Havuz

👾 下一代透明智能体架构 | Next-Gen Transparent Agent Architecture 🔍 全行为审计 | 🛡️ 两段式安全调用 | 🧠 双水位记忆 | ⏰ 心跳任务 📊 P0 级事故率降低 80% | 兼容 OpenClaw + Claude Code 技

A desktop-first literature manager for PDF reading, translation, paper overviews, and AI agent workflows.

A pure open-source coding agent developed by AI

54 terminal-style agent-like spinners for React Native & Expo. Lightweight, zero native dependencies — just Text. No heavy UI threads

Agnes AI 全模态 API 非官方帮助中心：完整 API 文档 + 通用支持 Skill。已同步 Agnes 3.0 Flash（512K 上下文 / 65,536 输出 / 三端点 / Thinking）与 Image 2.5 Flash，覆盖文本、图像、视频模型接入，适

HarnessEval-W: Agentifying the Evaluation of Visual Worlds

The graph based agentic IDE

Persistent multi-model workflow teams for DeepSeek Harness — dynamic lead planning, bounded DAGs, per-agent model/tools, Run Center and Toke

The first self-evolving AI agent. Rewrites its own source code in real-time. 6 AST mutation strategies. Absorbs GitHub repos autonomously. 7

Import conversation history from 25+ AI coding agents into DeepSeek Harness as resumable sessions — tool calls, reasoning and results kept i

🦞 ResearchClawBench: Evaluating AI Agents for Automated Research from Re-Discovery to New-Discovery

An edge-native Multimodal Android Agent that integrates multimodal perception, memory and action

Automated friction logging for agents.

Install, manage, and share skills across every major coding agent — Claude Code, Cursor, Copilot, and more.

Jev-Mem: System-One Controlled Agentic Memory

Everything that *went* wrong with Claude.

Agent that actually understands social platforms. Fast. Precise. Deep.

The open-source trading harness for Claude Code / Codex agents.

Open-source desktop AI agent that gets work done — plans & self-corrects, agentic visual workflows, generative UI, and 100+ offline tools in

Physical AI runtime for embodied agents — governed action, verified experience, physical memory, and skill evolution.

GameWorld: Towards Standardized and Verifiable Evaluation of Multimodal Game Agents

One desktop for all your AI coding Agent — Claude Code, Codex CLI & Gemini CLI. Auto-detect, one-click install, unified chat, file explorer,

Agent Harness developed specifically for local small-parameter models.

Turn tracker tickets into autonomous agent sessions

RAG ReAct Agent - A Retrieval-Augmented Generation system with ReAct (Reasoning+Acting) agent loop for intelligent question answering with m

AgentAegis is a lightweight plugin providing full-lifecycle runtime protection for OpenClaw.

A lightweight AI agent and skill workflow framework built with Godot.

Agent-first AI SEO (AEO/GEO) operating platform

💡 Turn experience into repeatable execution.

An LLM programming assistant engine built with Go, supporting WebSocket, multi-turn dialogues, tool calling, permission control, and skill e

👁️ Review AI generated code and plan changes

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

All Jina AI APIs as Unix CLI commands. Search, read, embed, rerank - with pipes.

Compose OpenClaw agents into executable DAG workflows. CLI tool, REST + WebSocket API, and React console included.

The best react-native Agent Skills. Forget 10x, this is 100x.

大师.skill — 输入行业，自动调研 6 轨[行业大佬 / 工具地图 / 工作流 / 知识正典 / 信息源 / 术语标准] → 提炼为可运行的行业 Master OS skill；装到任意 Claude Code / OpenClaw / Codex / Hermes age

Open-source terminal coding agent and SDK. Bring your own key for 25+ providers or a local model, with sandboxed subagents. Part of Directio

Open-source AI Personal Assistant for planning, writing and personal knowledge. Use LISA Cloud or connect your own Mac.

VEFX-Bench: A Holistic Benchmark for Generic Video Editing and Visual Effects

Benzi is code intelligence infrastructure for AI models. It compiles your codebase into a resolved, queryable map of calls, data flow, contr

An Omni-Modal, Omni-Discipline AI Scientist

This is a fork of the https://dockbox.dev project I made

Loopcut: an AI agent that works inside Blender. A fork of Blender (GPL).

用 AI 把本地代码变成文档，一条命令搞定

⚡ Code mode for agents

One Page Agent.The browser-native workbench that lives in One Page.

A Local-First and Config-First Agent Harness Dev Kit

Wonda CLI — AI-powered content creation from your terminal

A local-first multi-agent app development platform, built on PenguinHarness

Tinybot is a lightweight personal AI Agent that is constantly evolving