Havuz

🎵 将音乐搬进AI终端 · 打造Coding专属智能DJ · 听歌新范式 · 交互式音乐 ｜A retro pixel DJ for Claude Code / Codex CLI / Terminal with Apple Music / QQ Music / Local Mu

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

Qwen-Planner-Agent: A Closed-Loop AI-for-AI Framework for Real-World Mobile Planner Agents

LLMs have ended reverse engineering as a high-barrier skill. Case study: reconstructing 6/7 custom HTTP signing parameters of Douyin (TikTok

AI protocol scanner — discover exposed MCP servers, A2A Agent Cards, and open LLM APIs in one command. 一条命令盘点 MCP、A2A Agent Card 和 LLM 开放接口暴

Free open-source Screenpipe GUI + macOS automation agent. Search your screen history, view analytics, automate workflows — all local, no clo

Local LLM cost-tracking proxy for OpenAI, Anthropic, Gemini, and pinned OpenRouter calls with token usage, failure, and billing-integrity re

The 30 MB open-source edge AI agent runtime. Run AI agents offline on Linux (Raspberry Pi, Jetson). GPIO, UART, MQTT as first-class nodes. I

A workbench for language model research

WorkWit: a self-hosted, open-source (MIT) enterprise AI Agent platform for office automation — built-in contract review & resume screening,

A personal AI agent that can work safely on your machine, remember useful context, and keep its data under your control.

600 KB WASM runtime for Cactus Compute's Needle AI tool-calling models, Needle 3, 2 and 1 from one build. Browser, Cloudflare Workers, Node.

Make Opus 4.8 (or any Claude model) work like Claude Fable 5 — a Claude Code skill + guard hooks (plan gate, model ceiling, per-task enforce

🧠 Brain-inspired cognitive architecture plugin for AI agents — persistent memory, evolving personality, neurochemistry-driven mood, learning

🔍 The hardest search benchmark in the wild — vague, multi-turn, proactive. 200 long-horizon tasks with persona-driven progressive disclosure

Selfhost modern LLM stacks. Run the whole fleet from your terminal

Zero-leak online detection of LLM decoding corruption and Free Web Search for your AI agents! Catch repetition loops, language drift and gar

SpeakerMem-R1: Speaker-Centered Dual-Track Memory for Multi-Party Dialogue

Rust CLI for AI subtitle workflows: transcribe, segment, translate, evaluate, and burn or mux subtitles.

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

Unified batch API for AI providers. Save up to 50% on LLM costs.

Keep one source of truth for your AI coding-agent rules. Convert and sync between AGENTS.md, CLAUDE.md, .cursorrules, Copilot, Windsurf, Cli

Local-first AI chat client combining SillyTavern-style character cards, LM Studio-style GGUF model management, Ollama/OpenAI-compatible APIs

Policy guardrails for coding agents (Claude Code, Codex, Cursor) — every tool call is checked locally, before it runs.

Production-grade Agent Skills for AI coding agents—composable workflows for planning, TDD, debugging, review, UI/UX, releases, incidents, an

Open-source AI-assisted HR onboarding for Feishu/Lark: configurable workflows, document OCR and review, Bitable sync, reminders, and a zero-

A quality-gated League of Legends post-game coaching agent built on deterministic match data, RAG, and LLM evaluation.

Multi-Agent self-correcting reasoning engine

AI-agent skill producing reusable Markdown from PDFs. It turns flowcharts, diagrams, and charts into text beside each caption instead of emp

A configurable Bash/PowerShell loop that runs an AI coding CLI with a fresh session each iteration

面向 PRD、业务规则、SOP、流程文档和产品截图的证据型 RAG 知识库。

Self-hosted AI workspace where chat becomes visual workflows, multi-agent operations, and reviewable automations. Local memory; local or clo

Deterministic-first execution engine for agent workflows in Go: the LLM extracts at the edge, a deterministic state machine decides. Zero de

High-performance Knowledge Graph engine for AI, LLMs, and GraphRAG — built for the next generation of intelligent applications.

A trustworthy context layer for AI that remembers, plans and acts — free text into typed commitments, decisions and memories, each with its

Local-first AI companion daemon — an agent harness with its own long-term memory. Remembers you, grows with you, extends and repairs itself.

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

Real-time YOLOv8n UAV detection on the RK3588S NPU | saturates the sensor at 46 FPS | ~140 MB RAM | fully hardware-accelerated (ISP+RGA+NPU)

Run a 110B on a 2016 PC with 16 GB RAM. Know your tok/s before you download. Placement beats budget: predicts speed + memory fit for any GGU

Durable single-Agent Harness for TypeScript: recoverable Threads, context continuity, explicit side effects, and a native TUI.

NEXBENCH measures what an autonomous agent can actually do on-chain — execute transactions, route swaps, bridge funds, manage DeFi positions

可恢复气候数据智能体：自然语言 → 获取 / 检查 / 绘图 / 报告

AgentVitals Checkup (/checkup) — an AI agent skill that gives your agent a professional health checkup: dual-axis Stability + Welfare scorin

Self-correcting learning engine for Claude Code — persistent identity, behavioral pattern tracking, and cross-session memory

Composable Agent Skills (Claude + OpenAI Codex) for taking an idea from fuzzy → validated → sequenced build → shipped — a manual tier (ideat

AI 驱动的电商全流程自动化系统。选品、上架、客服、运营分析、货源筛选，基于 DeepSeek V4 + Ollama 混合模型路由，自驱型 ReAct Agent 框架

交接 Skill（Jiaojie）：跨窗口、跨模型、跨设备、跨语言的 AI 上下文交接工具。换窗口，不失忆；换模型，不重来。Open-source AI context handoff.

Building a small LLM in PyTorch from scratch - a step-by-step journey inspired by Stanford CS336.

AI桌面人形机器人 — ESP32-S3全栈运行，不会开口说话，22种情绪+关系成长+6路舵机AI控制，全栈开源(CC BY-NC-SA 4.0)

Convert CodeBuddy/WorkBuddy (Tencent coding assistant) subscription into an OpenAI-compatible API. Use CodeBuddy GLM-5.2/Kimi/DeepSeek model