Havuz

Subpool, ekiplerin yetkili AI abonelik ve API hesaplarını tek bir self-hosted gateway üzerinden havuzlayıp yönetmesini sağlar.

Neden yükseliyor · 25 günlük yaşına rağmen 83 yıldız ve son 28 günde 61 commit dikkat çekiyor. Commit temposu yüksek; ancak yalnızca 2 farklı yazar görünmesi katkı tabanının şu an dar olduğuna işaret ediyor.

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

Agent-first lightweight browser automation — direct CDP, no Playwright, more accurate and more reliable.

SkillAdam: Better Skills for Your AI Agent🚀 Claude Code/Codex/Cursor 插件，一键进化你的skill

An autonomous, always-on agent on your Android phone. It has its own browser, keeps a wiki memory of you, and hands the heavy jobs to your o

🧬 Symbio（共生）- AI Infra 级多 Agent 协同框架 | 33 Killer Features: 动态 DAG, 本体化记忆, 防过早完成, 数据飞轮, 神经符号安全, OpenTelemetry 可观测, HITL 人类介入, MCP 原生支持, 语义缓存,

👾 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

2026 年编程导航 AI 编程实战新项目，基于 Taro + React + FastAPI + DeepSeek 的 AI 闯关学习小程序，支持一句话 / 文本主题 AI 出题、闯关答题与即时讲解、联网搜索增强、RAG 私有知识库出题、AI 生图配图、微信登录与通关复盘报告。

一款集成codex claudecode opencode workbuddy 等智能体的agent工具，可免除繁琐的配置，帮助小白更方便的使用gpt,claude,grok，国模等大模型，支持中转站对接

Native Android AI agent: use your own API keys (OpenAI/Anthropic/Gemini), opencode-style modes, device tools, Shizuku shell, screen analysis

Local-first YOLO workbench for annotation, training, evaluation, and AI assistance.

Dynamic-memory-first collaborative AI framework for long-form story generation, chapter planning, and coherent narrative writing

AgentScope Java, Java ile uzun süre çalışan ve dağıtık ortamlara taşınabilen agent uygulamaları geliştirmek için bir framework sunuyor.

Neden yükseliyor · 13 günlük yaşına rağmen 108 yıldıza ve son 28 günde 12 commite ulaşmış; Java tarafında üretim odaklı agent altyapısı arayanların ilgisini çekmiş olabilir. Ancak yıldız ve README özellikleri benimseme ya da üretim başarısının kanıtı değil; farklı yazar sayısının 1 olması katkı tabanının şimdilik dar olduğunu gösteriyor.

Persona agents with explicit memory, retrieval, adversarial smoke tests and a practical post-training roadmap.

杀戮尖塔2的MOD，将杀戮尖塔2的游戏状态与操作暴露为本地 HTTP API 包装成 MCP Server，供支持 MCP 的AI客户端直接调用

Graph-Orchestrated Agent Loop — a production-grade framework on LangGraph. Combine workflow graphs and agent loops, transpile Dify DSL to ru

Local-first Agent Runtime connecting LLMs to controlled tools, Chrome, desktop automation, MCP, context governance, and verifiable memory

面向任务执行的 AI 工作台：模型在单个 Agent 循环里自选搜索、网页深读、地图与知识库等工具，回答来源可追溯。

你的随身 AI 剪辑搭档 | Pocket AI co-editor for video montage — AI video editing plugin & MCP server for Claude Code, Codex, Hermes & OpenCode

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

Pluggable controls for reliable AI agents: validated outputs, bounded loops and frozen collective decisions.

Evidence-grounded scientific agent system for research automation, citation verification and paper production.

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

Agent Harness developed specifically for local small-parameter models.

Claude Code / Codex / pi plugin that hands agent steps needing no text output to Jev (TypeSafe's judgment model) — measured p50 ~230 ms and

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

DevLabs™ Free, open source and local-first. A multi-agent harness that works with the AI subscriptions you already pay for. It turns the ter

OryxOS is an open-source Distributed AI Agent OS

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

Everything that *went* wrong with Claude.

Desktop app built on Claude Code harness for proactive engineers.

AI生图工作台 (AI Image Generator)、视频工作台。支持 Agent 与工作台模式、无限画布、素材管理、提示词反推/广场及 PWA，支持外链式配置；可接入 Grok、GPT Image 2 等自定义模型生图。自适应手机端。

A full featured, powerful, and efficient AI Agentic Harness/Desktop Agent app designed from the ground up with local inference on consumer h

Isolated Linux desktop workspaces for AI agents — a hidden, agent-owned desktop and browser over MCP, so an agent can do GUI and web work wi

Harnessclaw is a powerful, Electron-based desktop application designed to manage, chat with, and operate AI agents and skills seamlessly.

基于 Deepseek-Harness 核心底座打造的桌面版 Agent.继承底坐全部能力。并补全 IDE 相关功能。

~66% Faster, ~44% Less Tokens, The only AI coding workflow you need, Supports small models

data agent 从问数到数据开发治理，自然语言问数、SQL 查询、图表看板与多 Agent 专家团分析，支持 MCP 数据源、自带模型和本地 Ollama。

Find the best AI models you can run

AdalFlow Alternative 2026: Auto-Optimize LLM Apps Without Code

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

Epistemological database for agent and human efforts, beliefs, and findings.

让Codex向你呈递公文并接受批示圈阅

An agentic system that auto-optimizes LLM workloads on AMD GPUs.

Tu asistente personal, directamente en tu ordenador. Habla contigo por voz, gestiona WhatsApp, atiende llamadas, consulta la web y recuerda

A minimal local coding agent in Go — a faithful port of Sebastian Raschka's mini-coding-agent, with no LLM framework.

ClipTalk —— 通过对话完成视频剪辑的 AI Agent。说句话，片子就剪好了。ClipTalk — An AI agent that edits videos through conversation. Just say it, it's edited.

Open-source, multi-model agent for coding, research, and everyday workflows. Independently built engine with our own Alysis Sandbox, strict

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