Awesome Agent Harness

Symphony turns project work into isolated, autonomous implementation runs, allowing teams to manage work instead of supervising coding agents.

The batteries-included agent harness.

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

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

Claude Code skill implementing Manus-style persistent markdown planning — the workflow pattern behind the $2B acquisition.

AGENTS.md — a simple, open format for guiding coding agents

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.

Ghostty-based macOS terminal with vertical tabs and notifications for AI coding agents

An open-source, code-first Python toolkit for building, evaluating, and deploying sophisticated AI agents with flexibility and control.

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

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

SWE-agent takes a GitHub issue and tries to automatically fix it, using your LM of choice. It can also be employed for offensive cybersecurity or competitive coding challenges. [NeurIPS 2024]

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

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.

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

Open-source Agent Operating System

AI Agent Framework, the Pydantic way

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).

Python SDK for Agent AI Observability, Monitoring and Evaluation Framework. Includes features like agent, llm and tools tracing, debugging multi-agentic system, self-hosted dashboard and advanced analytics with timeline and execution graph view

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.

The LLM Evaluation Framework

Context window optimization for AI coding agents. Sandboxes tool output, 98% reduction. 15 platforms

Autonomous multi-session AI coding

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

Supercharge Your LLM Application Evaluations 🚀

Browser Harness | Self-healing harness that enables LLMs to complete any task.

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

A framework for few-shot evaluation of language models.

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

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

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

Agent S: an open agentic framework that uses computers like a human

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

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

Secure, Fast, and Extensible Sandbox runtime for AI agents.

A framework for building, orchestrating and deploying AI agents and multi-agent workflows with support for Python and .NET.

GitHub Copilot CLI brings the power of Copilot coding agent directly to your terminal.

Multi-Agent Harness for Production AI

AI Observability & Evaluation

An Open-Source Asynchronous Coding Agent

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

"Context engineering is the delicate art and science of filling the context window with just the right information for the next step." — Andrej Karpathy. A frontier, first-principles handbook inspired by Karpathy and 3Blue1Brown for moving beyond prompt engineering to the wider discipline of context design, orchestration, and optimization.

Cybersecurity AI (CAI), the framework for AI Security

The best agent harness.

Build effective agents using Model Context Protocol and simple workflow patterns

Specification and documentation for the Model Context Protocol

Project management skill system for Agents that uses GitHub Issues and Git worktrees for parallel agent execution.

PraisonAI 🦞 — Hire a 24/7 AI Workforce. Stop writing boilerplate and start shipping autonomous self-improving agents that research, plan, code, and execute tasks. Deployed in 5 lines of code with built-in memory, RAG, and support for 100+ LLMs.

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