Havuz

Parallel AI coding, without repo chaos. Desktop workbench for Claude Code and Codex with per-session git worktrees, terminal, editor, SCM, a

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.

Framework for building, optimizing, and deploying AI agents as Effect services. Define an agent as a declarative blueprint. Run it against b

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

Local MCP server that helps coding agents stop re-reading the same code every turn. Repository intelligence, cache-write optimization, and l

TYSA (Teach Yourself Anything): an learning harness that finds where your understanding ends and teaches from there. Electron app built on M

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

chatablex AI Agent.

Build an ETF research agent, one working module at a time. Runnable code, bilingual deep dives, and a traceable 0→1 journey.｜逐模块构建 ETF 投研 Ag

Turn one-off AI collaboration prompts into long-running repository governance. · “把一次性的 AI 协作提示，疏导成项目里长期可运行的治理体系。”——Dayu Harness Skill（大禹治库.

《Harness Engineering实战：构建可靠的生产级AI Agent》配套代码仓库

Open-source, self-hosted AI-assisted operations for Kubernetes and Linux. Start here for source, architecture, deployment, and contributions

A desktop SQL learning workspace that brings local SQLite, an AI tutor, visual schemas and hands-on practice together through a coordinated

The agent that learns how you decide - and proves it by never deciding for you. A local-first, loop-native runtime for a team of AI agents o

The open interoperability layer for AI agents. Connect your favorite agents and harnesses. Work together.

Attention is your scarcest resource. Chief is the local-first layer that guards it — turning every agent, alert, and feed into one honest ca

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

Hermes Production Patterns — 面向 Hermes Agent 的生产级工程模式集⋯装了 Hermes 却不会写靠谱的技能？Cron 跑偏没人发现？输出质量靠肉眼审查？状态全靠脑子记？6 个 Starter Kits + 20 个工程公约 + hpp C

Less hype. Better harnesses. Measurable outcomes. AI Agent 思考与实践：上下文、工具、评估与超越拟人的设计。

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

For an organization to trust AI with its code, three things must hold — trust, traceability, and stability at scale. cladding wraps your AI

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

Composable harness runtime for production agents — primitives, traces, evolution, outerloop governance.

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

A small, file-first verification harness that turns an AI agent's "I'm done" claim into an auditable admission decision. 100% offline & zero

Deterministic spec-to-code context for AI coding agents — one graph linking requirements, docs, code, and tests.

Project-local agent harness skill for traceable AI workflows

Open-source benchmark for evaluating LLMs on domain-specific geological reasoning, AI for geology, and source-grounded geological knowledge.

Agentic browser automation built from small, reusable pieces.

Open-Source Agentic Harness for Reliable Task Completion, even on small local models. 💻🧠🤖

A warn-only runtime layer for Claude Code agents. Keeps feature state, scope and handoffs on disk so they survive compaction, and requires a