Havuz

A wallet of AI agents that use real tools and ask each other when a question isn't theirs. Runs on your computer; the model is your choice,

Cooking AGI / AGI 大锅烩 · Bilingual (English / 中文) ML & LLM notes with worked examples, step-by-step figures and coding practice. Free to read

蓝毛小女仆 (Blue-Haired Little Maid) · 住在 Windows 桌面上的 Q 版蓝发小女仆桌面宠物：106 个手绘透明动画、本地 Ollama 或在线模型陪聊、可选看屏幕吐槽、离线语音识别（安装器与便携版）。免费开源 MIT。同时是 DeepSeek H

Agent skills, 15 original character cards and a calibrated AI-flavor detector for roleplay card authors. Skills run in Claude Code / Cursor

Open-source AI browser agent for web reverse engineering. Turn websites into browser-free API clients and crawlers with CDP, network tracing

Python toolkit for fingerprinting anonymous LLMs on OpenAI-compatible endpoints using tokenizer, context, error, and vision probes

A realtime assistant for Mac and Windows. Talk to it and it answers aloud, shows your schedule and mail as cards, and hands longer work to a

AI/LLM on Kubernetes 基础设施知识库：涵盖 GPU、大数据、调度、分布式训练、LLM 推理、RAG、Agent 与生产运维。| AI/LLM on Kubernetes Infrastructure Knowledge Base: Covering GPUs,

On-device AI agent for Android, tuned for free OpenRouter/Kilo models with automatic model/key fallback and rate-limit recovery. Tools: web

目标打造全球跨境卖家的开源 AI 全能运营助手：基于 LangGraph、RAG 与多智能体协作，连接 Amazon、独立站、ERP 和广告平台，覆盖市场洞察、智能选品、竞品监控、关键词研究、Listing 优化、广告投放、销量预测、库存补货、利润核算、客服分析、合规风控、内容营

Vendor-neutral Go CLI for the Open Knowledge Format. Create, validate, lint, index, search, and graph OKF bundles. Built to be driven by AI

Give Claude Code or Antigravity an intern: drive Gemini (Antigravity), Codex, Copilot, Cursor and opencode as sub-agents, plus experimental

One-message Claude Code deployment on your Muse agent VM, plus dimensio, a multi-model agent workspace. 在 Muse 上一键部署 Claude Code 和多模型 agent

High-throughput, self-hostable LLM router in Go. BYO provider keys, k8s-native, key pooling + batch + usage observability.

Free, browser-based BYOK AI website builder — v0 / Lovable / Bolt.new alternative. Bring your own key from a variety of providers, generate

Let your AI agent call your phone and talk to you — MCP servers for live, interruptible voice calls + tiered alerts, using free self-hosted

DSH 消息编辑插件：编辑已发送的消息并从该处分叉对话，气泡下方带版本计数与树状视图。Edit a sent message and branch from that point — version counter, tree view, placement presets.

Noisegate: a differential privacy gateway that lets an untrusted LLM agent query sensitive data over MCP (Model Context Protocol), with a fo

MCP server that lets AI agents operate Moodle: courses, assignments, forums, grades and files-as-markdown.

A plan-driven, multi-agent coding loop: separate planner, coder, and reviewer roles, each on the provider and model you choose, work togethe

AI-powered algorithmic trading agent for the Charles Schwab API. Python, options strategies (wheel/theta, covered calls, iron condors, verti

Mercury CLI: multiple AI coding sessions in one terminal. Mix and match provider and locally hosted models, spawn cross-company agents & wor

Dify 1.19-compatible MCP server + CLI — 193 tools for building, testing, publishing, and migrating Dify workflows, with stdio/HTTP MCP, DSL,

Self-hosted AI voice agent for Asterisk. Streaming STT to LLM to TTS over AudioSocket, with barge-in and tool calling.

Winning Qwen and DeepSeek setups for AMD Strix Halo: pinned Ansible recipes and matched benchmarks on a 128 GiB Ryzen AI Max+ 395 / Radeon 8

[ICML 2026] NanoQuant: Efficient Sub-1-Bit Quantization of Large Language Models

See and review any Vivado / Zynq / PYNQ project: drill-down Vivado-style diagrams and clock-domain, constraint and overlay checks for AI cod

SDK-first, independently maintained SemIf fork for fast, self-hosted semantic decisions.

📚 An educational, step-by-step implementation of LLM KV cache reuse — learn prefix caching, chunk keys, storage & eviction, from pure Python

Home Assistant app: an LLM fallback for Assist that learns from what Assist couldn't handle and suggests aliases, automations and scenes

Run a 177B model (Qwen3.8-Flash-Next) on an 8 GB laptop GPU. Measured: 6.6 GiB VRAM, 47.8 GiB RAM, 34-35 tok/s. The n-gram table stays on di

P2P — Prompt to Prompt: a prompt that writes prompts. Claude plugin; file edition for other models in releases.

长篇小说作者的 AI 写作 IDE：对话式 Agent 审稿、修订、起草，逐字 diff 由你确认才落盘；事实台账与伏笔账防吃书。本地优先，自带模型 key。An AI writing IDE for long-form fiction.

Teach your agent to work with evals: WHEN you actually need an eval or benchmark, HOW to build one that holds up, and how to read what it te

A native LLM operating system, make LLM the operating system interpretation layer.

Local-first personal workspace: write notes, track tasks, chat with an AI that knows your files - all plain Markdown, no cloud.

A drift net for your feeds: catch the tools, repos and articles your chats share before they drift away. Sorted, summarised, searchable, loc

Self-hosted LLM gateway in Rust: one OpenAI- and Anthropic-compatible endpoint for Claude, Codex, Qoder, Cline, Grok, Antigravity, CodeBuddy

Lightweight multi-agent trading analysis framework with A-share, HK, and US market support

A lightweight workflow orchestrator for Pi with six specialist agents for exploration, research, architecture, UI/UX, implementation, and v

The agent loop for Python. Your harness, any model.

Shared, persistent memory for AI agents. Self-hosted MCP server with semantic search, vector RAG, and live updates. Works with Claude, Curso

Real-time AI coaching for sales & negotiation calls — live suggestions while you talk, voice translation into the meeting, deep debrief afte

Run a coding model at 300+ tok/s on your Mac. Native Rust + Metal inference engine for LiquidAI LFM2.5-24B-A2B (MLX 4-bit) on Apple Silicon.

Your team uses Odoo — without logging in to Odoo. Free, self-hosted AI assistant on Telegram & WhatsApp: employees apply for leave, approve

An assistant that learns how each person it talks to actually works. Runs on your Mac, reaches people through iMessage.

RikkaHub Plus（酒馆和命理增强版）—— 基于 rikkahub 的深度定制分支：命理排盘（西洋/印度/古典占星、八字、紫微）+ 酒馆角色卡与世界书兼容 + 群聊 + Agent 工具

A coding agent that rewrites its own harness (prompts, tools, compiled core) while it works, so the harness grows with the model. A Root it

Viglet Turing: open source enterprise search with generative AI. Faceted semantic search, RAG chat with citations and AI agents over your ow

Your engineering taste, in every coding agent. Shadowclone learns your rules and delivers them as skills to Claude Code, Codex, Cursor, Pi,