MohitGoyal09/AgentForge

One brain, many harnesses. Portable .agent/ folder (memory + skills + protocols) that plugs into Claude Code, Cursor, Windsurf, OpenCode, OpenClaw, Hermes, or DIY Python — and keeps its knowledge when you switch.

Open-source, self-hosted Claude Code - a terminal AI assistant and the Python framework behind it. Tool-calling, sandboxed execution, multi-agent teams, skills, checkpoints, unlimited context - on Pydantic AI, any model.

Hierarchically modularized and ultra optimized agents suite. Balancing minimalism and ergonomics is the core philosophy with extra good tastes. Dal is minimalist and pluggable core, Dalgona is highly opinionated batteries-included agent. Pick what you want, or command agents to write plugins and customizations in your own preferences!

Bash is all you need - A nano claude code–like 「agent harness」, built from 0 to 1

AI agent toolkit: unified LLM API, agent loop, TUI, coding agent CLI

The lightest harness for agentic work.

Minimal and readable coding agent harness implementation in Python to explain the core components of coding agents.

🛠️ The meta-harness for AI agents — scaffold your own focused, branded agent harness with its own npx CLI, MCP server, memory, learning loop, and witness-signed releases. Works with Claude Code, Codex, pi.dev, Hermes, OpenClaw, and RVM (hardware-isolated sandbox).

Production-ready open source terminal coding agent with readable, layered code: permission rules, OS sandboxing, MCP, skills, sub-agents, and Anthropic, OpenAI-compatible, Gemini, or local models.