Havuz

智能体 = 大模型 + Harness。深入剖析 Harness 工程原理、设计、实现与实践！

The DeepSeek and OpenRouter Harness built on Elixir

OpenCode++: a Coding Agent Reliability Harness for OpenCode, adding context, edit boundaries, command evidence, verification gates, impact a

First-tree routes work to the right agent, gives it the same context your team has, and loops humans in only when the rules say so. Lives in

Lives inside your Claude Code session. Capture work as structured experience, then render resumes, Korean cover letters, interview answers,

Spec-driven development for Claude Code, layered on OpenSpec. You read one spec; parallel agents ship it to a tested commit.

Build a coding agent from scratch, one harness primitive at a time. 15 chapters (ch-00..ch-14), each green on two gates.

Starter kit for building an agent harness, the map, guardrails, and feedback loops that let AI agents ship software reliably.

Nausicaa treats an Agent run as a dynamic topology of Lanes rather than one fixed linear loop. The model can decide when to observe, fan out

Reliability harness for long-running OpenClaw agents: persistent state, strict task contracts, scheduled execution, and external validation.

A set of Claude Code and GitHub Copilot plugins providing the AI Literacy framework's complete development workflow — harness engineering, a

Create your own benchmark for coding AI Agents

Context engineering for coding agents - CLAUDE.md templates, mechanical enforcement, and a field guide to 20+ best practices. Bootstrap with

Open-source enterprise AI workforce platform — containerized roles, declarative skills, MCP tools, policy-driven security, K8s-native schedu

Build LLM systems you actually control. A free, open engineering book + course — from tokenization to serving your own models. Mechanisms, t

A work-centered runtime for agentic software engineering. Work persists; agents, context, and graphs assemble around it.

CubeLoop — a Pythonic, async-native agent harness core designed for high performance, readability, and production-grade persistence.

Idea-to-store autonomous harness for Flutter/Flame games across Claude Code, Antigravity, and Codex. Automates research, planning, design, g

Cross-platform AI agent harness for 12+ hour autonomous development cycles. Spec-driven, DAG-orchestrated, with a 3-critic evaluation pipeli

A human-governed AI coding workflow that distills ephemeral session context into persistent project memory—making work traceable, reviewable

The missing tool to sift your Claude Code sessions: regex search across all record types, recover files, extract images, inspect subagent to

Lightweight Doc-to-agent-ready knowledge pipeline. Three-stage Bronze→Silver→Gold architecture extracts structured elements, page content, a

The first AI plugin that speaks first. Code-enforced learning + active forgetting + PAC (Proactive Accountability Challenge). Works with Cla

The coding agent you don’t have to watch. Start a task and walk away. AFK builds the feature, verifies its own work, and texts you when it’s

Map, inspect, and audit AI-agent markdown ecosystems (skills, agents, commands, hooks) as a graph.

Mexus is a local web console for managing multiple CLI AI Agent instances in parallel.

Self-improving agent harness for ChatGPT and Codex on Mac. #1 on AssistantBench. On-disk memory, privacy zones, verified completion.

Run reviewable, resumable coding-agent workflows across Claude Code, Codex, Gemini, GitHub Copilot CLI, or any CLI. You define the stages in

Spec-driven development and context engineering for Claude Code, Cursor, Codex, and GitHub Copilot — backed by project context in Git.

🚀 Level up your career with GenAI. 📄 Tailor your CV to any JD, 🔍 automate company research, and 🗓️ generate custom interview prep plans for

OpenBrowser is free local AI coding agent — use your ChatGPT, Claude, or Gemini browser subscription. No API keys. CLI + Chrome extension br

基于pi agent core构建的harness agent

Production-grade software delivery for coding-agent teams on Multica — dynamic planning, deterministic execution, verifiable delivery.

《从0开始构建 AI 智能体》 一本带你亲手打造属于自己的AI Agent 的实战书

Skill repository to enforce Engineering disclipline in coding assistants

Self-hosted 多用户 WeChat / 微信 AI 智能体控制台，支持 Web 管理、Docker部署、MCP、Skills、记忆、定时任务、沙盒执行和长期运行，支持分享AI Bot给团队成员。

Entente — provenance engineering for coding agents: handoffs become confirmable, verifiable, retryable contracts; agents form a network with

The linter for your agent harness. Works with Claude Code, Codex, and Cursor.

Open-source Environment toolkit of claw-like agents, support task/harness generation and evaluation

A cross-platform agent framework and samples, support on Windows/MacOS/Android/iOS/HarmonyOS

Free and open-source production-grade RAG platform that converts documents into conversational AI assistants. Enable private deployment for

Work less, produce more, Be lazy. The-LazyIDE is the desktop AI IDE built for lazy-smart engineers: a LazyManager who plans and orchestrates

《智能体工程：从一句话到一个闭环》（Prompt · Context · Harness · Loop），本书将大语言模型驱动的智能体系统拆解为四种递进的工程范式，四种范式从 Token 到 System，从一次调用到完整的自主闭环，构成了智能体系统的完整工程视图。

Agent-first Rust/Axum backend harness for SDD-driven Clean/Hexagonal/DDD services, ECS-style runtime composition, counter-service reference

Agentic browser automation built from small, reusable pieces.

AI Harness Engineering Template — guardrails, gates, and boundaries for AI coding agents. One-command install. Zero dependencies.

A Git-native knowledge layer for your team — and a set of tool suite that keeps it alive.

Distribute and safely manage a cross-host personal harness and durable work state.

Simple Long Horizon Agent - A simple yet effective AI agent for learning, experimentation, and long horizon work.

An AI agent for your desktop and terminal.