Awesome Agent Harness

Flexible and powerful framework for managing multiple AI agents and handling complex conversations

Open-source observability for your GenAI or LLM application, based on OpenTelemetry

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.

A simple SWE style browser agent framework that achieves SOTA results on long horizon web tasks.

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

Nexent is a zero-code platform for auto-generating production-grade AI agents using Harness Engineering principles — unified tools, skills, memory, and orchestration with built-in constraints, feedback loops, and control planes.

SWE-bench: Can Language Models Resolve Real-world Github Issues?

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

The CLI and skills that turn any coding assistant into an expert at creating, evaluating, and deploying AI agents on Google Cloud.

An open-source Collaborative Multi-Agent OS for transparent, human-in-the-loop task coordination via Matrix rooms.

AI Agent Governance Toolkit — Policy enforcement, zero-trust identity, execution sandboxing, and reliability engineering for autonomous AI agents. Covers 10/10 OWASP Agentic Top 10.

Our library for RL environments + evals

Your agent in your terminal, equipped with local tools: writes code, uses the terminal, browses the web. Make your own persistent autonomous agent on top!

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

Next Generation Agentic Proxy for AI Agents and MCP servers

Open-source security automation platform for teams and AI agents

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

Evaluation and Tracking for LLM Experiments and AI Agents

Cascading runtime for AI agents. Optimize cost, latency, quality, and policy decisions inside the agent loop.

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

Framework for evaluating and improving agents

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

A streamlined and customizable framework for efficient large model (LLM, VLM, AIGC) evaluation and performance benchmarking.

Agent harness to make your slop code well-engineered and beautiful.

Security scanner for AI agents, MCP servers and agent skills.

Open source platform for AI Engineering: OpenTelemetry-native LLM Observability, GPU Monitoring, Guardrails, Evaluations, Prompt Management, Vault, Playground. 🚀💻 Integrates with 50+ LLM Providers, VectorDBs, Agent Frameworks and GPUs.

Build applications that make decisions (chatbots, agents, simulations, etc...). Monitor, trace, persist, and execute on your own infrastructure.

A benchmark for LLMs on complicated tasks in the terminal

Terminal coding agent powered by Kimchi's multi-model orchestration

A production-oriented multi-agent orchestration framework.

τ-Bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains

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.

OpenTelemetry Instrumentation for AI Observability

ClawKeeper: Comprehensive Safety Protection for OpenClaw Agents Through Skills, Plugins, and Watchers (aka The Norton for OpenClaw)

Tensorlake is a serverless runtime for sandboxes and deploying background agentic applications

CUGA is an open-source generalist agent harness for the enterprise, supporting complex task execution on web and APIs, OpenAPI/MCP integrations, composable architecture, reasoning modes, and policy-aware features.

No description.

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.

CheetahClaws: A Fast and Easy-to-Use Agent Harness Infrastructure for Long-Horizon, Multi-Model, and Tool-Using AI Systems

Official AHE code — Agentic Harness Engineering: observability-driven automatic evolution of coding-agent harnesses (concurrent w/ meta-harness). NexAU-AHE reaches 84.7% ± 2.1 pass@1 on Terminal-Bench 2 (GPT-5.5). Lifts GPT-5.4 69.7→77.0% over 10 iters, beats Codex/ACE/Training-Free GRPO; frozen harness transfers to SWE-bench-Verified.

Claw-Eval is an evaluation harness for evaluating LLM as agents. All tasks verified by humans.

Sandboxed code execution for AI agents, locally or on the cloud. Massively parallel, easy to extend. Powering SWE-agent and more.

The open agent control plane. Govern autonomous AI agents with pre-execution policy enforcement, approval gates, and audit trails. Works with LangChain, CrewAI, MCP, and any framework.

Deterministic safety solutions for probabilistic AI agents

A generative AI-powered framework for testing virtual agents.

Secure runtime to sandbox AI agent tasks. Run untrusted code in isolated WebAssembly environments.