[CVPR2024 Highlight][VideoChatGPT] ChatGPT with video understanding! And many more supported LMs such as miniGPT4, StableLM, and MOSS.
Repository Index
75,360 visible repositories in the index
529–552 of 1,139 · Most stars
🤖 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.
Leaderboard Comparing LLM Performance at Producing Hallucinations when Summarizing Short Documents
- generative-ai
- hallucinations
- llm
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.
A high-performance inference engine for AI models
LLM as a Chatbot Service
Translatedhttps://checkcc.org is a Claude runtime environment detection and account risk analysis tool, aimed at users who are registering a Claude account, subscribing to Claude Pro, applying for the Claude API, or using Claude Code, or who are worried about Claude account bans, account restrictions, or subscription failures.
- check
- claude
- claude-code
- claude-max
A python package to analyze and compare voices with deep learning
SuperCLUE: 中文通用大模型综合性基准 | A Benchmark for Foundation Models in Chinese
- chatgpt
- chinese
- evaluation
- foundation-models
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
🕹️ Open-source, developer-first LLMOps platform designed to streamline prompt design, version management, instant delivery, collaboration, troubleshooting, observability and more.
A Repo For Document AI
- document-parser
- document-image-analysis
- table-recognition
- ocr
OneTrainer is a one-stop solution for all your Diffusion training needs.
- fine-tuning
- lora
- training
- image-model-training
Dead simple FLUX LoRA training UI with LOW VRAM support
[NeurIPS 2024] OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments
- agent
- artificial-intelligence
- benchmark
- multimodal
🌊 AChat - An open-source/self-hosted/local-first AI platform, designed for enterprises and teams, perfectly combining powerful local processing capabilities with seamless remote synchronization.
Full description can be found here: https://discuss.huggingface.co/t/pretrain-gpt-neo-for-open-source-github-copilot-model/7678?u=ncoop57
Templates and workflow for generating PRDs, Tech Designs, and MVP and more using LLMs for AI IDEs
- ai-agents
- ai-workflow
- beginner-friendly
- mvp-development