InnerVault

Library

85,340 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.

Results

Looks like a goal we have a starting path for: I want to build an AI agent

  1. An MCP Multimodal AI Agent with eyes and ears!

    Stale GitHub, the-ai-merge 581 ★Apache-2.0Updated 10 months ago

    git clone https://github.com/the-ai-merge/multimodal-agents-course.git
  2. AppAgent

    AI repositories

    AppAgent: Multimodal Agents as Smartphone Users, an LLM-based multimodal agent framework designed to operate smartphone apps.

    Stale GitHub, TencentQQGYLab 6,902 ★MITUpdated 20 months ago

    git clone https://github.com/TencentQQGYLab/AppAgent.git
  3. OmAgent

    AI repositories

    [EMNLP-2024] Build multimodal language agents for fast prototype and production

    Stale GitHub, om-ai-lab 2,669 ★Apache-2.0Updated 31 days ago

    git clone https://github.com/om-ai-lab/OmAgent.git
  4. MMClaw

    Agents & frameworks

    Ultra-Lightweight, Pure Python Multimodal Agent.

    Stale GitHub, CrawlScript 151 ★GPL-3.0Updated 22 days ago

    git clone https://github.com/CrawlScript/MMClaw.git
  5. mobile-use

    Agents & frameworks

    MobileUse: an open-source mobile GUI agent for Android phone automation, AndroidWorld/AndroidLab evaluation, hierarchical reflection, and proactive exploration.

    Stale GitHub, MadeAgents 234 ★MITUpdated 4 months ago

    git clone https://github.com/MadeAgents/mobile-use.git
  6. OSWorld

    Datasets & benchmarks

    [NeurIPS 2024] OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments

    Indexed GitHub, xlang-ai 3,262 ★Apache-2.0Updated 2 days ago

    git clone https://github.com/xlang-ai/OSWorld.git
  7. Qwen3.7 Flash is a vision-language reasoning model from Alibaba. It is suited for multimodal agents, visual coding, search, and computer interaction, with strengths in object recognition, spatial understanding, and real-world...

    Indexed OpenRouter model list, qwen Updated 3 months ago

    qwen/qwen3.7-flash
  8. GLM-4.5V is a vision-language foundation model for multimodal agent applications. Built on a Mixture-of-Experts (MoE) architecture with 106B parameters and 12B activated parameters, it achieves state-of-the-art results in video understanding,...

    Indexed OpenRouter model list, z-ai Updated 15 months ago

    z-ai/glm-4.5v
  9. GLM-5V-Turbo is Z.ai’s first native multimodal agent foundation model, built for vision-based coding and agent-driven tasks. It natively handles image, video, and text inputs, excels at long-horizon planning, complex coding,...

    Indexed OpenRouter model list, z-ai Updated 7 months ago

    z-ai/glm-5v-turbo

Indexed entries aren't reviewed or tested by InnerVault. Details come straight from each source. Anything that can reach your accounts, files or browser can do damage, so read the source before you install it.