Witsy: desktop AI assistant / universal MCP client
Repository Index
74,362 visible repositories in the index
793–816 of 1,140 · Most stars
Enforce the output format (JSON Schema, Regex etc) of a language model
[ACL2026] "MiniRAG: Making RAG Simpler with Small and Open-Sourced Language Models"
A pipeline parallel training script for diffusion models.
JoyAI-VL-Interaction: An Open Real-time Video-Language Interaction System
An automatic evaluator for instruction-following language models. Human-validated, high-quality, cheap, and fast.
- deep-learning
- evaluation
- foundation-models
- instruction-following
Desktop AI Assistant powered by GPT, Gemini, Claude, Grok, Ollama, DeepSeek, Perplexity, and more - chat, agents, tools, MCP, plugins, RAG, vision, voice, image and video generation, speech synthesis and speech recognition, web search, memory, presets, canvas, assistants, themes, computer use. Windows, Linux, and Mac.
[ACL 2023] One Embedder, Any Task: Instruction-Finetuned Text Embeddings
- embeddings
- information-retrieval
- language-model
- text-classification
A pre-execution guard for AI coding agents. It blocks destructive Git and file system commands, plus common attempts to access sensitive files, before a tool call runs. Supports Amp Code, Antigravity CLI, Claude Code, Codex, Cursor, DeepSeek Harness, Devin CLI, GitHub Copilot CLI, Grok Build, Hermes Agent, Kimi Code, OpenClaw, OpenCode, and Pi.
prompt2model - Generate Deployable Models from Natural Language Instructions
**ShellGPT is a free chatgpt client, now Supported online search.no need for a key, no need to log in.Multi-node automatic speed measurement switch,Long text translation with no word limit, AI graphics.免费的chatgpt客户端，已支持联网搜索,无需密钥，无需登录,多节点自动测速切换,长文翻译不限字数,AI出图**
A repository that contains models, datasets, and fine-tuning techniques for DB-GPT, with the purpose of enhancing model performance in Text-to-SQL
A LLM trained only on data from certain time periods to reduce modern bias
AI中文提示词秘籍ChatGPT中文提示词秘籍（Prompt圣经）K-Render整理
Cambrian-1 is a family of multimodal LLMs with a vision-centric design.
- chatbot
- clip
- computer-vision
- dino
Fast, Flexible and Portable Structured Generation
- large-language-models
- structured-generation
👾 nao is the #1 open source agentic BI. (1) Create context with nao-core cli, (2) deploy nao chat interface for everyone
- agentic-analytics
- analytics
- analytics-engineering
- bigquery
Easy token price estimates for 400+ LLMs. TokenOps.
14-stage Fusion Pipeline for LLM token compression — reversible compression, AST-aware code analysis, intelligent content routing. Zero LLM inference cost. MIT licensed.
- ai-agent-tools
- context-compression
- context-pruning
- context-window-optimization
Quill - A Modern SaaS-Platform Built With Next.js 13
Predict stock market prices using RNN model with multilayer LSTM cells + optional multi-stock embeddings.
- lstm
- rnn-tensorflow
- stock-price-prediction
- embeddings
Implementation of all RL algorithms in a simpler way
Local AI app and inference engine for agents. Run open-weight LLMs locally — private, 100% offline on your computer. Join our Discord: https://discord.com/invite/8wGSsvmg4V
Enable Gemini in Chrome, AI Powered History search, DevTools Al Innovations in Google Chrome without cleaning data and reinstall.
- ai
- ai-browser
- ai-browser-automation
- ai-browser-control