RELATED 01
Ruflo
Agent swarms with shared vector memory and task routing for Claude Code and other MCP clients
81kGitHub stars
87k/wknpm downloads
89popularity score
AgentDB
Gives an agent self-learning vector memory: store and search patterns, episodes, skills and causal links.
Official · rUv TypeScript Local · stdio Knowledge and memoryAI and ML
79 popularity score ★ 97 ↓ 169k/wk
Connect your client
Local (npm)
Add in one click
Opens the app, which asks before it adds the server.
Or add it by command or config
Claude CodeTerminal
claude mcp add agentdb -- npx -y agentdb mcp startClaude Desktopclaude_desktop_config.json
{
"mcpServers": {
"agentdb": {
"command": "npx",
"args": [
"-y",
"agentdb",
"mcp",
"start"
]
}
}
}Cursor~/.cursor/mcp.json
{
"mcpServers": {
"agentdb": {
"command": "npx",
"args": [
"-y",
"agentdb",
"mcp",
"start"
]
}
}
}VS Code.vscode/mcp.json
{
"servers": {
"agentdb": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"agentdb",
"mcp",
"start"
]
}
}
}Codex~/.codex/config.toml
[mcp_servers.agentdb]
command = "npx"
args = ["-y", "agentdb", "mcp", "start"]Gemini CLITerminal
gemini mcp add --scope user agentdb npx -- -y agentdb mcp startWhat it does
AgentDB is a self-learning vector memory engine for AI agents, built on the RuVector Rust engine and stored in a single .rvf file with no server or API key. It is available as an npm library, a CLI and an MCP server (npx agentdb mcp start) with 41 tools.
The tools store and semantically search patterns (with batch insert, import and export), keep tiered working, short and long-term memory, record causal links between memories and query them in a Cypher-like way, store and recall episodes with critiques (Reflexion), build and compose reusable skills, summarise lessons and successful strategies, and run learning and routing: reinforcement-learning algorithms, Thompson-sampling bandits, consolidation, diversity re-ranking and filtered search. Search combines BM25 keywords with dense vectors and learns from feedback.
Add it to a client with npx agentdb@latest mcp start (Node native bindings on Linux, macOS and Windows, with a WASM fallback). The current npm release is an alpha (3.0.0-alpha).
What it needs
| Runtime | Node.js |
|---|
Tools 41
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
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
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
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