Agent infrastructure
Agent-Cockpit
chutingyean/Agent-Cockpit
Agent Cockpit is a local whiteboard and MCP server for AI research agents that traces every claim back to the run and code that produced it, with staleness checks and replay.
Topics
Related projects
omg.dev554A remote control and session manager for coding agents such as Claude Code, Codex, Cursor, and OpenCode. It lets you assign tasks from a phone or web UI, follow progress, and get notified when work finishes.
codebase-memory-mcp48.3kA local MCP server that gives coding agents a persistent code knowledge graph for search and call tracing.
Graft11.2kA self-learning context layer for coding agents. It builds a tree-sitter code map and saves team learnings, then feeds them to Claude Code, Cursor, Codex, and other agents through hooks and MCP.- Trail-Code11.1kShared memory and code-map context layer for Claude Code, Cursor and Codex coding agents.
skills1.5kA reusable library of agent skills for software factories. Each SKILL.md packages a focused workflow such as exploration, specification, implementation, review or autonomous research.
squadra1.3kAn orchestration toolkit that coordinates multiple Claude Code, Codex and Cursor sessions through a shared task registry, proofs, independent reviews and a local dashboard.