Provides AI agents with a governed, three-layer project memory (guide, code facts, and knowledge) through namespaced MCP tools for code search, context compilation, impact analysis, and proposal-driven documentation updates.
Turns local project directories into persistent MCP workspaces, allowing AI agents to read files, modify code, run commands, manage Git, and save session progress across conversations.
Provides a shared, persistent workspace with versioned files, semantic search, run logging, and cross-agent provenance, allowing agents to maintain context across sessions and tools.
Provides bounded repository context and edit-grant MCP tools to coding agents such as Codex, indexing local repositories and enabling fingerprint-checked patch application.
