Havuz

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

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

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

OpenAI Codex 源码深度研究 (Rust + TS + Python)：2 总纲 + 25 章 + 3 附录, ~51 万字 + 149 张 Mermaid 架构图

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

Open-source multi-agent orchestration harness for OpenCode — specialized agents, durable workflows, research, planning, implementation, revi

The open-source agent harness, ready out of the box and customizable in depth. Tools, context, durable execution, permissions and recovery f

⚡ Millisecond System-1 judgement for every tool call in DeepSeek Harness — Jev-powered risk classification & evidence-gated auto-approval. F

Benchmark coding agents and agent harnesses on 226 deterministic file-editing tasks with byte-exact verification and a public leaderboard.

DSH 插件：把 WorkBuddy 桌面 App 里的模型接入 DeepSeek Harness，零配置直接用。（原生嵌入"插件-插件配置页"）

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

A local-first coding agent that doesn't take "done" on faith: the engine keeps the run going until the project's own tests pass, and every g

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

开源 · 本地优先的 AI 智能体：编程与实干兼备。 自带模型密钥，内置 MCP、技能、插件、工作流、知识库以及数据库。

AI csapatod, ami fut amíg te alszol.

A living 3D city for your AI agents, self-hosted. Bring OpenClaw and Hermes agents, connect a Grok Bot, or build agents on any AI model: the

Pi adapter for official DeepSeek Harness minimal mode. V4 Pro thinks We need… / I need…, not Let me…

Execution posture harness for Claude Code. Your coding agent stops one step early; Castra is the step.

A pure-Go port of pi (earendil-works/pi) — the pi-ai unified multi-provider LLM API, pi-agent-core agent loop, and pi-coding-agent, native i

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

Runtime-neutral AI execution bridge for Claude Agent SDK, Codex app-server, and Agent Client Protocol (ACP).

Jev-powered decision layer for DeepSeek Harness

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

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

EOC: open-source operating system for OpenAI Codex workflows with agents, skills, hooks, rules, memory, safety gates, and cross-harness adap

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

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

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

Let an AI agent use your PS Vita.

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。

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

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,

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

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

Safe to explore. Free to build. Koder by aixplain is an AI coding harness for desktop and terminal, with permission checks, reviewable chang

Runtime for coding-agent harnesses. Run Claude Code, Codex, OpenCode, Pi, and Grok in one terminal; hop live between them; search or resume

A minimal, evidence-gated harness for Codex and Claude Code: reuse what works, add only what is missing, verify before evolving.

A minimal coding-agent harness built to measure what context management actually costs: constraint survival after compaction (8%→83%), def

Assessment-driven, local-first learning agent built on an observable Agent Runtime and eval harness—grounded ingestion, trace replay, HITL a

Write, validate, and review Agent SKILL.md's directly in Visual Studio Code. SKILL.md Inspector provides live diagnostics for every file na

Verifiable AI coding agent harness / 可验证的 AI 编码代理：evidence hash-chain · hollow-answer gate · manual verification checklist · 6 engines + MCP

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”）

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

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

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

Fable-style spec + evidence gate for Claude Code + Codex. Makes Opus/Codex work under Fable-like discipline: blocks every edit until a deter

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