An on-premises, OCR-free unstructured data extraction, markdown conversion and benchmarking toolkit. (https://idp-leaderboard.org/)
- document
- document-analysis
- extraction
- llms
110,088 visible repositories in the index
361–384 of 901 · Most stars
An on-premises, OCR-free unstructured data extraction, markdown conversion and benchmarking toolkit. (https://idp-leaderboard.org/)
An optimized deep prompt tuning strategy comparable to fine-tuning across scales and tasks
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.
:cloud: :rocket: :bar_chart: :chart_with_upwards_trend: Evaluating state of the art in AI
Simple UI for LLM Model Finetuning
🤖 A Python library for learning and evaluating knowledge graph embeddings
Portable local AI studio for Windows, Linux, and macOS. Zero-setup GUI for Image Generation, GGUF LLMs, Text to Speech & Speech to Text
A list of StableDiffusion styles and some notes for offline use. Pure HTML, CSS and a bit of JS.
Enforce the output format (JSON Schema, Regex etc) of a language model
[ACL2026] "MiniRAG: Making RAG Simpler with Small and Open-Sourced Language Models"
Mezon is a new way to communicate with your team. It's faster, better organized, better for WFH.
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
👾 nao is the #1 open source agentic BI. (1) Create context with nao-core cli, (2) deploy nao chat interface for everyone
A repository that contains models, datasets, and fine-tuning techniques for DB-GPT, with the purpose of enhancing model performance in Text-to-SQL
Community maintained hardware plugin for vLLM on Apple Silicon
Aila(AI超元域): The premier AI integration tool for Windows, macOS, and Android. Ask once, get answers from 10+ AIs like ChatGPT, Gemini, Claude3, Copilot, Poe, perplexity and more. Features customizable AI and prompts.
Steering-first neuron explorer for Qwen3.5-4B: push every MLP neuron, keep every rollout, browse the results
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.
🚀阿童木聊天室 nestjs+vue全栈聊天室 前后端分离 typescript一把梭
An open-source implementaion for fine-tuning Qwen-VL series by Alibaba Cloud.
CORTEX RAG is an enterprise retrieval and knowledge assistant that helps teams find accurate answers from company data with citations, permission-aware retrieval, and fast deployment
中文羊驼大模型三期项目 (Chinese Llama-3 LLMs) developed from Meta Llama 3
designed specifically for AI painting (GPT, Midjourney, Nano Banana, etc.). Help users quickly build, manage, and iterate complex prompts through a visual "fill-in-the-blank" interaction. 通过可视化的"填空"交互方式,帮助用户快速构建、管理和迭代复杂的 Prompt。