Awesome Harness Engineering

Sub-millisecond VM sandboxes for AI agents via copy-on-write forking

Inspect: A framework for large language model evaluations

Portable AI agent orchestration with mechanical protocol enforcement. 186 agents, zero runtime dependencies.

Use Claude Code's autonomous agent loop with DeepSeek V4 Pro, OpenRouter, or any Anthropic-compatible backend. Same UX, 17x cheaper.

One brain, many harnesses. Portable .agent/ folder (memory + skills + protocols) that plugs into Claude Code, Cursor, Windsurf, OpenCode, OpenClaw, Hermes, or DIY Python — and keeps its knowledge when you switch.

Official, AWS-supported MCP servers, skills, and plugins to help AI agents build on AWS

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.

Coding Agent singularly focused efficiency and context curation. Reduces API costs by 50-80% vs other agent AND improves the code quality at the same time. Uses Hash Anchored edits, massively parallel operations, AST manipulation and many many other optimizations. https://dirac.run/

Code and Data for Tau-Bench

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

Reference code for the Meta-Harness paper.

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

Give Claude Code a memory that evolves with your codebase. Hooks automatically capture sessions, the Claude Agent SDK extracts key decisions and lessons, and an LLM compiler organizes everything into structured, cross-referenced knowledge articles - inspired by Karpathy's LLM Knowledge Base architecture.

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

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

The MCP server that turns Claude into the only coding agent hitting 100% on a real benchmark. -77% active tokens, -76% wall time, 0 losses across 96 tasks on Claude Opus 4.7. Structural code navigation + persistent memory. Works with every MCP client.

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

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.

Stash — persistent memory layer for AI agents. Episodes, facts, and working context stored in Postgres. MCP server included. Self-hosted, single binary, no cloud required.

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.

Every practical and proposed defense against prompt injection.

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

Bring your own agent and build a self-improving agentic system. Automatically mine failures, optimize the agent harness, and gate against regressions.

You should sandbox your agents. This is for when you don't.

State machine guardrails for AI agents

Browser Use Box: a 24/7 Claude Code agent for Playwright-style browser automation with Browser Use Cloud, Telegram, and a real browser on any box you own.

React components for visualizing traces from AI agents

MCP Fusion - The TypeScript framework for secure MCP servers.

tui-use lets agents interact with programs that expect a human at the keyboard — REPLs, debuggers, TUI apps, and anything else bash can't reach.

Meta Harness Implementation

Demonstration of an agent harness with access to tools like Slack, GitHub, and Linear so it can act as your own complete software engineer.

Continual harness optimization

swebench repro script for running confucius-code-agent (CCA)

Automated harness evolution for AI agents. A Claude Code plugin that iteratively optimizes system prompts, routing, retrieval, and orchestration code using full-trace counterfactual diagnosis. Based on Meta-Harness (Lee et al., 2026).

Agent debugging skill. Stop AI debugging guesswork with runtime evidence.

Build your own coding agent workshop - Feb 19th 2026

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

No description.

Point-in-time snapshot of projects describing themselves as AI agent harnesses (April 2026)

ML6 x AISO Agent Workshop (March 2026)