Awesome Agent Harness

Own your AI. The native macOS harness for AI agents -- any model, persistent memory, autonomous execution, cryptographic identity. Built in Swift. Fully offline. Open source.

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

Self-hosted TypeScript agent runtime with durable approvals and verifiable run records. Own it, approve it, audit it.

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

A model-driven approach to building AI agents in just a few lines of code.

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.

ByteRover CLI (brv) - The portable memory layer for autonomous coding agents (formerly Cipher)

TencentDB Agent Memory delivers fully local long-term memory for AI Agents via a 4-tier progressive pipeline, with zero external API dependencies.

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!

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

Portable AI agent runtime for the JVM. One @Agent class runs on Spring AI, LangChain4j, Anthropic, or 9 more behind one SPI. Token streaming, tool calls, human approvals, and governance over WebSocket, SSE, gRPC, or WebTransport/HTTP3. Speaks MCP, A2A, and AG-UI.

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

Agent Skills as a Memory Layer

The platform for LLM evaluations and AI agent testing

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

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.

Official Microsoft Learn MCP Server and CLI tool – powering LLMs and AI agents with real-time, trusted Microsoft docs & code samples.

A Go framework for building production agent systems with graph workflows, tools, memory, A2A, AG-UI, MCP, evaluation, and observability.

Continual learning infra for self-improving agents

E2B Desktop Sandbox for LLMs. E2B Sandbox with desktop graphical environment that you can connect to any LLM for secure computer use.

LLM powered fuzzing via OSS-Fuzz.

The multi-agent harness that checks the work: verifies agent runs by artifacts (stop-hook gates, independent judges, append-only event logs) across Claude Code, Codex, Cursor, and 10+ runtimes.

Open-source AI agent harness in native Rust — GUI, CLI, headless, and webapp from one binary. Multi-provider, MCP, skills, plugins, agent teams.

Evaluate and improve models and agents using environments

A desktop multi-agent harness built with Rust, Tauri, and React, powered by langgraph-rust.

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.

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

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.

Agent harness and tookit for building AI agents and agentic applications. CLI and SDKs included

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

Self-hosted Personal AI + agent runtime in .NET (NativeAOT-friendly)

Safe runtime for autonomous on-chain AI agents: isolated sandboxes, Library skills, encrypted secrets.

A collection of Model Context Protocol (MCP) servers, clients and developer tools by IBM.

The production-ready agent harness framework for Python

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

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

Benchmark for comparing agent harnesses on everyday online tasks — fixes the base model, varies the harness. Sister project of ClawBench, same scoring pipeline.