AI Agent Harnesses
Point-in-time snapshot: April 2026
A curated list of projects describing themselves as AI agent harnesses or related to "harness engineering."
A Note On Terminology
The term "agent harness" emerged in late 2025 / early 2026 as a way to describe the orchestration layer that runs an AI agent. A harness manages the tool-dispatch loop, permissions, context, and lifecycle of an agent — as distinct from a framework (which provides higher-level abstractions for building agents) or a backend (which provides the inference and model serving).
The term gained traction partly through the adjacent concept of "harness engineering" — the practice of configuring and optimizing these orchestration layers (writing CLAUDE.md files, designing tool schemas, structuring agent prompts, etc.).
This list captures projects that self-identify with the "harness" label as of April 2026. The terminology is still fluid and not universally agreed upon — some projects listed here blur the line between harness, framework, and agent platform.
Agent Harnesses
Projects that provide runtime orchestration for AI agents — tool dispatch, conversation loops, context management, and agent lifecycle.
bytedance/deer-flow — Open-source long-horizon SuperAgent harness that researches, codes, and creates. Handles tasks from minutes to hours using sandboxes, memories, tools, subagents. · Python · 57,759
bytedance/deer-flow View on GitHubcode-yeongyu/oh-my-openagent — Agent harness (previously oh-my-opencode) with multi-provider support. · TypeScript · 48,154
code-yeongyu/oh-my-openagent View on GitHublangchain-ai/deepagents — Agent harness built with LangChain and LangGraph. Planning tool, filesystem backend, and subagent spawning. · Python · 19,118
langchain-ai/deepagents View on GitHubaden-hive/hive — Outcome-driven agent development framework and runtime harness. Self-improving, human-in-the-loop. · Python · 10,038
aden-hive/hive View on GitHubxerrors/Yuxi — Agent harness integrating LightRAG knowledge base and knowledge graphs. Built with LangChain + Vue + FastAPI, supports MCP. · Python · 4,805
xerrors/Yuxi View on GitHubmindfold-ai/Trellis — Agent harness for agentic coding workflows. · Python · 4,610
mindfold-ai/Trellis View on GitHubHKUDS/OpenHarness — Open Agent Harness. · Python · 3,363
HKUDS/OpenHarness View on GitHubcan1357/oh-my-pi — AI coding agent for the terminal — hash-anchored edits, optimized tool harness, LSP, subagents. · TypeScript · 2,646
can1357/oh-my-pi View on GitHubkevinrgu/autoagent — Autonomous harness engineering. · Python · 2,084
kevinrgu/autoagent View on GitHubchrysb/alphaclaw — Setup harness for OpenClaw. Deploy in minutes, stay running for months. · JavaScript · 943
chrysb/alphaclaw View on GitHube10nMa2k/cc-mini — Ultra-light harness scaffolding for AI agents, a mini version of Claude Code. · Python · 677
e10nMa2k/cc-mini View on GitHubtruffle-ai/dexto — Coding agent and general agent harness for building and orchestrating agentic applications. · TypeScript · 608
truffle-ai/dexto View on GitHubChachamaru127/claude-code-harness — Claude Code dedicated development harness — autonomous Plan-Work-Review cycle. · Shell · 420
Chachamaru127/claude-code-harness View on GitHubaristoteleo/PantheonOS — Evolvable, distributed agent framework and harness for data science and bioinformatics. · Python · 370
aristoteleo/PantheonOS View on GitHubMaxGfeller/open-harness — Code-first, composable SDK to build powerful AI agents. · TypeScript · 337
MaxGfeller/open-harness View on GitHubvortezwohl/Autono — ReAct-based highly robust autonomous agent (harness) framework. MCP support. · Python · 209
vortezwohl/Autono View on GitHubaiming-lab/AutoHarness — Automated harness engineering for AI agents — audit, governance, safety. · Python · 181
aiming-lab/AutoHarness View on GitHubdust-tt/srchd — Research agents harness. · TypeScript · 69
dust-tt/srchd View on GitHubthu-nmrc/OpenHarness — Fully autonomous AI agent execution framework for OpenClaw built on harness engineering. From Tsinghua University. · Python · 62
thu-nmrc/OpenHarness View on GitHubthu-nmrc/OpenHarness-For-Codex — Specialized variant of OpenHarness designed for AI-driven software development. · Python · 39
thu-nmrc/OpenHarness-For-Codex View on GitHubmastersof-ai/harness — Agent runtime with full system prompt control. Define agents in markdown, run in terminal TUI or web UI. Powered by Claude Agent SDK. · TypeScript · 31
mastersof-ai/harness View on GitHub
Resource Lists & Guides
Projects focused on curating resources, guides, and best practices for harness engineering rather than providing a harness runtime.
walkinglabs/awesome-harness-engineering — Awesome tools and guides for harness engineering. · 1,264
walkinglabs/awesome-harness-engineering View on GitHubAutoJunjie/awesome-agent-harness — Curated list of agent harness projects, orchestration tools, and developer resources. · 277
AutoJunjie/awesome-agent-harness View on GitHubPicrew/awesome-agent-harness — Awesome list of agent harness engineering resources — projects, tools, benchmarks, and guides. · Python · 109
Picrew/awesome-agent-harness View on GitHubalchemiststudiosDOTai/harness-engineering — Harness engineering discussion — shortcuts, automation, hacks, and productivity with code agents. · Shell · 87
alchemiststudiosDOTai/harness-engineering View on GitHubjrenaldi79/harness-engineering — Context engineering for coding agents — CLAUDE.md templates, enforcement, and best practices field guide. · JavaScript · 55
jrenaldi79/harness-engineering View on GitHub
Star counts as of April 2026. This is a static snapshot and will not be updated.