AI 开源项目

Natively — Free open-source AI meeting assistant, interview copilot, and note taker. The best alternative to Cluely, Otter, Granola, Final Round AI, Fireflies, and Interview Coder. Real-time transcription, AI meeting notes, lecture recording, local RAG, BYOK, and stealth mode. Runs locally. No subscriptions. No data breaches.

Open source implementation and extension of Google Research’s PaperBanana for automated academic figures, diagrams, and research visuals, expanded to new domains like slide generation.

Local-first AI job intelligence workbench for scraping roles, ranking fit, and generating tailored application materials.

Open-source, self-hosted file-processing tool. Convert, compress, OCR, transcribe & run local AI across image, video, audio, PDF & documents, via UI, REST API & pipelines. Your files never leave your network.

AI-powered cross-platform e-book reader with semantic search, RAG chat, local vector store, notes, TTS, and WebDAV sync.

⚡ 需求分析效率提升 200%！全球首个为 AI 编程时代设计的团队协作 MCP 服务器，自动分析需求自动编写前后端代码，下载切图

A realtime voice runtime that keeps Agents talking, working, and present. Real-time Voice Runtime for AI Agents

Turn Claude Code into your offensive security research assistant. Specialized AI subagents for authorized penetration testing plan engagements, analyze recon, research exploits, build detections, audit STIGs, and write reports.

🧭 Architecture-first system design: 26 bilingual tutorials, 25 architecture templates, and 6 end-to-end cases covering distributed systems, AI-native systems, RAG, coding Agents, and production trade-offs.

An agentic toolkit to control, debug, and profile iOS and Android apps. Made by Software Mansion.

Consider it done. The open-source AI agent that works out of the box · 想到，就能做到。开源、开箱即用的 AI Agent。

🚀 One sentence → your one-person company of AI experts → complete deliverable in minutes. 267 CN + 184 EN + 5 more languages (ko/ru/pt-BR/id/ar) · zero-code YAML · auto-verified acceptance · Web Studio / Desktop / Docker · 11 LLM providers (7 key-free). 一句话组建你的「一人公司」AI 专家团队，几分钟交付完整方案；验收自动核验，网页 / 桌面 / Docker 全渠道。

Proma brings a seamless general-purpose Agent experience to your workflow. Built for 100× professionals and the proactive Agent era

A Systematic Analysis and Discussion of Claude Code for Designing Today's and Future AI Agent Systems

Helios: Real Real-Time Long Video Generation Model

Let Claude (or any LLM) actually watch a video — scene-aware, deduplicated frames + transcript, from a URL or local file. Runs locally, MIT.

A curated collection of the best GPT Image 2 prompts and examples. The prompts come from top creators on X.

On-device, real-time multimodal AI with features similar to GPT-Live

Community recipes for serving LLMs on RTX 3090/4090/5090 CUDA gpus. Multi-engine (vLLM, llama.cpp, ik_llama) and model-agnostic. Currently shipping Qwen3.6-27B Qwen3.6 35B Gemma 4 26B Gemma 4 31B configs for 1× and 2× cards.

AI-native video production toolkit for Claude Code

Fine-tune LLMs from one YAML. Layer streaming trains an 8B model on a 4 GB laptop GPU.

TokenSpeed is a speed-of-light LLM inference engine.

An open-source desktop app for generating videos with LTX models

High-performance multi-data-source database client — ~30MB, AI & MCP ready, zero Electron bloat. | 高性能多数据源数据库客户端：约 30MB，AI 与 MCP 就绪，告别 Electron 膨胀。