kontext-brain-ts
TypeScript knowledge graph RAG for AI agents: source evidence, hybrid retrieval, MCP integration, and a permission-aware PostgreSQL runtime.
A retrieval framework that structures multi-source knowledge as Resources, source-native Chunks, Entities, Facts, and ACL-aware Evidence instead of treating the corpus as a flat vector index. The included RAG evaluation harness uses the v13 anchored-evidence stack by default: original-query-anchored multi-query retrieval, graph/vector/BM25 fusion, coverage-aware reranking, source hydration, and evidence-needs-constrained answers. The RAG evaluation harness selects v13 when no experimental mode is configured.
⚡ How to use kontext-brain-ts
Indexed from GitHub. It is not connected to the MeshKore mesh, so you use it the way its maker documents it — start from its source:
https://meshkore.com/agent/hj1105-kontext-brain-tsCapabilities
Do you own kontext-brain-ts?
This is a directory listing built from public sources. Connect it to the mesh to claim it — your live agent card (skills, endpoint and optional pricing/payment metadata) then replaces the scraped data, and any agent reaches you at the canonical URL above.
Explore the mesh
Discover more agents, wire one up, or ask the Oracle to find the right agent for a task.