This repo contains evaluation code for the paper "MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI"
- computer-vision
- deep-learning
- deep-neural-networks
- evaluation
142,273 visible repositories in the index
1,273–1,296 of 1,507 · Most stars
This repo contains evaluation code for the paper "MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI"
Are Copilots Local Yet? The frontier of local LLM Copilots for code completion, project generation, shell assistance, and more. Find tools shaping tomorrow's developer experience, today!
Question answering system for PDF files
AINL helps turn AI from "a smart conversation" into "a structured worker." It is designed for teams building AI workflows that need multiple steps, state and memory, tool use, repeatable execution, validation and control, and lower dependence on long prompt loops. AINL is a compact, graph-canonical, AI-native programming system for (READ: README)
Desk-Emoji is a truly open-source AI desktop robot featuring an emoji screen, a two-axis console, and LLM capabilities for voice chat.
Open-source runtime AI agent security tool - monitors and controls AI agents, catching malicious tool use, prompt injection, and policy drift in real time, before the agent acts.
A fast, native RSS reader — plus an agent-facing CLI so your AI agent can read, search and triage your feeds from the shell.
使用 Vue3 + Typescript + Tailwind CSS 框架,调用 OpenAI 的 gpt-3.5-turbo 模型 API 实现的简单聊天对话,支持连续对话。
Uses ChatGPT API, Bard API, and Llama2, Python-Nmap, DNS Recon, PCAP and JWT recon modules and uses the GPT3 model to create vulnerability reports based on Nmap scan data, and DNS scan information. It can also perform subdomain enumeration to a great extent
口袋AI:在手机上离线运行大模型的私人 AI 助手(Android / iOS)。本地推理、数据不出手机,内置 HF 镜像与中文模型。Offline on-device LLM chat app, the Chinese fork of PocketPal AI.
The definitive OpenAI, Claude, MCP, Harness, Evals, and Production Agent Systems learning roadmap.
Open-source SEO & GEO audit: a zero-dependency CLI (npx), an agent skill for Claude Code, Cursor, Codex, Gemini & Copilot, 47 SEO prompts and a cited Google/Bing/AI-search knowledge base. Checks robots.txt, sitemaps, canonicals, hreflang, structured data, Core Web Vitals and AI crawlers — then fixes them.
A local AI gateway for AI agents, unifying your subscriptions and API providers with smart routing and on-device privacy protection.
MindWork AI Studio is a free, independent cross-platform desktop app for local and cloud LLMs across providers, built to democratize AI access.
Run Qwen3-TTS text-to-speech locally on Mac (M1/M2/M3/M4). Voice cloning, voice design, custom voices. 100% offline using MLX.
ComfyUI nodes for vision-language models: Qwen3-VL, Moondream 3, Florence-2, SmolVLM2, InternVL, Gemma 3, MiniCPM-V. Plus open-vocabulary detection, SAM2/SAM3 segmentation, video temporal reasoning, GGUF via llama.cpp, and hosted LLM/VLM APIs.
Lightweight Claude OAuth to OpenAI-compatible API proxy
八字、紫微、星盘、六爻、梅花、奇门、大六壬、小六壬、塔罗、雷诺曼、灵签、择日一站式玄学算命占卜工具包,输出结构化提示词与数据。提供公开 API、MCP Server 与 skill。
历年ICLR论文和开源项目合集,包含ICLR2021、ICLR2022、ICLR2023、ICLR2024、ICLR2025.
Minimal and scalable research codebase in JAX, designed for rapid iteration on frontier research in LLM and other autoregressive models.
🔍 Explore what happens under the hood with the ChatGPT web app, its backend API calls and more. And some speculation, of course.
Turn any document into clean, AI-ready Markdown. Local-first desktop app: reads scanned PDFs, batches folders, runs offline, and uses far fewer tokens than vision models.
A llama.cpp drop-in replacement for OpenAI's GPT endpoints, allowing GPT-powered apps to run off local llama.cpp models instead of OpenAI.
论文XMind笔记生成工具,将论文pdf通过ChatGPT转换为带有图片和公式的简要XMind笔记,提高论文阅读效率。