68,760 visible repositories in the index
25–48 of 66 · Most stars
Rapid-MLX is an open-source (Apache 2.0) OpenAI- and Anthropic-compatible LLM inference server for Apple Silicon, built on MLX, focused on reliable tool calling for coding agents. Up to 4× faster than Apple's MLX (mlx-lm) on the same weights.
Fully featured & enhanced replacement for copilot.vim complete with API for interacting with Github Copilot
Witness the aha moment of VLM with less than $3.
一个多模态多模型通用型的全局全能 AI 查询生成桌面悬浮助手应用
✨ Reverse-engineered Python API for Google Gemini web app
[CVPR 2026] PromptEnhancer is a prompt-rewriting tool, refining prompts into clearer, structured versions for better image generation.
WhatsApp Web automation library for Node.js and TypeScript. Manage sessions, send and receive messages, handle media and build bots with Puppeteer. Part of the WPPConnect ecosystem.
A Xcode 5+ plugin that adds more flexible autocompletion rather than just prefix-matching.
한국 문서를 읽고·고치고·새로 쓰는 AI 문서 도구 — HWP·HWPX·PDF·오피스·스캔(OCR)을 Markdown으로, 신구대조·서식 보존 편집·Markdown→HWPX 작성·HWP→HWPX 변환·양식 채우기·공문서 검수까지. 라이브러리·CLI·MCP | Read, diff, edit, write and convert Korean documents (HWP, HWPX, PDF, Office, scans) — library, CLI and MCP server
🌲 春松客服，开源客服系统
The goal of this project is to enable users to create cool web demos using the newly released OpenAI GPT-3 API with just a few lines of Python.
TranslatedPagekin (formerly AI Novel Writer): free, open-source AI novel writing app for long novels and web fiction. Imitate, continue, rewrite; import writing skills. Local-first, no model bundled. Windows & macOS. Pagekin, a free AI novel writing app, covers everything from settings and blueprints to the main text, review, and final draft. It supports deconstructing and imitating, continuing, and rewriting, and can import writing Skills (such as removing the "AI flavor"). You must configure the model yourself; your works stay local.
OCRFlux is a lightweight yet powerful multimodal toolkit that significantly advances PDF-to-Markdown conversion, excelling in complex layout handling, complicated table parsing and cross-page content merging.
ASR/STT subtitle generator. Uses Qwen3-ASR, local LLM, Whisper, TEN-VAD. Noise-robust for JAV
This includes the original implementation of SELF-RAG: Learning to Retrieve, Generate and Critique through self-reflection by Akari Asai, Zeqiu Wu, Yizhong Wang, Avirup Sil, and Hannaneh Hajishirzi.
The collection of pre-trained, state-of-the-art AI models for ailia SDK
Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by executing routine tasks, explaining complex code, and handling git workflows - all through natural language commands. All original source code is the property of Anthropic.
A community-driven PHP SDK for OpenAI.
Steering-first neuron explorer for Qwen3.5-4B: push every MLP neuron, keep every rollout, browse the results
1M param OCR model - runs on CPU, 15x faster than tesseract, close to 1B+ param models in accuracy
LLPhant - A comprehensive PHP Generative AI Framework using OpenAI GPT 4. Inspired by Langchain
Own the flow: one open-source AI platform for your knowledge, models and channels – web, WhatsApp, email, Outlook, Nextcloud & ownCloud. Local and cloud models side by side, with the cost on every answer.
37 tok/s from Qwen3-Next-80B (48 GB) on a 32 GB laptop, 24 without drafts vs 2.8 for llama.cpp; reading 62 vs 16 tok/s. Faster than llama.cpp on all 13 models compared in Q4_K_M. LLMs bigger than your RAM, pure C, CPU or GPU.
Run models larger than your RAM or VRAM by streaming MoE experts from SSD. Built on llama.cpp.