A control plane with a durable state kernel for long-horizon agents and teams. Keep work moving and improving across sessions, with less human attention.
-
Updated
Oct 2, 2026 - Python
Agent harnesses are the runtime scaffolding around AI agents. They usually combine context delivery, tool interfaces, planning state, memory, sandboxes, permissions, evaluation, and observability so agents can complete longer tasks reliably. Agent harnesses are especially common in coding agents, research agents, and multi-agent workflows where repeatability, safety, and traceability matter.
A control plane with a durable state kernel for long-horizon agents and teams. Keep work moving and improving across sessions, with less human attention.
Awesome list for AI agent harness engineering: tools, patterns, evals, memory, MCP, permissions, observability, and orchestration.
Knowhere extracts, parses, and outputs structured chunks ready for AI Agents and RAG.
Agent harness to make your slop code well-engineered and beautiful.
HarnessRouter Community Edition: the self-hosted, Apache-2.0 edition of the unified interface for agent harnesses. Run Codex, Claude Code, Hermes, PI, DSH, and more through one API, with sessions, streaming, files, cancellation, and failure handling. Implements the Unified Harness Protocol (UHP), an open standard. Your keys, your infrastructure.
An awesome list of Agent Harness engineering resources, including GitHub projects, tools, benchmarks, and practical guides.
AI-native agent harness for coding workflows by python: multi-model LLM orchestration, stateful sessions, tool governance, traceable delivery, and provider routing for GPT, Claude, DeepSeek, Qwen, Kimi, GLM, and MiniMax.
Codebase harness + loop engineer
🏆 Ranked list of 167 AI agent harnesses, plus templates, playbooks, MCP, and learning resources. Rescored weekly.
Local-first, open-source Claude Science alternative, before Claude Science is a thing. Turn your AI agent into personal DNA expert.
ViNote(视记AI)|DeepSeek Harness SDK 驱动的开源视频知识 Agent。以工具编排、SQLite 会话恢复和流式交互,串联 YouTube / Bilibili 检索、下载、转写与笔记生成,支持视频问答、知识卡片和思维导图。FastAPI + React,支持 OpenAI 兼容接口模型。
Deterministic safety solutions for probabilistic AI agents
Veldra — talk an agent into existence, then watch it grow. A self-hostable, local-first agent platform: describe what you need in plain language and it compiles a working agent tools, MCP, RAG, teams. The more you use it, the better it gets agents learn from your feedback and reshape as you talk.
从 0 复刻 WorkBuddy-style 桌面 AI 助手 Harness:24 章 Python 教程,覆盖 Agent Loop、工具调用、记忆系统、Sidecar、沙盒审计、DeepSeek/OpenAI 评测轨迹
Bounded-autonomy plugin harness for agents. Intent to implementation: ready, then go.
The production-ready agent harness framework for Python
A self-hosted 2D AI workspace for AI Agents
From ticket to reviewed pull request. Free and open-source, on your machine.
Zenith: a continuous-improvement harness for long-running agent tasks. Turns Claude Code, Codex, or Hermes into a multi-agent mission orchestrator via MCP/ACP.
ScienceBuddy: Recursive-in-Recursive Self-Improvement for Interactive Scientific Agents