Awesome Agent Harness

Agenta is a workspace where you and your team build agents and automations.

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!

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

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

Open-source security automation platform for teams and AI agents

agent-sandbox enables easy management of isolated, stateful, singleton workloads, ideal for use cases like AI agent runtimes and reinforcement learning (RL).

Agent Skills as a Memory Layer

LangChain 🔌 MCP

Evaluation and Tracking for LLM Experiments and AI Agents

The platform for LLM evaluations and AI agent testing

Devon: An open-source pair programmer

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

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

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

OpenLIT is the open-source agent harness engineering platform: trace, evaluate, guard, and improve everything around the model in your AI agents, on OTEL.

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

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

A production-oriented multi-agent orchestration framework.

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

Professional context and harness engineering for Claude Code and OpenAI Codex. Build production-grade software with spec-driven development, TDD, persistent memory, quality gates, code intelligence, human oversight, and end-to-end verification.

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

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.

Continual learning infra for self-improving agents

Code repo for "WebArena: A Realistic Web Environment for Building Autonomous Agents"

Reference code for the Meta-Harness paper.

OpenTelemetry Instrumentation for AI Observability

Evaluate and improve models and agents using environments

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

The Cloud Sandbox Built for AI Agents

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

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

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

Batteries for your Pydantic AI agent.

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.

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.

Security Governance for Agentic AI

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.

An agent benchmark with tasks in a simulated software company.

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

Collection of evals for Inspect AI

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

The action firewall for AI agents. Enforce policy and human approval before risky tool calls, shell commands, workflows, and production changes, with auditable evidence.

A generative AI-powered framework for testing virtual agents.

The production-ready agent harness framework for Python

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

WorkArena: How Capable are Web Agents at Solving Common Knowledge Work Tasks?

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