Awesome Agent Harness

An open-source AI coding agent that lives in your terminal.

A format specification for describing a visual identity to coding agents. DESIGN.md gives agents a persistent, structured understanding of a design system.

Persistent file-based planning for AI coding agents and long-running agentic tasks. Crash-proof markdown plans that survive context loss and /clear, plus a deterministic completion gate and multi-agent shared state on disk. Manus-style. Works with Claude Code, Codex CLI, Cursor, Kiro, OpenCode and 60+ agents via the SKILL.md standard.

Beads - A memory upgrade for your coding agent

#1 Persistent memory for AI coding agents based on real-world benchmarks

Open source Ghostty-based macOS terminal with vertical tabs and notifications for AI coding agents. Built for multitasking, organization, and programmability.

A configuration framework that enhances Claude Code with specialized commands, cognitive personas, and development methodologies.

Official Compound Engineering plugin for Claude Code, Codex, Cursor, and more

Specification and documentation for Agent Skills

Test your prompts, agents, and RAGs. Red teaming/pentesting/vulnerability scanning for AI. Compare performance of GPT, Claude, Gemini, DeepSeek, and more. Simple declarative configs with command line and CI/CD integration. Used by OpenAI and Anthropic.

The first open-source harness builder for AI coding. Make AI coding deterministic and repeatable.

Debug, evaluate, and monitor your LLM applications, RAG systems, and agentic workflows with comprehensive tracing, automated evaluations, and production-ready dashboards.

Open-source infrastructure for Computer-Use Agents. Sandboxes, SDKs, and benchmarks to train and evaluate AI agents that can control full desktops (macOS, Linux, Windows).

Devika is the first open-source implementation of an Agentic Software Engineer. Initially started as an open-source alternative to Devin.

Context window optimization for AI coding agents. Sandboxes tool output (98% reduction), persists session memory, and enforces routing across 17 platforms via MCP + hooks.

Open source agentic operating system

Build reliable customer-facing AI agents with Parlant: an interaction control harness optimized for controlled, consistent, and predictable LLM interactions.

Open-source Agent Operating System

🐫 CAMEL: The first and the best multi-agent framework. Finding the Scaling Law of Agents. https://www.camel-ai.org

A comprehensive collection of Agent Skills for context engineering, multi-agent architectures, and production agent systems. Use when building, optimizing, or debugging agent systems that require effective context management.

Gas Town - multi-agent workspace manager

The LLM Evaluation Framework

MCP Toolbox for Databases is an open source MCP server for databases.

⌥ AI Coding agent for the terminal — hash-anchored edits, optimized tool harness, LSP, Python, browser, subagents, and more

Agent Skills for Google products and technologies

"OpenHarness: Open Agent Harness with a Built-in Personal Agent--Ohmo!"

Eigent: The Open Source Cowork Desktop to Unlock Your Exceptional Productivity. Local and Free Alternative to Claude Cowork.

Autonomous multi-session AI coding

Personal memory across agents

Open-source, secure environment with real-world tools for enterprise-grade agents.

The official TypeScript SDK for Model Context Protocol servers and clients

Use Claude Code, OpenCode, Cursor CLI, and Codex on mobile and web with CloudCLI (aka Claude Code UI). CloudCLI is a free open source webui/GUI that helps you manage your Claude Code session and projects remotely.

The best agent harness.

IronClaw is an Agent OS focused on privacy, security and extensibility

Security scanner for AI agent skills. Detect vulnerabilities, malicious patterns, and security risks.

A blazing fast AI Gateway with integrated guardrails. Route to 1,600+ LLMs, 50+ AI Guardrails with 1 fast & friendly API.

Code Editor for the AI Agents Era - Run an army of Claude Code, Codex, etc. on your machine

The all-in-one, open-source backend platform for agentic coding. InsForge gives your coding agent database, auth, storage, compute, hosting, and AI gateway to ship full-stack apps end-to-end.

TensorZero is an open-source LLMOps platform that unifies an LLM gateway, observability, evaluation, optimization, and experimentation.

One portable memory layer for every AI agent: local-first, Markdown-native, user-owned, and self-evolving across apps, tools, and workflows.

Multi-Agent Harness for Production AI

🤗 ml-intern: an open-source ML engineer that reads papers, trains models, and ships ML models

Agent Reinforcement Trainer: train multi-step agents for real-world tasks using GRPO. Give your agents on-the-job training. Reinforcement learning for Qwen3.6, GPT-OSS, Llama, and more!

AI Observability & Evaluation

Visual testing tool for MCP servers

The fullstack MCP framework to develop MCP Apps for ChatGPT / Claude & MCP Servers for AI Agents.

An Open-Source Asynchronous Coding Agent

Instant, Concurrent, Secure & Lightweight Sandbox for AI Agents.

AI Agent Engineering Platform built on an Open Source TypeScript AI Agent Framework

Orchestrate multiple coding agents from desktop and mobile