Enables AI agents to query and maintain source-bound project knowledge with git-computed freshness verdicts and a gated write path, providing trusted, up-to-date documentation for legacy codebases.
Anchors a codebase's engineering context — file cards, rules, modules and decisions — in a small git-committed graph, and injects the applicable slice before each edit while refusing changes to files the agent hasn't actually understood. It also records the why behind each constrained edit so later sessions and teammates start from that understanding instead of rediscovering it.
Enables coding agents to maintain local-first project memory, coordinate task ownership across Git worktrees, and verify completion against project-defined checks with durable evidence stored in the repository.
Saves decisions, rules, bugs, to-dos and failed approaches from coding-agent chats as lines in a repo file, then brings the relevant ones back in later sessions. It also checks planned commands and file edits against those saved rules before they run, asking first when a rule might be broken.
Enables AI coding agents to query a team's institutional coding rules and lessons learned, resolving a project → framework → language → global scope hierarchy so only the entries relevant to the current task are returned instead of whole knowledge-base files. It also supports governed proposal approval, PR and feature audits, meeting-transcript extraction, optional semantic ranking, and access-controlled audit logging, while keeping Markdown files as the source of truth.
Saves decisions, rules, bugs, to-dos, and failed approaches from Claude Code, Cursor, and Codex chats into a repository file, then brings relevant entries back in later sessions and checks tool calls against saved rules before commands or edits run.
