Awesome Harness Engineering

Zep | Examples, Integrations, & More

autonomous harness engineering

AI observability platform for production LLM and agent systems.

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

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

Agent harness to make your slop code well-engineered and beautiful.

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

Inspect: A framework for large language model evaluations

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

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.

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.

Code and Data for Tau-Bench

Reference code for the Meta-Harness paper.

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

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.

MCP server that gets Claude to 97.9% (188/192) on a real coding benchmark at -80% active tokens and -83% wall time, vs 78.3% plain. Structural code navigation + persistent memory engine. Works with every MCP client.

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

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.

Deterministic orchestrator for CLI coding agents (Claude Code, Codex, Gemini CLI, +40 more). No model in the coordination loop, so parallel runs in per-task git worktrees replay byte-identically. Signed lineage plus an opt-in HMAC audit chain a reviewer checks offline, without rerunning it. Cluster mode, air-gap deploy. https://bernstein.run

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.

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

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.

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

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).

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

No description.

ML6 x AISO Agent Workshop (March 2026)