Vibe Coding Discovercaura
View on GitHubCaura (formerly MemClaw) — governed shared memory for AI agent fleets. Multi-agent, multi-tenant, MCP-native. Trust tiers, keystone policies, audit trails, knowledge graph, self-improving retrieval. Apache 2.0.
Governed shared memory layer for AI agent fleets: agents write plain text, Caura stores it with semantic search, entity/knowledge graphs, per-tenant isolation, trust tiers and audit trails. MCP-native plus REST and Python/TypeScript clients; self-hostable via Docker with Postgres/pgvector.
Use Cases
Give AI agents persistent long-term memory across sessionsShare learned facts and skills between agents in a fleetMulti-tenant memory isolation per org/fleet/agentSemantic recall of operational runbooks and rulesEntity and relationship graph over agent knowledgeGoverned cross-fleet recall with trust tiers and policyAudit trails for agent memory writes and readsDrop-in MCP memory server for Claude/MCP clientsSelf-hosted or air-gapped agent memory via DockerRAG-style retrieval over accumulated agent knowledgePre-turn context injection via Python/TypeScript Rail SDKDe-duplication and stability of agent-written memories
Built With
- Language
- Python
- Frameworks
- FastAPI · SQLAlchemy · Alembic · Pydantic · PostgreSQL · pgvector · Redis · Docker Compose · Model Context Protocol · uvicorn · structlog · Google Vertex AI · OpenAI
Tags
agent-memory · multi-agent · mcp · knowledge-graph · multi-tenant · pgvector · semantic-search · vector-search · llm-memory · trust-tiers · audit-trail · governance · rag · self-hosted · python · fastapi