Yashasm18/ForgeAgent
One agent proves a capability is safe. Every other agent -> Codex, Cursor, Claude Code, reuses it instantly, without rebuilding or re-verifying.
GitHub repository with 5 stars and 0 forks.
Language: Python
Topics: agentic-ai, ai-agents, ai-safety, developer-tools, llm-tools, openai-build-week, python, capability-memory, mcp, governance