# Agentdb

> Self-learning vector memory for AI agents — single-file .rvf cognitive container with HNSW search, episodic Reflexion memory, causal graph + Cypher, 9 RL algorithms, Thompson Sampling bandit, 41 MCP tools, hybrid (BM25 + dense) retrieval, GNN attention. 1

## Facts
- Page: https://tashan.sh/capability/pkg-agentdb
- tashan id: pkg:agentdb
- Source: https://github.com/ruvnet/agentdb
- npm: https://www.npmjs.com/package/agentdb
- Type: npm
- Category: ai
- tashan score: 79.0 / 100
- Adoption: 70.0
- Upkeep: 72.0
- Freshness: 97.0
- Evidence coverage: 100% of the inputs this score can use
- Health: active
- Instruction depth: not yet graded
- npm downloads: 121,808/week
- Official: no

## Install

```sh
claude mcp add agentdb -- npx -y agentdb
```

## Security audit
Not scanned. We audit npm-published capabilities; this one has no npm package we can resolve, or has not reached the queue. This is not a clean bill of health.

---
Measured 2026-08-08 by tashan (https://tashan.sh) from public evidence. Scorer s5.