Open highlighted repo slot
Put your repository first
Promote a GitHub repo at the top of Awesome repository list views for 7 days.
Awesome List
An awesome list of Agent Harness engineering resources, including GitHub projects, tools, benchmarks, and practical guides.
GitHub stars and default-branch commits for Picrew/awesome-agent-harness.
Open highlighted repo slot
Promote a GitHub repo at the top of Awesome repository list views for 7 days.
Agent Skills as a Memory Layer
The platform for LLM evaluations and AI agent testing
Cascading runtime for AI agents. Optimize cost, latency, quality, and policy decisions inside the agent loop.
A streamlined and customizable framework for efficient large model (LLM, VLM, AIGC) evaluation and performance benchmarking.
Official Microsoft Learn MCP Server and CLI tool – powering LLMs and AI agents with real-time, trusted Microsoft docs & code samples.
τ-Bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains
A Go framework for building production agent systems with graph workflows, tools, memory, A2A, AG-UI, MCP, evaluation, and observability.
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.
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.
Open-source AI agent harness in native Rust — GUI, CLI, headless, and webapp from one binary. Multi-provider, MCP, skills, plugins, agent teams.
A desktop multi-agent harness built with Rust, Tauri, and React, powered by langgraph-rust.
Evaluate and improve models and agents using environments
The Continuous-Improvement Stack for Agents. Our environment data and evals power agent improvement and monitoring.
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.
A coding agent and general agent harness for building and orchestrating agentic applications.
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.
Open-source benchmark for browser AI agents on daily tasks.
Safe runtime for autonomous on-chain AI agents: isolated sandboxes, Library skills, encrypted secrets, and OKX read-only security checks.
Self-hosted Personal AI + agent runtime in .NET (NativeAOT-friendly)
A collection of Model Context Protocol (MCP) servers, clients and developer tools by IBM.
Secure runtime to sandbox AI agent tasks. Run untrusted code in isolated WebAssembly environments.
The production-ready agent harness framework for Python
Open Python agent harness for production AI apps: tools, MCP, memory, workspace, telemetry, subagents, background tasks, and OmniServe APIs.