Havuz

Agent workflow for deadline-bound execution with evidence gates

JoyCode API 代理 — 协议翻译成 Anthropic/OpenAI 兼容格式，让 Claude Code 直接调用 JoyCode支持的模型，比如GLM 5.1等

闲亭 DeskPark — 简洁优雅的网页桌游平台：斗地主、掼蛋、德州扑克、四川麻将；单人人机与多人联机、房间聊天、像素虚拟形象、AI 托管人机，Docker 一键部署

Local evidence debugger and trajectory-test toolkit for TypeScript AI agents: inspect causal runs, catch wrong tool paths in CI, and share s

DeepSeek Harness Web UI plugin for streaming rendering and scroll handling.

Run Claude Code and OpenCode on your Android phone, no computer needed. Or follow and steer agents on your computer: live sessions, tool app

A universal, industry-neutral taxonomy of cognitive core skills (perception, memory, reasoning, planning, action, verification, learning, go

A reference operating model for organizations where any role can be filled by a human or an agent, every process is built for agents first,

An AI workforce on your desktop. Describe the work; a team of AI agents does it in the open and hands it back checked. Any model, any harnes

将 Qoder 的 AI 服务转化为兼容 OpenAI/Claude/Codex 格式的 API，支持每日签到领 Credits、多账号管理、模型上下文展示

MCP server for the complete Zabbix API - 237 tools, multi-server, OAuth 2.1 + bearer auth, PDF reports, systemd ready. Works with ChatGPT, C

OpenAI- and Anthropic-compatible API for Duck.ai, driven by a real Chrome browser via Playwright. Streaming chat, image generation, session

freebuff 反代 Docker 一键部署, 可用 deepseek-v4.1-flash(可识图), GPT 5.6 Luna, 牛来(gml-5.3 flash), gemini-3.8-flash, 支持配置代理, 多账号管理, 已支持新版额度消费模式, 超时自动中断会

Self-hosted workout tracker with an AI coach that knows your training. Bring your own LLM (Claude or any OpenRouter model). Strength + cardi

Track the carbon footprint of your Claude Code sessions, in the terminal and the Claude desktop app

Evidence-aware on-prem LLM inference sizing and TCO calculator

Open-source, bilingual AI video-prompt skill — rewrite ideas into model-ready text-to-video prompts. A portable Agent Skill (Claude Code, Co

Persistent memory plugin for OpenCode. Obsidian-style knowledge base that survives across sessions

Tactical AI Workspace Monitor & EDR

Self-hosted, Docker-first OpenAI-compatible LLM gateway with provider routing, fallbacks, API keys, and usage controls.

MakoCode — 茉子版 Agent | Galgame 风格桌面 AI Agent，零门槛体验 Agent 的乐趣

Streamline AI Workloads on Kubernetes: Universal Python SDK Guide 2026

Open Source Instruction Tuning LLM Training Library 2026

基于 Hybrid RAG 与 LangGraph 的本地代码仓库理解工具，支持中英文提问、语义检索、证据引用和多问题拆分

A Unified Memory Benchmark Suite for Memory-Augmented Agents

A nightly newspaper that writes itself: an agent runs the desks, the figures come from code, and it refuses to publish an edition with marks

Cromford: the open-source software factory. Tickets in, reviewed, merged and production-checked changes out.

JanusX — open-source AI-coding workspace: worktree parallel dev, split terminals for Claude/Codex/OpenCode/Pi, checkpoints with diff-restore

Antidote for fluffy specs, a toolkit for fact-driven development with AI agents

Self-hosted voice gateway in Go that speaks the OpenAI Realtime (GA) WebSocket protocol and runs a cascaded ASR → LLM → TTS pipeline behind

⚡ Terminal HUD, hard budget breakers & prompt-cache leak alerts for AI coding agents (Claude Code, Cursor, Codex)

ИИ-помощник для переписки: ответ появляется серым прямо в поле чата, Tab вставляет черновик, отправляете вы. Mac, Windows, iPhone

Second yourself. One agent that remembers you, with many hands to act for you: a multi-agent harness (Claude Code, with Codex helpers), a se

你只需要打字，剩下交给Kitten：最懂你的安卓AI agent助手！完美复刻豆包手机核心功能，利用安卓副屏拉起对应APP，结合视图识别能力进行自动化操作，实现代回QQ微信、点外卖、购物等功能。

弦外之音 —— 微信聊天里的关系进展助手：读屏（无障碍树 / 截屏视觉）→ Jev 判读 + 攻略度 → 聊天模型出 3 条候选回复，攻略度常驻挂在屏幕上。不改微信、不发消息、不注入点击。

数模Agent（数模 Agent）/ 数学建模 AI 助手：多智能体协作完成题意分析、文献检索、建模、代码执行与论文写作，支持人工审核和断点恢复。Local-first multi-agent workbench for mathematical modeling.

Tiny LLMs, Q4, in the browser. WebGPU lab inspired by yangqi0/petitgpt.

Local-first code intelligence for AI assistants. Turns your codebase into a knowledge graph your AI can query, navigate, and remember. 25 MC

WHIRL (Windows HIP Inference for RDNA LLMs): native Windows C++/HIP LLM inference engine for the AMD Ryzen AI Max+ 395 (Radeon 8060S) and Ra

LLM frontend for roleplay and creative writing

Cheaper and better Greptile alternative runs on your own github actions.

Self-hosted, open-source financial data MCP server for AI agents — SEC filings, XBRL financials, 13F holdings, insider & congressional trade

🧠 Production-grade memory sidecar for AI agents — gbrain + Hindsight + 3-tier recall. Agent-agnostic, battle-tested. | 生产级外挂记忆系统，兼容Hermes/Cl

Provider-pluggable orchestration runtime for multi-model AI inference. ( Sakana Fugu style )

Zero-dependency, single-file HTML design system & agent skill inspired by shadcn/ui. 100% offline, zero npm, 6 layout archetypes & atomic ar

Open, self-hostable agentic service for organizations — durable, replayable agent sessions, human approvals, governed credentials and memory

Runs Hugging Face ONNX models on any Nx backend, with no per-architecture code

为 DeepSeek Harness 设计的破限插件：卸掉宿主的提示词限制和审批拦截，让助手照你说的做，不半路拒绝、不反复请示。补丁逐条可选，随时还原原版。 A jailbreak plugin for DeepSeek Harness: it strips the host's

Open-source AI gateway for LLMs & AI agents, built in Rust. One OpenAI-compatible API for OpenAI, Anthropic, Gemini, Bedrock & more — routin

Interactive canvas for taking an LLM apart tensor by tensor: measured INT8/INT4/FP8 error, distributions, spectra and outlier channels for e