Results for “vision”

A repo lists papers related to LLM based agent

MLX Studio - Home of JANG_Q - Image Gen/Edit + Chat/Code All in one - + OpenClaw (Anthropic API)

@e2b-dev✓ Official

AI computer use powered by open source LLMs and E2B Desktop Sandbox

Code repo for the paper: Attacking Vision-Language Computer Agents via Pop-ups

Give AI agents motion vision, decode hidden messages inside random-dot “ghost font” videos.

The RL Bridge for LLM-based Agent Applications. Made Simple & Flexible.

[CVPR 2025 🔥]A Large Multimodal Model for Pixel-Level Visual Grounding in Videos

[CVPR 2024 🔥] Grounding Large Multimodal Model (GLaMM), the first-of-its-kind model capable of generating natural langu

A curated list of Generative AI tools, works, models, and references

AI smart home assistant for Home Assistant: LangGraph agent + MCP tools + RAG knowledge graph + vision perception

图文并茂的 PDF RAG 系统：支持版式感知分块、图表深度理解与精准视觉溯源。 Multimodal PDF RAG: Features layout-aware chunking, visual chart understanding,

Anthropic Claude API wrapper for Go

A curated list of awesome things related to Anthropic Claude

Source-backed GPT-5.6 use cases for coding, agents, creative work, integrations, benchmarks, and practical limits.

♾️ Private Agent Fleet with Spec Coding. Each agent gets their own GPU-accelerated desktop. Run Claude, Codex, Gemini an

[CVPR2024 Highlight] Editable Scene Simulation for Autonomous Driving via LLM-Agent Collaboration

Bundle agentic coding souverain : OpenCode + agent-vm + Albert API + skills État + MCP

Yunjue Agent: A Fully Reproducible, Zero-Start In-Situ Self-Evolving Agent System for Open-Ended Tasks

优质稳定的OpenAI、Claude等的API接口-For企业和开发者。OpenAI的api proxy，支持ChatGPT的API调用，支持Anthropic claude的官方接口形式，支持Google gemini的官方接口形式，支持

Exploring Zep & Knowledge Graphs with Open-Source models as an alternative to OpenAI's Assistant Threads

Odyssey: Empowering Minecraft Agents with Open-World Skills

Transform any arXiv papers into slides using LLMs

Pocket-sized Ruby AI agent framework / LLM assistant with multi-LLM support

xLAM: A Family of Large Action Models to Empower AI Agent Systems

Multi-channel AI proxy with intelligent key rotation. 智能密钥轮询的多渠道 AI 代理。

A declarative way to control LLMs.

Elixir implementation of a LangChain style framework that lets Elixir projects integrate with and leverage LLMs.