harness
Tracked open-source repos tagged harness, sorted by stars.
- #31
A catgirl who lives with you in real time — reaching out first, sharing your media, and actually getting things done, powered by an embodied emotional engine.🐱❤️一只会主动找你玩的 AI 猫娘。
★ 2,719+19Star change over the last 7 days - #32
DeepBot is a system-level AI assistant built for both personal productivity and enterprise workflows — one-click setup, seamless experience, and native Feishu integration.
★ 2,275+1Star change over the last 7 days - #33
🧩 FrontierAgent, our agent framework, open-sourced alongside it — native command-line TUI, ReAct and Agent Team modes, one command on macOS and Linux, no preinstall, no hard Docker dependency.
★ 2,063+613Star change over the last 7 days - #34
PhyAgentOS is a Recursive Self-Improving (RSI) physical agent operating system that enables agents to recursively self-improve through agentic workflows.
★ 2,009+123Star change over the last 7 days - #35
🐧 Harness for RSI. Let AI Build AI. Multi-Agent Auto-Dev Platform. Everything is Transparent.
★ 1,935+119Star change over the last 7 days - #36
A desktop app to prototype agent ideas, inspect every harness step, replay failures, and evaluate performance, all in one place. Local-first, cloud-ready for managed agents.
★ 1,775+32Star change over the last 7 days - #37
AI automation skills specifically designed for Unity
★ 1,697+13Star change over the last 7 days - #38
🦭 会记忆、能持续推进目标、会动态编排多 Agent 的跨端桌面 AI 助手,也可服务化常驻 NAS / 云端 | A cross-device desktop AI agent with memory, autonomous goals, dynamic workflows, and headless deployment
★ 1,555+23Star change over the last 7 days - #39
The long-horizon computer-use harness. Run AI agents across desktop apps and the CLI for extended periods while preserving task state and making reliable progress on complex workflows. Features fresh-context execution, durable verified state, independent auditing, recoverable progress, and native Claude Code / Codex / OpenClaw integration.
★ 1,454+85Star change over the last 7 days - #40
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.
★ 1,323+47Star change over the last 7 days - #41★ 1,298-1Star change over the last 7 days
- #42
The Agent Harness for AI-Human Collaboration, inspired by the AI-DLC (AI-Driven Development Lifecycle)
★ 1,154+3Star change over the last 7 days - #43
A desktop multi-agent harness built with Rust, Tauri, and React, powered by langgraph-rust.
★ 1,103+1Star change over the last 7 days - #44
HugAgentOS: The Self-Evolving AgentOS for Ontology-Grounded Trustworthy Reasoning
★ 1,034+225Star change over the last 7 days - #45
DeepSeek Harness (DSH) ecosystem: curated plugins, tools, and infrastructure from dsh-external/hub and the public dsh-plugin topic.
★ 1,014+67Star change over the last 7 days - #46
The all-in-one AI agent living in your terminal. Build landing, mobile apps, backends, manages files, deep research, schedule tasks and events. Self-improving, self-healing, fully autonomous. TUI, CLI and Daemon. Connect to your favorite channels.
★ 930+14Star change over the last 7 days - #47
Exo is an agent + harness architecture that is fully recursive, able to safely edit all aspects of itself at runtime to get better at your tasks.
★ 913+18Star change over the last 7 days - #48
A Claude Code plugin that makes Opus behave like Fable — completion, evidence, and verification enforced as procedure. Ships only what a Fable-vs-Opus comparison proved transferable.
★ 895+0Star change over the last 7 days - #49
AI workflow automation plugin for intelligent code generation with Claude/Codex
★ 887+1Star change over the last 7 days - #50
CUGA is an open-source generalist agent harness for the enterprise, supporting complex task execution on web and APIs, OpenAPI/MCP integrations, composable architecture, reasoning modes, and policy-aware features.
★ 873-1Star change over the last 7 days - #51
🤖 Automatically collected AI repos, tools, websites, papers & tutorials. 实用AI百宝箱 💎
★ 860+1Star change over the last 7 days - #52
ClawProBench is a live-first benchmark harness for evaluating LLM agents in the OpenClaw runtime with deterministic grading and repeated-trial reliability.
★ 823+0Star change over the last 7 days - #53★ 817+7Star change over the last 7 days
- #54
Harness the power of local LLMs with this TUI MCP Client for Ollama. Featuring all core MCP primitives (tools, prompts, resources), agent mode, multi-server, model switching, streaming responses, human-in-the-loop, thinking mode, model params config, system prompts, and saved preferences.
★ 816+2Star change over the last 7 days - #55
🏆 Curated, ranked list of AI agent harnesses (100+) — plus an MCP server, llms.txt & JSON so agents can recommend them too. Rescored weekly.
★ 802+66Star change over the last 7 days - #56
Claw-Eval is an evaluation harness for evaluating LLM as agents. All tasks verified by humans.
★ 766+5Star change over the last 7 days - #57
DeepSeek Harness (dsh) 从 0 到 1 深度手册:安装/插件开发/性能调优/实测案例/同模型多 Agent 实测对比(中文 + 英文 PDF)
★ 750+45Star change over the last 7 days - #58
The most autonomous AI agent framework: runs unattended on GitHub Actions, self-healing skills, drives Claude Code, Grok, Codex & more. No approval loops. Configure once, forget forever.
★ 716+13Star change over the last 7 days - #59
Community desktop companion for DeepSeek Harness — one-click Electron app for macOS and Windows
★ 712+244Star change over the last 7 days - #60
Open-source AI Agent platform for teams. Your agents don't just chat — they read files, run code, call APIs, and deliver results.
★ 630+32Star change over the last 7 days