You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Extracts claims from SOPs, policies and regulations, has a person approve or reject each one, then serves the approved set to agents over MCP - each claim carrying a byte range to its source sentence. Open Knowledge Format (OKF) bundles, no database.
BundleWalker is a local-first tool that turns a source bundle into a navigable knowledge workspace for people and AI agents. It proposes review-first writes to cited, interlinked OKF Markdown while preserving the exact bytes of every accepted source as immutable evidence.
Retours d'usage, anomalies et demandes d'évolution sur l'outillage du OKF Bundle Hub. Roadmap des évolutions — décidées, reportées, refusées, avec leur motif — et limitations connues. Bundle OKF alimenté par kb_propose, révisé par kb-review.
A zero-infra MCP server that turns an Open Knowledge Format (OKF) bundle into fast, lexical-first knowledge discovery for LLM agents — no vector DB, no embeddings by default.
Experiment 2: Governed analytics for AI agents: an OKF knowledge plane linked to Malloy semantic models, with a build that proves the two agree and an eval loop that proves the agent uses them.