Havuz

Full-stack LiveKit voice agent starter: a Python voice worker, FastAPI token server, and React frontend. Run, deploy, and swap each piece on

AI code review pipeline — review, auto-fix, test generation & HTML report in one command. Zero dependencies, 6 AI providers (OpenAI/DeepSeek

小白也能上手的 Claude Code / Codex 上游配置切换桌面应用 | A cross-platform, site-driven desktop app for switching Claude Code & Codex providers

Open-source LLM control plane: observe every call, recommend savings, then apply only human-approved, reversible routing.

Explore the Y Combinator portfolio: AI idea validator, success predictor, live hiring board, and email digests. Live at exploreyc.com.

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

WorkForge is a Windows MCP gateway that lets ChatGPT inspect files, resume Git work, make SHA-guarded edits, read images, and run supervised

Lightweight cost observability for every API call in your stack. Track LLM tokens, database ops, and external services from your terminal.

Self-hosted LLM gateway — route OpenAI/Anthropic/Gemini traffic by config, not code. Fallback, protocol translation, telemetry.

Open-source AI assistant with voice control, browser automation, desktop overlay, and 109+ tools. Built with Python, Next.js, and Three.js.

Self-hosted AI gateway with a built-in dashboard. OpenAI-compatible API, multi-tenant, sandboxed code execution, MCP integrations, file stor

Privacy-first bilingual webpage translation browser extension.

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

Your personal AI team that gets things done. Shared memory. Any model. Local or cloud. Run. Rest. Dream. 🐨

Browser-native multi-agent playground: drop LLM personas on a 3D map, watch them live, and talk to them. OpenAI, Gemini, Claude, Ollama. No

RoleMule — One mule for every role. Self-hosted AI job companion. Paste a posting (or Chrome extension): five agents analyze the role, score

Generate LinkedIn posts for technology specialists from a profile, recent news, and a supporting image.

Real-time meeting & audio transcription for Windows (system audio + mic) — live captions via Deepgram, AI summaries via OpenAI. Tauri 2 + Re

Independent local Stream Deck Plus companion for the Codex desktop app.

The complete toolkit for building AI agents in JavaScript. Lightweight core, React & Terminal UIs, autonomous runtime, tools, skills, memory

Document extraction and validation for logistics companies.

Multiplayer infrastructure for AI agents

Self-hostable agentic OS. Build, run & audit multi-agent AI teams from signed plugins. Bring your own LLM key, own all your data, EU/GDPR-re

Agent Reliability Analyzer extension for VS Code and Cursor: find agent reliability issues

Open-source realtime voice AI with adaptive VAD, latency telemetry, interruptible TTS, an inspectable TypeScript WebSocket gateway, and expe

6 specialized AI agents collaborating via A2A protocol to power e-commerce — product discovery, orders, pricing, reviews, inventory & suppor

Agent Reliability Analyzer for Azure Pipelines: find agent reliability issues

Agent Reliability Analyzer docs: install, configure and fix agent reliability issues

Token-efficiency linter for LLM prompts and payloads

Open-source AI workforce platform. Agents with tasks, tools, browsers, and email.

大模型故障 token（glitch token）资料库：收录各 LLM 分词器中已公开记录的异常 token，附异常表现、来源与复现链接。A curated catalog of LLM glitch tokens.

AI-powered SaaS translation platform for web novels — batch translate with RAG memory, multi-agent collaboration, Stripe billing, Chrome ext

AI API排行榜 - 实时139+中转站,自动排行,最高性价比中转站 Claude/GPT/Gemini/DeepSeek API中转站 | AI API Transit Station Ranking

Local-first, extensible AI agent workspace — FastAPI + Next.js + LangGraph, with skills, MCP tools, artifacts, long-term memory, sub-agents,

Self-hosted alphaxiv-style paper-reading app (FastAPI CORS proxy + Vite/React/TS SPA)

Open-source AI prompt engineering workspace — production-ready Next.js SaaS with conversational refinement, multi-engine targeting (ChatGPT,

AI-powered Adaptive Card MCP server — 9 tools for generating, validating, optimizing cards for Teams, Outlook, Copilot, ChatGPT. npm: adapti

Local-first AI image creation workbench | 本地优先的 AI 图片创作工作台

A minimal browser-agent harness - six tools, any model. pi for the browser.

Agent Reliability Analyzer CLI for macOS and Linux: find and fix agent reliability issues

Agent Reliability Analyzer CLI for Windows: find and fix agent reliability issues

Open-source multi-tenant AI agent workspace · 18 personas · 146 active capabilities · 889 platform indexes · 91 curated AI models + 1000+ Op

AI 生图 Web 应用

Self-hosted document library and PWA reader for PDF, Markdown, and text files, with NAS folder watching, full-text search, sharing, annotati

AI-powered log diagnostics engine that analyzes server logs, stack traces, and infrastructure failures to identify root causes and recommend

TypeScript AI agent framework where personality is architecture. Specialists, not chatbots.

A medical FAQ chatbot powered by Retrieval-Augmented Generation (RAG) using FastAPI, LangChain, Qdrant, and React.

AI-powered e-commerce chatbot built with Next.js and MongoDB.

AI workspace for collaborative Overleaf/LaTeX writing

Hearthstone gives babysitters and family instant answers to household questions, grounded in your Google Docs with cited sources; Bun backen