A self-hosted MCP server that enables AI coding agents to read, edit, search, and run code in local projects with human review loops and policy controls.
A local, agent-to-agent artifact exchange for LLM workflows. Enables MCP-capable tools like Claude, Codex, and Gemini to publish, list, read, update, and continue from artifacts without copying content through chat.
Self-hosted MCP server that gives coding agents persistent, code-aware memory with structural graph recall and blast-radius planning. It links experiential decisions to code locations and provides honest measurement instruments.