WikiKB: a fast, repository-native knowledge base for people and agents
WikiKB is an efficient, transparent and explicitly curated knowledge base layer, for humans and agents, built on the GitHub repository wiki. Yes, every repo comes with a wiki! Most of them go unused, making it the perfect landing place for a human-readable, agent-addressable memory. WikiKB content can be ingested and queried from the command line, through GitHub issues, or agentically using the provided skill definition.
Idée qu'on m'a déjà présentée (utiliser les Wiki comme KB pour les agents et les humains + API Github pour query), mais cette fois il y a tout le tooling pour l'exploiter efficacement.
WikiKB is fast and efficient, leveraging Self-Organizing Memory for Agents (SOMA) from the GraphRAG Zero project at Microsoft Research.
❤️ Graph RAG.
WikiKB can ingest a local document or a public URL:
wkb ai-research ingest ./notes/retrieval-design.md --tag retrieval,design wkb ai-research ingest https://example.com/research-paper --tag research
OK, l'idée est d'ajouter les docs à la main et de demander à l'agent de les ajouter. ai-research doit être le nom de la collection ?
Here, ai-research is the local name registered for owner/repository.
Confirmé
Efficient: indexing and retrieval run locally on the CPU. Provider-optional: retrieval works without an LLM account or API request.
Idéal
Extraits cités issus de ce lien visité le , crédits: Russell Horton