Awesome Agent Harness

The agent that grows with you

Model Context Protocol Servers

🙌 OpenHands: AI-Driven Development

AI coding assistant skill (Claude Code, Codex, OpenCode, Cursor, Gemini CLI, and more). Turn any folder of code, SQL schemas, R scripts, shell scripts, docs, papers, images, or videos into a queryable knowledge graph. App code + database schema + infrastructure in one graph.

Universal memory layer for AI Agents

Python SDK, Proxy Server (AI Gateway) to call 100+ LLM APIs in OpenAI (or native) format, with cost tracking, guardrails, loadbalancing and logging. [Bedrock, Azure, OpenAI, VertexAI, Cohere, Anthropic, Sagemaker, HuggingFace, VLLM, NVIDIA NIM]

aider is AI pair programming in your terminal

Build, run, and manage agent platforms.

Multi-harness agentic plugin marketplace for Claude Code, Codex CLI, Cursor, OpenCode, GitHub Copilot, and Gemini CLI

Build resilient agents.

The batteries-included agent harness.

Beads - A memory upgrade for your coding agent

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

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

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

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

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

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

Open source MCP Servers for AWS

Plano is an AI-native proxy and data plane for agentic apps — with built-in orchestration, safety, observability, and smart LLM routing so you stay focused on your agents core logic.

Omnigent is an open-source AI agent framework and meta-harness: orchestrate Claude Code, Codex, Cursor, Pi, and custom agents — swap harnesses without rewriting, enforce policies and sandboxing, and collaborate in real time from any device.

🧊 Open source LLM observability platform. One line of code to monitor, evaluate, and experiment. YC W23 🍓

Python SDK for AI agent monitoring, LLM cost tracking, benchmarking, and more. Integrates with most LLMs and agent frameworks including CrewAI, Agno, OpenAI Agents SDK, Langchain, Autogen, AG2, and CamelAI

All-in-One Sandbox for AI Agents that combines Browser, Shell, File, MCP and VSCode Server in a single Docker container.

The open-source LLMOps platform: prompt playground, prompt management, LLM evaluation, and LLM observability all in one place.

An AI Gateway, registry, and proxy that sits in front of any MCP, A2A, or REST/gRPC APIs, exposing a unified endpoint with centralized discovery, guardrails and management. Optimizes Agent & Tool calling, and supports plugins.

Enterprise AI Platform with guardrails, MCP registry, gateway & orchestrator

Open-source security automation platform for teams and AI agents

LangChain 🔌 MCP

AI-Driven Life Cycle (AI-DLC) adaptive workflow steering rules for AI coding agents

Devon: An open-source pair programmer

Amazon Bedrock Agentcore accelerates AI agents into production with the scale, reliability, and security, critical to real-world deployment.

AI Agent Builder and Runtime by Docker Engineering

agent-sandbox enables easy management of isolated, stateful, singleton workloads, ideal for use cases like AI agent runtimes.

The NVIDIA NeMo Agent toolkit is an open-source library for efficiently connecting and optimizing teams of AI agents.

A benchmark for LLMs on complicated tasks in the terminal

LLM powered fuzzing via OSS-Fuzz.

Open-source, end-to-end platform for evaluating, observing, and improving LLM and AI agent applications. Tracing · Evals · Simulations · Datasets · Gateway · Guardrails. Self-hostable. Apache 2.0.

The Continuous-Improvement Stack for Agents. Our environment data and evals power agent improvement and monitoring.

A production-ready runtime framework for agent apps with secure tool sandboxing, Agent-as-a-Service APIs, scalable deployment, full-stack observability, and broad framework compatibility.

Open-source benchmark for browser AI agents on daily tasks.

Open Python agent harness for production AI apps: tools, MCP, memory, workspace, telemetry, subagents, background tasks, and OmniServe APIs.

Evaluation harness for OpenHands V1.