Havuz

Local agency/runtime harness for ChatGPT Web: repositories, tasks, commands, validation, Git, skills/memory, observability, and opt-in compu

Gray is an open-source (MIT) AI agent harness shipped as one static Rust binary. Bash-only tools, resumable JSONL sessions, a self-compactin

AI coding agent framework — portable, stage-gated harness for Claude Code, Codex, and OpenCode

Jev-powered decision layer for DeepSeek Harness

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

Local-first agent harness (Windows + Ollama) for 2–9B models. Same 2B model: 0.017 → 0.821 across four agent harnesses — 48×. 288-cell bench

Pixir: supervised subagents and workflows for coding agents

Your AI coding harness, ported to every client you use. Capture Claude Code (or Codex) rules, hooks, skills, subagents, commands and MCP ser

Pi coding-agent harness with durable sessions, causal history, reversible components, and approval-gated host self-extension.

Make AI agents aim higher without losing control: a Claude Code skill with two bars per task, a cheap gate check before expensive work, and

The control plane for your coding agents, however you run them. One checkout of rules, skills, subagents, hooks and stances, projected into

A coding agent that rewrites its own harness (prompts, tools, compiled core) while it works, so the harness grows with the model. A Root it

A recursive self-improvement (RSI) workflow that evolves both target agents (e.g., Pi and DeepSeek Harness) and the RSI system itself.

Autonomous AI research harness for Claude Code. Sibling to rockie-codex (OpenAI Codex CLI). Apache-2.0.

OpenClaw 源码深度研究：27 章技术主线 + 2 月以来 PR 演进 + fork/变种生态 + 缺陷与 roadmap（2026-04 snapshot）

A harness for hosted Grok Bot crews. Its core rule: it is not allowed to guess.

Agentic coding scheduler, a Rust agent harness that runs background coding agents autonomously

Your AI Video Harness. Runs locally, with a visual editor so you can jump in anytime.

Forge your own agent harness — a config-to-code generator that renders a thin, standalone Python agent harness you fully own. No LangChain/L

Multiplayer harness where humans and AI agents work together and build on shared context.

Evidence-grounded AI agent for Java code repair with LLM-guided patches and human-in-the-loop review.

Jetson Nano edge AI vision Agent Harness: real-time video analytics, MCP tools, event evidence, DeepSeek online/offline, secure recovery

A terminal where one Claude Code session supervises the AI agents in your other tabs: which is stuck, which is done, which is still running.

Run one AI agent as the orchestrator of your whole workspace, inside the Orca ADE, on the CLI subscription you already pay for. No API key,

Redpen makes coding agents prove they are actually done.

DSH 插件：基于知乎开放平台官方 API 创建的站内搜索、全网索引搜索与直答三个工具。搜索不幻觉，引用有出处。（原生嵌入“设置-插件-插件配置”）

A harness for AI coding agents building Mendix apps with mxcli: a staged pipeline, gates and tests that prove what was built, readable progr

A local-first autonomous agent harness with a web UI, live charts and buttons in its answers, sparks that keep working while you sleep, voic

A minimal yet ready-to-use AI agent harness, built on best practices for frontier models.

CrewCode is the control center for multi-agent software development.

ReqForge — From requirements to shippable products. Open-source Agent Harness for Claude Code, Cursor & OpenCode. Spec→Plan→Build, hooks, re

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

Skill letting Agents scan a repo, ask what it cannot infer, then generate a complete open source file collection i.e. README, LICENSE, contr

Five layers of an agent harness, each with the failure it prevents. Runnable with no API key.

Aielia: an everyday AI assistant built with Build a Harness, the open-source control layer, 11-layer agent harness and visual canvas (LangGr

Minimal surface, complete architecture: a small, local-first coding-agent harness that re-derives the invariants of DeepSeek Harness with fe

Local-first, IM-native AI coworker runtime with async role agents, trace replay, evidence, and agentic evaluation.

Shellby MCP turns ChatGPT Web into a local coding agent with full computer access, persistent tools, and multi-agent capabilities.

Free open-source toolkit to understand, audit and rescue vibe-coded or legacy codebases: source-linked maps, team handoff, human-approved fi

长任务，不刷屏：关键进度清晰可见，完成后自动折叠，详情随时展开。 Long agent tasks, without transcript clutter: focused progress, auto-folded history, details on demand.

The harness that builds harnesses: tell it about your work and it builds a custom AI agent with its own tools, views, skills and UI. Runs in

A governance harness for AI-assisted software delivery. You govern. Agents deliver.

The last agentic harness you'll ever need. Bring any model; Pennant does the rest on your Mac and iPhone, and asks before anything is sent,

Spec Driven — orchestrator-first Agent Skills for spec-driven development. The orchestrator skill turns a PRD or idea into approved SPECs, t

🐱 MiNerva·咪涅瓦 — 替你干活的赛博猫｜An autonomous AI agent that actually does the work.

The best AI harness you can run yourself. One file: web UI, tools, memory and orchestration built in. Run a team of agents across providers

Let an AI agent use your PS Vita.

Project-local agent harness skill for traceable AI workflows

Independent evidence-gated second brain for understanding and porting DeepSeek Harness architecture.

Stop re-explaining your work to your coding agent. Plain markdown and YAML in git, read at session start by Claude Code, Codex and Copilot C