AgenticMind¶
The auditable, self-improving knowledge & memory layer for AI agents — grounded answers with provable citations, a full why-trace for every answer, and a corpus that improves itself, served to any agent over MCP. Zero-key, multilingual, and self-hostable on Postgres alone. Apache-2.0.
Not "memory storage for an agent." It's the substrate an agent points at when it needs answers it can trust, a trail it can audit, and a knowledge base that compounds. No source, no claim — and a receipt for every answer.
Run it — no clone (~1 min)¶
Needs Docker (Compose v2.23+) and an OpenAI-compatible key:
OPENAI_API_KEY=sk-... sh -c "$(curl -fsSL https://raw.githubusercontent.com/Moai-Team-LLC/AgenticMind/main/quickstart.sh)"
The MCP endpoint comes up at http://localhost:3000/mcp, authenticated with a single static
bearer (MCP_API_KEY, auto-generated). Point Claude Code / Cursor at it with the
Authorization: Bearer <MCP_API_KEY> header. Embeddings run locally (zero-key); only
synthesis uses your chat key.
Connect guides for Claude Code, Cursor, Claude Desktop, and agent frameworks
live in the repo's examples/.
Start here¶
- The why-trace — why every answer ships a replayable, citation-keyed receipt.
- Postgres-only — vectors, full-text, graph, and the queue in one database.
- Provenance is the differentiator — the axis that survives commoditization.
- Safe by construction — the security posture in context.
- Security model — auth, scopes, RLS, data residency.
- Deploy · Operations — running it for real.
Ecosystem¶
AgenticMind is the flagship reference implementation of the Agentic Product Standard — the open standard (plus Claude Code skills) for building production-grade agentic products.