Havuz

An open-source, coding agent harness designed specifically for local LLMs. Designed as everything a user needs to jumpstart their own harnes

An AI agent plays Baldur's Gate 3 on Linux through a Lua mod and an MCP server, seeing only what a player sees. Includes a model benchmark a

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

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

elastic inference for your agentic workloads, on your terms

Claude Code, Codex, and multi-agent configuration system: principles, hooks, skills, and workflow patterns for AI-assisted development

VS Code extension kanban board for agentic AI workflows

An open-source AI agent for the browser. Bring any model. It plans in the side panel, acts on real pages through tools, and verifies every c

Unofficial, open-source Windows desktop harness for Kimi Code CLI.

A custom coding harness for TypeSafe AI's Jev: an LLM proposes, Jev answers narrow questions, code decides, every step leaves a receipt.

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

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

Let an AI agent use your PS Vita.

Coding-agent tools on TypeSafe's Jev, measured in public. review-router: caught 13 of 13 CVE fixes a filename rule sent to a quick review. j

Harness-oriented agent system framework for production-grade LLM agent applications

Build an agent harness from scratch, one branch per step. Code for Tejas Kumar's AI Engineer Europe 2026 talk "Harnesses in AI: A Deep Dive"

A provider-agnostic scaffolding kit for running structured multi-agent workflows in your codebase.

Tuvis(兔维斯) — desktop mission control for AI coding agents: live session monitoring, remote injection, Skill/MCP management & usage ledger. O

Claude Code 源码深度研究，包括 Foundations/Execution/Infrastructure 三大章节和 23 个子系统的架构分析拆解。

Benchmark for comparing agent harnesses on everyday online tasks — fixes the base model, varies the harness. Sister project of ClawBench, sa

Durable execution framework for AI agents in Go. Keeps agent state, tool calls, and execution loops resilient across process crashes.

A terminal-native AI agent runtime built in Rust. Interactive chat, parallel agent orchestration, and autonomous supervision.

A lightweight, general-purpose harness for tool-using LLM agents, fair benchmark evaluation, harness baselines, and personal assistant workf

Skill repository to enforce Engineering disclipline in coding assistants

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

Provider-neutral bounded agent runtime for Android/JVM: controlled context (trust/priority/budgets), profile-scoped tools, OpenAI-compatible

AI-assisted XAUUSD daily research workflow with Research Skill, Agent Harness, LangGraph, Tool Calling, and free public data sources.

Declarative, local-first runtime for bounded AI agents — define an agent in one manifest, run it headless, and audit every effect.

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

Build the memory your agent actually needs — automatically.

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

The agent loop for Python. Your harness, any model.

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

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）

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,

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

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

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

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

Inference-native Tokenmaxxing Agent Harness for Loop Engineering

Portable CC-inspired skills for memory, verification, multi-agent coordination, context compression, and proactive coding-agent workflows.

Agent Harness developed specifically for local small-parameter models.

:dog: Beagle is designed to be the unified platform for the broader Recursive Self-Improvement (RSI) ecosystem. Think of it as Hugging Face

Local-first AI companion daemon — an agent harness with its own long-term memory. Remembers you, grows with you, extends and repairs itself.

Durable single-Agent Harness for TypeScript: recoverable Threads, context continuity, explicit side effects, and a native TUI.