement à des clients comme Claude Code, Cursor ou Cline. Le serveur donne accès à des capacités telles que agentdb_pattern_store, agentdb_pattern_search et agentdb_reflexion. Il s'exécute localement dans Node.js, dans le navigateur via WASM ou dans des environnements edge, sans nécessiter de clés API externes ni d'abonnements mensuels. Le moteur sous-jacent RuVector en Rust garantit des performances élevées pour les recherches vectorielles HNSW et la recherche hybride.
Ce que vous pouvez faire avec
- 1Connecter la mémoire aux clients LLMIntégrez une bibliothèque de skills sophistiquée et une mémoire épisodique directement dans votre flux de travail d'assistant de code actuel.
- 2Stocker des patterns cognitifs complexesSauvegardez des patterns d'exécution réussis et des métadonnées dans un fichier unique et portable pour une mémoire agentique à long terme.
- 3Effectuer des recherches sémantiques hybridesRécupérez des informations en combinant la correspondance exacte par mots-clés et l'intention par vecteurs denses.
Extrait du README du projet. Chaque cas d'utilisation est vérifié par rapport à une citation du document.
Comment installer AgentDB MCP
Formats vérifiés le 10 nov. 2026Ajouter à CursorAjouter à GooseInstaller AgentDB MCP dans Claude Code
$ claude mcp add agentdb -- npx -y agentdbInstaller AgentDB MCP dans Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"agentdb": {
"command": "npx",
"args": [
"-y",
"agentdb"
]
}
}
}Installer AgentDB MCP dans VS Code
.vscode/mcp.json
{
"servers": {
"agentdb": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"agentdb"
]
}
}
}Installer AgentDB MCP dans VS Code CLI
$ code --add-mcp '{"name":"agentdb","type":"stdio","command":"npx","args":["-y","agentdb"]}'Installer AgentDB MCP dans Claude Desktop
claude_desktop_config.json
{
"mcpServers": {
"agentdb": {
"command": "npx",
"args": [
"-y",
"agentdb"
]
}
}
}Installer AgentDB MCP dans Codex
$ codex mcp add agentdb -- npx -y agentdbInstaller AgentDB MCP dans Codex config.toml
~/.codex/config.toml
[mcp_servers.agentdb] command = "npx" args = ["-y", "agentdb"]
Installer AgentDB MCP dans Gemini CLI
$ gemini mcp add -s user agentdb npx -- -y agentdbInstaller AgentDB MCP dans Gemini settings.json
~/.gemini/settings.json
{
"mcpServers": {
"agentdb": {
"command": "npx",
"args": [
"-y",
"agentdb"
]
}
}
}Vérifications automatisées
Exécuté le 12 nov. 2026Rapport complet →A passé nos vérifications automatisées. Il ne s'agit pas d'un audit de sécurité : lisez le code et donnez au serveur l'accès le plus restreint dont il a besoin. Fonctionnement des vérifications
- Dépôt source lié et accessibleRéussi
- Licence open source (OSI)Réussi
- Commit ou version publiée au cours de l'année écouléeRéussi
- Nom du package non proche d'un package populaireRéussi
- L'endpoint distant utilise HTTPSNon vérifié
- Les outils destructifs sont étiquetésNon vérifié
- Aucune instruction cachée destinée au modèleRéussi
- Aucun avis critique dans le package ou ses dépendancesNon vérifié
README
Voir sur GitHubAgentDB
Vector memory that gets smarter every time your agent uses it.
A single-file cognitive container — vectors, indexes, learning state, and a cryptographic audit trail in one .rvf. Self-learning search improves up to 36% from feedback alone, with no manual tuning. Runs in Node, the browser, edge runtimes, and offline.
Explore the wider ecosystem
Building agents that remember? Explore the wider ecosystem.
Explore Cognitum One · Try ruOS, an agentic desktop in your browser.
Why AgentDB?
Most vector databases store embeddings and call it done. AgentDB watches which results your agent actually used, learns from that signal, and ranks the next query better. The bandit underneath also picks the right RL algorithm, the right compression tier, and the right pattern weighting on its own — so the database itself gets sharper while you focus on the agent.
The name: a database that thinks like an agent — episodic memory, skill library, causal reasoning, and a learning loop, all in one file. Built by
rUvon theruvectorRust engine.
What AgentDB Does
Self-Learning Vector Memory
Agent ──► AgentDB (.rvf) ──► HNSW search ──► top-k results
│ │
▼ ▼
recordFeedback(id, reward) ◄── agent uses some, ignores rest
│
▼
Bandit re-tunes ranking / RL choice / compression ──► next query is smarter
3 lines to self-learning search:
const backend = await SelfLearningRvfBackend.create({ learning: true, storagePath: "./my.rvf" }); const results = await backend.searchAsync(query, 10); // search backend.recordFeedback(results[0].id, 0.9); // learn — next search is smarter
Quick Start
Node.js 20.9.0 or newer is required, matching the patched sharp runtime used by local Transformers embeddings and better-sqlite3 12. Node 18 is no longer supported.
There are three ways to use AgentDB depending on what you're building. Pick whichever matches your stack:
| npm library | CLI | MCP server | |
|---|---|---|---|
| What you get | TypeScript / JS API for any Node app | agentdb binary, scriptable from any shell |
41 tools callable from Claude Code, Cursor, Cline, etc. |
| Install | npm i agentdb |
npx agentdb … (no install) |
claude mcp add agentdb -- npx agentdb mcp start |
| Best for | Embedding the engine in your own code | Quick experiments, CI scripts, ad-hoc memory | Plugging memory + learning into an LLM agent |
Path A — npm library
npm install agentdb
import { SelfLearningRvfBackend } from 'agentdb/backends/self-learning';
const db = await SelfLearningRvfBackend.create({
dimension: 384,
learning: true,
storagePath: './memory.rvf',
});
// Use your embedding model here; any 384-dim Float32Array works.
const embedding = Float32Array.from({ length: 384 }, (_, i) => Math.sin(i));
await db.insertAsync('doc1', embedding, { text: 'Hello world' });
const hits = await db.searchAsync(embedding, 5);
db.recordFeedback(hits[0].id, 1.0); // it was useful — db gets smarter
Path B — CLI in 10 seconds
# Try it without installing (creates ./agentdb.db)
npx agentdb init
npx agentdb reflexion store "session-1" "implement_auth" 0.95 true "Used OAuth2 with PKCE"
npx agentdb reflexion retrieve "authentication" --k 5
Path C — MCP server (Claude Code, Cursor, etc.)
claude mcp add agentdb -- npx agentdb@latest mcp start
That registers 41 MCP tools — agentdb_pattern_store, agentdb_pattern_search, agentdb_hierarchical_store, agentdb_causal_edge, agentdb_skill_library, agentdb_reflexion, etc. They call the same engine the npm library does, just over Claude's tool-calling surface.
What You Get
| Capability | Description |
|---|---|
| 🧠 Self-Learning Search | Up to +36% search quality from feedback alone — Thompson Sampling bandit re-tunes ranking, RL choice, and compression tier with zero manual config |
| 🐝 Cognitive Memory | 6 human-inspired patterns — episodic replay (Reflexion), skill library, causal reasoning, hierarchical context, semantic clustering, working memory |
| 🤖 9 RL Algorithms | Q-Learning, SARSA, DQN, PPO, Actor-Critic, Policy Gradient, Decision Transformer, MCTS, Model-Based RL — bandit picks the right one per task |
| ⚡ 150× faster than SQLite | RuVector Rust engine via NAPI bindings; HNSW vector search; sub-millisecond reads on 100k+ vectors |
| 🔍 Hybrid Search | BM25 keyword + dense vector fused with Reciprocal Rank Fusion — exact terms and semantic intent in one query |
| 🕸️ Graph Intelligence | Cypher queries, causal edges, GNN 8-head attention (+12.4% recall), hyperedges for n-ary relationships |
| 💾 Single-file Storage | Everything (vectors, indexes, learning state, audit log) in one .rvf "Cognitive Container" — no servers, no API keys, no monthly bills |
| 🎯 Quantization | 4-32× memory reduction with PQ8 / PQ4 / binary quantization; minimal recall loss; runs on commodity hardware |
| 🔌 41 MCP Tools | First-class Claude Code / Cursor / Cline integration — pattern store, search, skill library, reflexion, causal edges, hierarchical recall, delete |
| 🌐 Runs Anywhere | Node, browser (WASM), edge runtimes, fully offline — same API, same .rvf file |
| 🛡️ Enterprise Security | JWT auth, API key rotation, Argon2id hashing, SOC2 / GDPR audit trails, cryptographic witness chain |
| 🔗 agentic-flow Integration | Drop-in for agentic-flow — backs ReasoningBank, MemoryController, NightlyLearner, and 30+ agents |
Optional native integrations
Installed by default as optional dependencies. Each has a JavaScript fallback, so agentdb works without them (ADR-018).
| Package | Powers | Measured |
|---|---|---|
@ruvector/graph-transformer |
Personalized PageRank in SparsificationService and sparse attention |
40x–780x faster than the JS path (500–5,000 nodes) |
@ruvector/mincut-wasm |
Exact global min cut in MincutService and partitioned attention |
cut of 4 edges where the old split cut 1,003 (1,000 nodes) |
@ruvector/rabitq-wasm |
Opt-in 1-bit index for the built-in sql.js backend (quantizedIndex: 'rabitq') |
6.4x faster at 50k vectors, recall@10 1.000 |
aidefence |
Opt-in prompt-injection screening of stored memories (AGENTDB_INJECTION_GUARD=warn|block) |
0.1–10 ms per field |
🧠 Self-Learning Loop
Most retrieval systems are read-only. AgentDB closes the loop:
search ──► top-k ──► agent picks the useful ones ──► recordFeedback()
│
▼
Thompson Sampling bandit
│
▼
re-weights ranking · re-picks RL algorithm · re-tunes compression
│
▼
next search is sharper
The bandit isn't a gimmick — it's used at four decision points:
- Pattern ranking — which historical pattern matches this new query best?
- RL algorithm selection — Q-Learning for tabular tasks, PPO for continuous control, MCTS for planning, etc.
- Compression tier — full precision when accuracy matters, PQ4 when memory does.
- Skill composition — chain skill A→B→C or skill A→D→E?
Each decision logs reward over time. Bad arms decay fast. Good arms stick.
⚡ Performance
| Metric | AgentDB | Baseline | Source |
|---|---|---|---|
| Vector search (100k vectors) | <1 ms | ~150 ms (SQLite + cosine loop) | benchmarks/hnsw/ |
| HNSW query (1M vectors) | 2–5 ms | ~100 ms (brute force) | benchmarks/vector-search/ |
| Bulk insert (10k vectors) | <100 ms | ~12 s (sql.js) | benchmarks/database/ |
| Memory footprint (1M × 384d) | ~96 MB (PQ8) | ~1.5 GB (raw f32) | benchmarks/quantization/ |
| Self-learning quality lift | +36% | n/a | benchmarks/ruvector-performance.test.ts |
| GNN attention recall | +12.4% | baseline HNSW | benchmarks/attention-performance.ts |
Run them yourself: npm run bench from this repo.
Long-term memory retrieval (LongMemEval)
Episode search fuses BM25 keyword ranking with vector ranking by default (hybrid: false turns it off), and rerank: true adds a local cross-encoder over the top candidates. Session retrieval on LongMemEval, default MiniLM embedder, local models only, official protocol (470 questions):
| LongMemEval_M (≈500 sessions per question) | recall_all@5 | NDCG@5 | recall_all@10 |
|---|---|---|---|
| dense only | 0.630 | 0.692 | 0.751 |
| hybrid (default) | 0.719 | 0.750 | 0.806 |
hybrid + rerank: true |
0.789 | 0.828 | 0.881 |
| LongMemEval paper, best (Contriever + LLM fact keys) | 0.762 | 0.632 | 0.862 |
The harness (benchmarks/longmemeval/) runs the same ranking functions over turn chunks; protocol, S-split numbers, other rerankers and limits are in ADR-016.
🔌 MCP Integration
41 tools across six families, all callable from Claude Code, Cursor, Cline, or any MCP-compatible client:
| Tool | Purpose |
|---|---|
agentdb_pattern_store |
Store a successful pattern with embedding + metadata |
agentdb_pattern_search |
Semantic search for similar past patterns |
agentdb_pattern_stats |
Retrieval stats, cache hits, hit-rate trends |
agentdb_pattern_delete |
Remove a pattern by id |
agentdb_batch_insert |
Bulk insert many patterns at once |
agentdb_batch_search |
Parallel multi-query search |
agentdb_export |
Dump patterns to JSON / CSV |
agentdb_import |
Load patterns from JSON / CSV |
| Tool | Purpose |
|---|---|
agentdb_hierarchical_store |
Tier-aware memory store (working / short / long) |
agentdb_hierarchical_recall |
Tier-filtered retrieval |
agentdb_hierarchical_delete |
Remove hierarchical entry by key |
agentdb_causal_edge |
Add a causal relationship between memories |
agentdb_causal_edge_delete |
Remove a causal edge by id |
agentdb_causal_node_delete |
Cascade-delete a node + incident edges |
agentdb_edges_by_endpoints |
Bulk-delete edges by (from, to, label) |
agentdb_causal_query |
Cypher-like graph queries |
agentdb_causal_explain |
Explain why two memories are connected |
agentdb_attestation_log |
Cryptographic audit trail |
| Tool | Purpose |
|---|---|
agentdb_reflexion_store |
Store an episode (task + outcome + critique) |
agentdb_reflexion_recall |
Retrieve relevant past episodes |
agentdb_reflexion_delete |
Remove an episode |
agentdb_reflexion_rebuild |
Re-hydrate vector index from durable SQL |
agentdb_skill_create |
Create a reusable skill from a pattern |
agentdb_skill_compose |
Chain skills A→B→C with bandit-picked composition |
agentdb_skill_search |
Find skills by intent embedding |
agentdb_critique_summary |
Summarize lessons from past failures |
agentdb_success_strategies |
Surface what worked across past episodes |
agentdb_task_stats |
Per-task win-rate, latency, reward trends |
agentdb_prune |
TTL + quality-based episode pruning |
agentdb_warm_cache |
Pre-populate query cache for a session |
| Tool | Purpose |
|---|---|
agentdb_learning_route |
Route a task to the right RL algorithm |
agentdb_learning_train |
Train a specific RL agent on episodes |
agentdb_learning_predict |
Get an action prediction for a state |
agentdb_bandit_update |
Update bandit reward for an arm |
agentdb_bandit_pick |
Sample the best arm under Thompson Sampling |
agentdb_consolidate |
Run NightlyLearner consolidation pipeline |
agentdb_compose |
Combine memory patterns into a strategy |
agentdb_synthesize |
Build a context window from related memories |
agentdb_explain_recall |
Feature-attributed retrieval results |
agentdb_diversity_rank |
MMR-rerank for diverse top-k |
agentdb_metadata_filter |
Filtered semantic search |
🔗 Used By
AgentDB powers the memory + learning layer in:
| Project | What it uses AgentDB for |
|---|---|
agentic-flow |
ReasoningBank backend, ReflexionMemory, NightlyLearner consolidation, 30+ agent memory namespaces |
ruflo |
Plugin marketplace memory, agent federation audit log, hierarchical recall for /adr-index, swarm coordination patterns |
@ruvector |
Reference downstream for the Rust engine — every release is verified against AgentDB's test suite |
If you ship something on top of AgentDB, open an issue and we'll add you.
🐳 Docker / Edge / Browser
AgentDB compiles to four targets from one source:
| Target | What | When |
|---|---|---|
| Node native | NAPI bindings (Linux, macOS, Windows; x64 + arm64) | Backend services, CLI, MCP server |
| Node WASM fallback | sql.js + WASM engine | Restricted hosts that can't run NAPI |
| Browser | Pure WASM bundle | Offline-first apps, edge functions, IDE extensions |
| Docker | docker-compose.yml in docker/ |
Local dev, CI, prod deploy |
# Browser
import { createBrowserDb } from 'agentdb/browser';
# Docker
docker compose -f docker/docker-compose.yml up
Documentation
| Doc | When to read it |
|---|---|
| Full README (deep) | Every feature, every API, every option — the complete reference (2,900+ lines) |
| PUBLISHING.md | npm publish flow, dist-tag policy, release verification |
| ADR-071 | WASM integration design |
| ADR-072 | RuVector advanced-feature integration |
| Examples | End-to-end runnable scripts — RAG chatbot, code-review agent, RL training, edge deploy |
| Benchmarks | Reproducible perf harness — HNSW, attention, quantization, RL, end-to-end |
Repository
| 📦 npm | agentdb |
| 🌐 Source | https://github.com/ruvnet/agentdb |
| 🐛 Issues | https://github.com/ruvnet/agentdb/issues |
| 🎨 Marketing site | ui/ (Vite + React + shadcn/ui) |
| 🧬 Engine | @ruvector (Rust + NAPI) |
| 🔗 Reference consumer | agentic-flow (uses this as a git submodule at packages/agentdb/) |
Support
| Resource | Link |
|---|---|
| Documentation | docs/README-full.md |
| Issues & Bugs | GitHub Issues |
| Enterprise | ruv.io |
| Community | Agentics Foundation Discord |
| Engine | ruvector |
| Powered by | Cognitum.one |
License
Works with / Used by
Part of the ruv.io open-source stack for agent memory, vector database, AI agents.
- Works with (its runtime dependencies):
@ruvector/attention,@ruvector/core,@ruvector/gnn,@ruvector/graph-node,@ruvector/graph-transformer,@ruvector/mincut-wasm,@ruvector/rabitq-wasm,@ruvector/router,@ruvector/ruvllm,@ruvector/rvf,@ruvector/rvf-node,@ruvector/rvf-solver,@ruvector/rvf-wasm,@ruvector/sona,@ruvnet/sublinear-core,aidefence,ruvector,ruvector-attention-wasm,ruvector-graph-transformer-wasm - Used by (published packages that depend on it):
@agentic-robotics/mcp,@agentic-robotics/self-learning,@claude-flow/aidefence,@claude-flow/cli,@claude-flow/memory,@claude-flow/neural,@foxruv/iris,@foxruv/iris-ultrathink,@foxruv/nova-medicina,@neural-trader/agentic-accounting-agents,@neural-trader/agentic-accounting-core,@neural-trader/example-dynamic-pricing
Built by rUv · ruv.io · Source
Learned memory reranking (3.10)
NeuralReranker learns a small local ruv-FANN scorer from labeled query groups.
It evaluates NDCG and MRR against baseline and active rankings before explicit
promotion. Opt-in neuralRerank queries default to shadow mode, preserving normal
results while exposing scores. Active mode ranks a bounded candidate pool;
revisioned checkpoints support rollback. Ten MCP tools expose training,
evaluation and model management, with admin-only promotion and rollback.
The four versioned inputs are similarity, historical reward, success and recency. Supply independent relevance labels and separate evaluation queries. Included synthetic benchmarks validate the pipeline, not production retrieval quality. Agents can also inspect weights and propose hash-bound WSP edits without training; these candidates must pass the same evaluation gates before promotion.
See the learned memory reranking guide.
Persisted neural models (3.8)
WeightPrograms from agentdb/controllers/WeightPrograms adds durable,
gradient-free weight patches evaluated by real WASM. Caller-authored proposals
are persisted with evaluation evidence; explicit promotion checks stored proposal
identity, generation, hashes and revision. Rollback restores retained checkpoints
as new revisions. Six strict MCP tools expose the workflow with learning/admin
permissions. Acceptance applies to caller-supplied examples and does not prove
generalization. See the weight programs guide.
FannModels from agentdb/controllers/FannModels stores dense ruv-FANN
checkpoints and revisions in your database. It provides real WASM batch inference,
SGD/AdamW training, and bounded prepared-model caching. AgentDB depends on
ruv-fann@0.1.2, which depends on ruv-fann-wasm@0.1.2; no optional native
accelerator is needed for this API.
Six MCP tools (agentdb_neural_create, get, list, predict, train, and
delete, each with the agentdb_neural_ prefix) follow the existing capability
policy. Readonly clients can inspect and predict; learning clients can create
and train; deletion requires admin or an explicit allow. See
the neural-model guide
for usage, persistence semantics and bounded training limits.
Questions sur AgentDB MCP
Comment ajouter AgentDB MCP à Claude Code ?
Exécutez claude mcp add agentdb -- npx -y agentdb dans votre terminal. Ajoutez --scope user pour le rendre disponible dans tous les projets.
Comment ajouter AgentDB MCP à Cursor ?
Ouvrez ~/.cursor/mcp.json et ajoutez le serveur sous mcpServers, avec la configuration Cursor indiquée dans la section d'installation ci-dessus.
Comment ajouter AgentDB à Claude Code ?
Exécutez claude mcp add agentdb -- npx agentdb@latest mcp start, ce qui enregistre 41 outils MCP. Cela fonctionne avec Claude Code, Cursor, Cline ou tout client compatible MCP.
Combien d'outils MCP AgentDB fournit-il ?
AgentDB expose 41 outils MCP répartis en six familles, incluant le stockage de patterns, la recherche, la bibliothèque de skills, la réflexion, les liens causaux et le rappel hiérarchique.
Comment AgentDB devient-il plus intelligent grâce aux retours ?
Après une recherche, vous enregistrez si les résultats étaient utiles, et un bandit Thompson Sampling réajuste le classement, le choix de l'algorithme de RL et le niveau de compression pour la requête suivante.
AgentDB nécessite-t-il un serveur externe ou des clés API ?
Non. Tout, y compris les vecteurs, les index, l'état d'apprentissage et le journal d'audit, est contenu dans un seul fichier .rvf et s'exécute hors ligne dans Node, le navigateur ou les environnements edge.