Awesome Harness Engineering

🙌 OpenHands: AI-Driven Development

Universal memory layer for AI Agents

A programming framework for agentic AI

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

Installable GitHub library of 1,800+ agentic skills for Claude Code, Cursor, Codex CLI, Gemini CLI, Antigravity, and more. Includes specialized plugins, installer CLI, bundles, workflows, and official/community skill collections.

Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 60-95% fewer tokens, same answers. Library, proxy, MCP server.

Composio powers 1000+ toolkits, tool search, context management, authentication, and a sandboxed workbench to help you build AI agents that turn intent into action.

A lightweight, powerful framework for multi-agent workflows

Cognee is the open-source AI memory platform for agents. Give your AI agents persistent long-term memory across sessions with a self-hosted knowledge graph engine.

Self-evolving Context Database for AI Agents. Unify Agent Memory, Knowledge RAG and Skills.

The batteries-included agent harness.

The AI Toolkit for TypeScript. From the creators of Next.js, the AI SDK is a free open-source library for building AI-powered applications and agents

Platform for stateful agents: AI with advanced memory that can learn and self-improve over time.

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.

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

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

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).

Hindsight: Agent Memory That Learns

A collection of projects designed to help developers quickly get started with building deployable applications using the Claude API

AG-UI: the Agent-User Interaction Protocol. Bring Agents into Frontend Applications.

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

AI Observability & Evaluation

NeMo Guardrails is an open-source toolkit for easily adding programmable guardrails to LLM-based conversational systems.

Build an agent harness and control it end-to-end. Open-source SDK for production AI agents in Python & TypeScript - any model, any cloud.

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

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.

Zep | Examples, Integrations, & More

A Comprehensive Benchmark to Evaluate LLMs as Agents (ICLR'24)

The World's First Unified Virtual Filesystem For AI Agents

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

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

Inspect: A framework for large language model evaluations

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.

Build, Evaluate, and Deploy GUI Agents — online RL training, standardized benchmarks, and real-device deployment in one framework.

a recursive self-improving harness designed to help your agents (and future iterations of those agents) succeed on any task

Weave is a toolkit for developing AI-powered applications, built by Weights & Biases.

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.

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

Audit-grade multi-agent orchestration for CLI coding agents (Claude Code, Codex, Gemini CLI, +40 more). HMAC-chained audit log, signed agent cards, per-artefact lineage, air-gap deploy. The orchestrator your compliance team will sign off on. https://bernstein.run

Human-in-the-Loop Protocol for Autonomous Agent Services — Open Standard (v0.8)