Verleiht einem AI-Client ein selbstlernendes Vektor-Gedächtnis, um Muster zu speichern, diese semantisch zu durchsuchen und das Ranking durch Feedback zu verbessern.
Auch bekannt als ruvnet/agentdb
- Stars
- 99
- Tools
- —
- Downloads, 30 Tage
- —
- Neueste Version
- —
- Letzter Commit
- 11. Nov. 2026
- Lizenz
- MIT
Was ist AgentDB MCP?
AgentDB ist ein MCP server. Verleiht einem AI-Client ein selbstlernendes Vektor-Gedächtnis, um Muster zu speichern, diese semantisch zu durchsuchen und das Ranking durch Feedback zu verbessern.
Zusammenfassung generiert aus dem README des Projekts
Über AgentDB MCP server
AgentDB ermöglicht es Entwicklern, die intelligente Anwendungen bauen, ihren AI-Agenten einen selbstlernenden kognitiven Container zur Verfügung zu stellen. Es fungiert als Single-File Vektor-Gedächtnis, das Muster, Skills und kausales Denken innerhalb einer .rvf Datei speichert. Im Gegensatz zu Standard-Vektordatenbanken, die nur Embeddings speichern, nutzt dieses System einen Thompson Sampling Bandit, um zu beobachten, welche Ergebnisse ein Agent tatsächlich nutzt. Dadurch kann die Suchqualität allein durch Feedback um bis zu 36 % gesteigert werden.
Nutzer können dies als npm Library für eigene Node.js Anwendungen integrieren oder den MCP server nutzen, um 41 spezialisierte Tools direkt mit Clients wie Claude Code, Cursor oder Cline zu verbinden. Der Server bietet Zugriff auf Capabilities wie agentdb_pattern_store, agentdb_pattern_search und agentdb_reflexion. Er läuft lokal in Node.js, im Browser via WASM oder in Edge Runtimes und benötigt keine externen API keys oder monatliche Abonnements. Die zugrunde liegende RuVector Rust Engine sorgt für hohe Performance bei HNSW Vektor-Suchen und Hybrid Retrieval.
Was du damit machen kannst
- 1Gedächtnis mit LLM-Clients verbindenIntegiere eine hochentwickelte Skill Library und episodisches Gedächtnis direkt in deinen bestehenden Workflow mit Coding-Assistenten.
- 2Komplexe kognitive Muster speichernSpeichere erfolgreiche Ausführungsmuster und Metadaten in einer einzigen portablen Datei für ein langfristiges agentisches Gedächtnis.
- 3Hybride semantische Suchen durchführenRufe Informationen mithilfe einer Kombination aus exaktem Keyword-Matching und dichten Vektor-Intents ab.
Geschrieben aus dem README des Projekts. Jeder Use Case wurde gegen ein Zitat daraus geprüft.
So installierst du AgentDB MCP
Formate geprüft am 10. Nov. 2026Zu Cursor hinzufügenZu Goose hinzufügenAgentDB MCP in Claude Code installieren
$ claude mcp add agentdb -- npx -y agentdbAgentDB MCP in Cursor installieren
~/.cursor/mcp.json
{
"mcpServers": {
"agentdb": {
"command": "npx",
"args": [
"-y",
"agentdb"
]
}
}
}AgentDB MCP in VS Code installieren
.vscode/mcp.json
{
"servers": {
"agentdb": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"agentdb"
]
}
}
}AgentDB MCP in VS Code CLI installieren
$ code --add-mcp '{"name":"agentdb","type":"stdio","command":"npx","args":["-y","agentdb"]}'AgentDB MCP in Claude Desktop installieren
claude_desktop_config.json
{
"mcpServers": {
"agentdb": {
"command": "npx",
"args": [
"-y",
"agentdb"
]
}
}
}AgentDB MCP in Codex installieren
$ codex mcp add agentdb -- npx -y agentdbAgentDB MCP in Codex config.toml installieren
~/.codex/config.toml
[mcp_servers.agentdb] command = "npx" args = ["-y", "agentdb"]
AgentDB MCP in Gemini CLI installieren
$ gemini mcp add -s user agentdb npx -- -y agentdbAgentDB MCP in Gemini settings.json installieren
~/.gemini/settings.json
{
"mcpServers": {
"agentdb": {
"command": "npx",
"args": [
"-y",
"agentdb"
]
}
}
}Automatisierte Checks
Geluften am 12. Nov. 2026Vollständiger Bericht →Unsere automatisierten Checks bestanden. Das ist kein Security-Audit: Lies den Code und gib dem Server nur den minimal notwendigen Zugriff. Wie die Checks funktionieren
- Source Repository verknüpft und erreichbarBestanden
- Open Source Lizenz (OSI)Bestanden
- Commit oder Release im letzten JahrBestanden
- Package-Name ähnelt keinem populären PackageBestanden
- Remote Endpoint nutzt HTTPSNicht geprüft
- Destruktive Tools sind markiertNicht geprüft
- Keine versteckten Anweisungen an das ModellBestanden
- Keine kritischen Advisories im Paket oder seinen AbhängigkeitenNicht geprüft
README
Auf GitHub ansehenAgentDB
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.
AgentDB MCP Fragen
Wie füge ich AgentDB MCP zu Claude Code hinzu?
Führe claude mcp add agentdb -- npx -y agentdb in deinem Terminal aus. Füge --scope user hinzu, damit der Server in jedem Projekt verfügbar ist.
Wie füge ich AgentDB MCP zu Cursor hinzu?
Öffne ~/.cursor/mcp.json und füge den Server unter mcpServers hinzu, mit der Cursor-Config aus dem Installationsabschnitt oben.
Wie füge ich AgentDB zu Claude Code hinzu?
Führe claude mcp add agentdb -- npx agentdb@latest mcp start aus, wodurch 41 MCP tools registriert werden. Es funktioniert mit Claude Code, Cursor, Cline oder jedem MCP-kompatiblen Client.
Wie viele MCP tools bietet AgentDB?
AgentDB stellt 41 MCP tools in sechs Kategorien bereit, darunter pattern store, search, skill library, reflexion, causal edges und hierarchical recall.
Wie wird AgentDB durch Feedback intelligenter?
Nach einer Suche kannst du Feedback dazu geben, welche Ergebnisse nützlich waren. Ein Thompson Sampling Bandit optimiert daraufhin das Ranking, die Wahl des RL-Algorithmus und die Compression Tier für die nächste Abfrage.
Benötigt AgentDB einen externen Server oder API keys?
Nein. Alles, einschließlich Vektoren, Indizes, Lernzustand und das Audit Log, befindet sich in einer einzigen .rvf Datei und läuft offline in Node, im Browser oder in Edge Runtimes.