OpenAssistant is a chat-based assistant that understands tasks, can interact with third-party systems, and retrieve information dynamically to do so.
Repository Index
132,241 visible repositories in the index
1–24 of 79 · Most stars
The Open Standard for Generative UI
lightweight, standalone C++ inference engine for Google's Gemma models.
SuperPrompt is an attempt to engineer prompts that might help us understand AI agents.
Solve Visual Understanding with Reinforced VLMs
- deepseek-r1
- grpo
- llm
- multimodal
The ultimate RAG for your monorepo. Query, understand, and edit multi-language codebases with the power of AI and knowledge graphs
- ai
- ast
- claude-code
- code-analysis
Kodezi Chronos is a debugging-first language model that achieves state-of-the-art results on SWE-bench Lite (80.33%) and 67% real-world fix accuracy, over six times better than GPT-4. Built with Adaptive Graph-Guided Retrieval and Persistent Debug Memory. Model available Q1 2026 via Kodezi OS.
- artificial-intelligence
- benchmark
- benchmark-report
- bug-fixing
An Open-Source Framework for Prompt-Learning.
🤗 AutoTrain Advanced
One-for-All Multimodal Evaluation Toolkit Across Text, Image, Video, and Audio Tasks
- agi
- evaluation
- large-language-models
- multimodal
TranslatedChinese Language Understanding Evaluation Benchmark: datasets, baselines, pre-trained models, corpus and leaderboard
- nlu
- benchmark
- chinese
- corpus
Sourcebot is a self-hosted tool that helps humans and agents understand your codebase.
- code-search
- code-intelligence
- sourcebot
- fair-source
[KDD'2026] "VideoRAG: Chat with Your Videos"
- large-language-models
- llms
- long-video-understanding
- multi-modal-llms
[CVPR2024 Highlight][VideoChatGPT] ChatGPT with video understanding! And many more supported LMs such as miniGPT4, StableLM, and MOSS.
A Repo For Document AI
- document-parser
- document-image-analysis
- table-recognition
- ocr
Skywork-R1V is an advanced multimodal AI model series developed by Skywork AI, specializing in vision-language reasoning.
- deepseek-r1
- llm
- r1v
- reasoning
[EMNLP 2023 Demo] Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding
- large-language-models
- video-language-pretraining
- vision-language-pretraining
- blip2
✨✨[NeurIPS 2025] VITA-1.5: Towards GPT-4o Level Real-Time Vision and Speech Interaction
- large-multimodal-models
- multimodal-large-language-models
- omni-language-model
- omni-modal-video-understanding
A unified cross-platform AI client supporting seamless transitions between standard cloud APIs and on-device, offline execution of custom and uncensored language models.
"FastCode: Accelerating and Streamlining Your Code Understanding"
AI code-writing assistant that understands data content
NVIDIA AI Blueprint for video search and summarization (VSS) is a GPU-accelerated reference architecture for building video analytics agents with real-time verified alerts, visual Q&A, and automated reporting. The VSS Blueprint uses vision language models (VLMs) such as NVIDIA Cosmos, LLMs such as NVIDIA Nemotron, RAG, and NVIDIA NIMs.
Text-To-Speech, RAG, and LLMs. All local!
- embeddings
- llm
- local
- rag
An unofficial C#/.NET SDK for accessing the OpenAI GPT-3 API