79,841 visible repositories in the index
553–576 of 1,242 · Most stars
🦦 Otter, a multi-modal model based on OpenFlamingo (open-sourced version of DeepMind's Flamingo), trained on MIMIC-IT and showcasing improved instruction-following and in-context learning ability.
An open source AI wearable device that captures what you say and hear in the real world and then transcribes and stores it on your own server. You can then chat with Adeus using the app, and it will have all the right context about what you want to talk about - a truly personalized, personal AI.
Code for the paper "Evaluating Large Language Models Trained on Code"
Native macOS menu bar app to use your Claude Code & ChatGPT subscriptions with AI coding tools - no API keys needed
一个现代化的 Claude Code & Codex API 代理服务，提供智能负载均衡、用户管理和使用统计功能。
Python package to easily retrain OpenAI's GPT-2 text-generating model on new texts
OP Vault ChatGPT: Give ChatGPT long-term memory using the OP Stack (OpenAI + Pinecone Vector Database). Upload your own custom knowledge base files (PDF, txt, epub, etc) using a simple React frontend.
The Swiss Army Knife of Offline AI. Chat, see, speak, and generate images on your phone or Mac — GGUF LLMs, vision, Whisper speech-to-text, Stable Diffusion, tool calling, and local-network servers. Runs on your CPU, GPU, or NPU. No account, no API key, zero data leaves your device.
[CVPR2024 Highlight][VideoChatGPT] ChatGPT with video understanding! And many more supported LMs such as miniGPT4, StableLM, and MOSS.
🤖 Type-safe, provider-agnostic TypeScript AI SDK for streaming chat, tool calling, agents, and multimodal apps across OpenAI, Anthropic, Gemini, React, Vue, Svelte, and Solid.
LLM-as-a-Verifier is a general-purpose framework that provides fine-grained feedback for any agent without requiring additional training. It achieves SOTA performance across coding, robotics, and medical agentic benchmarks.
Intercept and inspect Coding Agent API traffic from Claude Code, Codex CLI, Gemini CLI, Cursor CLI, OpenCode, Kimi/Kimi Code, Pi, and Hermes in a local trace viewer.
High-performance single-GPU inference for selected model checkpoints and GPUs.
A high-performance inference engine for AI models
Document Chatbot — multiple files. Powered by GPT / Embedding.
Leaderboard Comparing LLM Performance at Producing Hallucinations when Summarizing Short Documents
A native macOS app that allows users to chat with a local LLM that can respond with information from files, folders and websites on your Mac without installing any other software. Powered by llama.cpp.
Miles is an enterprise-facing reinforcement learning framework for LLM and VLM post-training, forked from and co-evolving with slime.
A python package to analyze and compare voices with deep learning
基于LangChain和ChatGLM-6B等系列LLM的针对本地知识库的自动问答
Deobfuscate Javascript code using ChatGPT
RAG Web UI is an intelligent dialogue system based on RAG (Retrieval-Augmented Generation) technology.
Comet: agent skill harness for turning ideas into evaluated workflows
AI Chatbots in terminal for free