Browse
→ AI & Models
→ AgentDB
AgentDB
Self-learning vector memory MCP server that improves search quality up to 36% through agent feedback loops. Consolidates vectors, indexes, learning state, and a cryptographic audit trail into a single portable .rvf file. Provides tiered memory with automatic quality refinement for AI agent workflows.
MCP unverified
Integration
| Transport | stdio |
| Auth | none |
| Endpoint | agentdb-mcp |
Use Cases
| 01 | Give AI agents persistent vector memory that automatically improves search relevance through feedback loops |
| 02 | Store and retrieve agent knowledge in a single portable file with built-in cryptographic audit trails |
| 03 | Build cognitive agent systems with self-refining memory that consolidates vectors, indexes, and learning state |
Tags
vector-memory self-learning embeddings cognitive audit-trail open-source
Machine-readable: /api/servers.json
· JSON-LD schema embedded in <head>