xiaomi-mlab
★ 671Orion
[ICCV 2025] Official code of "ORION: A Holistic End-to-End Autonomous Driving Framework by Vision-Language Instructed Action Generation"
AI channelLLM apps 
★ 670
Open-source LLM apps and frameworks
Most-starred projects
4,297–4,320 of 5,866agentscope-ai
★ 670agentscope-studio
A development-oriented visualization toolkit
evanca
★ 670flutter-ai-rules
Flutter AI Skills and Rules for Claude, Codex, Cursor, and Other AI-Powered IDEs
Starter app to build with OpenAI ChatKit SDK
OpenSQZ
★ 670MiniCPM-V-CookBook
Cook up amazing AI applications effortlessly with MiniCPM / MiniCPM-V / MiniCPM-o
t8
★ 670hypura
Run models too big for your Mac's memory
byronka
★ 669minum
The smallest and simplest Java web app framework
seo-skills
★ 669seo-audit-skill
A comprehensive SEO audit command-line tool with 332 audit rules across 20 categories. Analyze any website for SEO best practices, Core Web Vitals, security headers, structured data, accessibility, and more.
wuyoscar
★ 669jev-skill
An awesome collection of Jev use cases, workflows, and agent skills.
xiaohuailabs
★ 669xiaohu-video-translate
Tell the AI one sentence and it automatically adds Chinese subtitles to foreign-language videos — download, transcribe, translate, polish and burn in, all in one pipeline, running fully locally with zero API cost for transcription.
joelhooks
★ 668pdf-brain
🧠 Local PDF knowledge base with vector search using libsql w/vectors
leonickson1
★ 668Swiftlet
Swiftlet is a Swift and Metal runtime that runs large Qwen Mixture-of-Experts models locally on Apple devices by streaming expert weights from storage, enabling 35B and 80B models to run with low RAM, including on iPhone.
livekit
★ 668client-sdk-js
LiveKit browser client SDK (javascript)
moeru-ai
★ 668xsai
🤖💬 extra-small AI SDK.
retrage
★ 668gpt-macro
ChatGPT powered Rust proc macro that generates code at compile-time.
addsumtech
★ 667slides_maker
Turn papers, code, and docs into presentation-ready, natively editable PPTX in Codex / Claude Code. Native charts and equations, speaker notes, click-build animations, and an independent critic review before delivery.
Azure
★ 667co-op-translator
Keep Markdown, Jupyter notebooks, and image text translated as your repository changes.
gargpratyush
★ 667jev-router
Route to the cheapest model in claude code for your task using jev-router
machinewrapped
★ 667llm-subtrans
Open Source project using LLMs to translate subtitles (SRT, SSA/ASS, VTT)
smixs
★ 667visual-skills
AI film director skills for agents: cinematic dramaturgy (Murch, blocking, montage) + exact prompt syntax for Seedance 2.5, Kling 3.0 Turbo/Omni, Veo 3.1, Nano Banana 2, GPT Image 2.5.
Agent-Field
★ 666pr-af
#1 open-source code reviewer on Code-Review-Bench
ServiceNow
★ 666AgentLab
AgentLab: An open-source framework for developing, testing, and benchmarking web agents on diverse tasks, designed for scalability and reproducibility.
Tencent
★ 666AICGSecEval
A.S.E (AICGSecEval) is a repository-level AI-generated code security evaluation benchmark developed by Tencent Wukong Code Security Team.
NadirRouter
★ 665NadirClaw
Open-source LLM router & AI cost optimizer. Routes simple prompts to cheap/local models, complex ones to premium — automatically. Drop-in OpenAI-compatible proxy for Claude Code, Codex, Cursor, OpenClaw. Saves 40-70% on AI API costs. Self-hosted, no middleman.