Havuz

以台灣用語和中文標點重寫 blader/humanizer，含中國用語偵測。支援 Claude Code、Codex、Claude.ai

AgendaScope 观澜 · 全球议程设置监控平台：172 国 408 主流媒体实时采集，议题聚类/议程溯源/50精品监控对象社交图谱（每边带新闻证据）/数据开放API；L0-L3 结构化数据库 + 处理状态机 + 分布式任务队列，云端 2C2G 仅做存储与展示，本地算力机做

An institutional-intelligence operating system: a council of 14 agents that remembers every deliberation, grades its own predictions against

Compose neural architectures as typed, executable graph cards with two-way PyTorch sync, step-by-step local execution, and a constrained AI

An MCP server that gives LLMs a real interactive PTY with observability and seamless human takeover.

Building Agent Systems with the EXAONE model.

A live, local dashboard to browse, search, resume & manage every Claude Code session on your machine — full conversation transcripts, an art

Turn long AI conversations into reusable domain knowledge across sessions

Opt-in dual-agent workflow: Claude Code plans and reviews, Codex implements, deterministic gates verify, and you decide what merges.

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

ZKE（Z Kubernetes Engine）：AI 原生的 Kubernetes 云操作环境，桌面式多集群控制台加受控 AIOps Agent，基于 Server + Agent 与 QUIC/mTLS，适用于私有云、混合云及边缘环境

Plug-and-play, dependency-free web command center for DGX Spark fleets (and any GPU boxes): live per-node GPU/CPU/mem/temps/power, optional

Unofficial MCP server for T-Bank (Т-Банк, ex-Tinkoff) mobile banking: accounts, cards, transfers, bill pay, grocery ordering, tickets & trav

AI thinking indicators and a voice-agent orb for React Native and Expo. Six dotted loading animations plus an audio-reactive voice orb, on t

670 MB/s Swift tokenizer inspired by Marcel Roed’s gigatoken. Zero-copy, NEON/CRC32, WebAssembly, and Embedded Swift.

Official plugins (Ghosts) for Cindy — source, review standards, and auto-publish to the plugin marketplace · Cindy 官方插件源码仓：欢迎提交你的插件，合入即自动上架插

A free, private, local AI for any app. One command, OpenAI-compatible, no API key.

Self-hosted workspace that runs several AI coding CLIs (OpenCode, Codex, Claude Code, Gemini) side by side in persistent rooms.

Per-key smart routing for New API: automatic failover, shared health, self-healing recovery, actual-route billing, and explainable decisions

🎯 AI-Powered Job Search Agent — searches multiple job boards and rates them against your profile using a local LLM

Per-turn model routing for the Pi coding agent: a small judge picks the cheap or the strong tier for each message, with multi-model failover

Governed AI analytics from natural language to auditable SQL, powered by a mandatory semantic layer, policy enforcement, and a visual Studio

Cindy, Claude Code ve Codex gibi agent harness’lerini tek bir masaüstü ve mobil istemcide birleştiren açık kaynaklı bir AI agent uygulamasıdır.

Neden yükseliyor · 67 günlük repo için 2.814 yıldız ve son 28 günde 1.767 commit ile 12 farklı yazar, güçlü ilgi ve yüksek geliştirme temposuna işaret ediyor. Bu ölçümler benimsemeyi veya ürün kalitesini tek başına kanıtlamaz; README’de öne çıkarılan çoklu harness ve model kullanımı da AI agent’lara artan ilgiyle örtüşüyor.

Ten cooperating AI agents that turn long podcasts into short-form videos, automatically. Free and open source, runs on free AI providers.

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

Solana pump.fun trading bot — Telegram-driven screening, strategy gates, LLM entry selection, Jupiter execution. Fork of yunus-0x/charon.

Self-hosted, private family AI health steward. Multimodal AI structures health data into a person-centric profile with dashboard & AI consul

让任何 AI 真正"看"视频：纯本地的视频阅读 skill——faster-whisper GPU 转写 + ffmpeg 场景感知抽帧，双通道带时间戳（t=MM:SS），数据不出机。1 小时视频 3~5 分钟读完。Give any AI agent eyes for video

Claude skill: turn your current conversation into a complete handoff document so any LLM can pick up exactly where you left off

A minimal coding-agent harness built to measure what context management actually costs: constraint survival after compaction (8%→83%), def

Open-source native Apple client for the AI you choose - iPhone, iPad, Mac, Apple Watch, and CarPlay. Your keys; no intermediary.

AIと一緒に漫画ネームを作るオープンソーススタジオ。Nyamuru Data Model（NDM）/ OMNY形式のネーム編集PWA・LLM向け生成プロンプト・画像生成ワークフローを収録

Self-hosted OpenAI-compatible mock server — test your LLM integrations without exposing your API key. By Axium.

Run always-on messaging agents on Agent Substrate. A multi-tenant gateway holds the channel connections while each conversation runs as a su

AI Agent / LLM application engineer Chinese interview question bank: 2,038 questions with reference answers

Offline-first project context and durable team management for coding agents. A local SQLite CLI for tasks, sessions, checkpoints, worktrees,

Privacy-first mobile sensor events for LLM-powered PWAs.

Diff your AI agent's behavior between two runs. See exactly which tool calls, args, costs and outputs changed when you swap models or edit p

Lightweight, provider-agnostic long-term memory for conversational agents

BOSS, farklı AI agent’ları tarayıcı, terminal, editör ve MCP araçlarıyla ortak bir masaüstü ortamında çalıştırmayı sağlayan açık kaynaklı bir uygulamadır.

Neden yükseliyor · Agent’ları gerçek tarayıcı, terminal ve araçlarla aynı çalışma alanında buluşturma vaadi güncel ve somut bir ihtiyaca yanıt veriyor; 69 günlük repo yaşı içinde 808 yıldız, son 28 günde 874 commit ve 8 farklı yazar da belirgin geliştirme hareketliliğine işaret ediyor. Ancak yıldızların hangi dönemde kazanıldığı bilinmediğinden yükseliş hızını ayrıca doğrulayamıyorum.

开源私域 AI 营销 SCRM 系统，Martech 获客引流利器， 智能AI客服 、销售 ReAct 自主 AI 智能体 全渠道聚合（抖音/小红书/快手/微信/WhatsApp/TikTok/Telegram）统一收件箱 独家 GEO 模块（生成式大模型引擎优化/AI 搜索占位

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

专为 AI 玩家设计的单文件卡牌肉鸽 🌙

General, reusable Flutter engineering skills for AI coding agents — architecture, Riverpod 3.x, testing, persistence, i18n/RTL, accessibilit

hummingbird is a lightweight, zero dependency runtime for massive open source Mixture of Experts (MoE) language models. It unifies SSD, RAM,

AI-native video editor driven as a local MCP server. Linux + Windows: ingest, transcribe, edit graph, melt/ffmpeg render, QC.

CareerDesk: Your Personal Career Assistant

Verify which LLM an OpenAI-compatible API really serves — single-token behavioral fingerprinting (Jensen-Shannon) from the paper "One Token

Run AI coding agents in parallel on one git repo and safely auto-merge their work — only changes that build and pass tests land. On top of p

AI brain for your Paperless-ngx archive — chat with your documents via local (Ollama) or cloud LLMs, with agentic tool use, semantic search