OmniAgent

by HarryHsing · Agent Tool · ★ 38

About OmniAgent

OmniAgent (ICML 2026): the first native omni-modal agent for active video perception — a 7B agent that beats Qwen2.5-VL-72B with 73% fewer frames.

agentaudio-visualicml2026llm-agentlong-video-understandingmllmmultimodalmultimodal-llmomni-modalqwen

Quick Facts

Stars38
Forks3
LanguagePython
CategoryAgent Tool
LicenseApache-2.0
Quality Score54.2963281311495/100
Open Issues2
Last Updated2026-07-03
Created2026-06-11
Platformspython
Est. Tokens~13k

Compatible Skills

These tools work well together with OmniAgent for enhanced workflows:

  • vllm-mlx — semantic(0.31)+complementary+rare_topics+same_lang+shared_platform (64%)
  • video-recap — semantic(0.37)+complementary+same_lang+similar_pop+shared_platform (63%)
  • ParaVT — semantic(0.51)+rare_topics+same_lang+similar_pop+shared_platform (62%)
  • HappyHorse-1.0-API — semantic(0.41)+complementary+same_lang+similar_pop+shared_platform (59%)

More Agent Tool Tools

Explore other popular agent tool tools:

View all Agent Tool tools →

Popular Python Agent Tools

Frequently Asked Questions

What is OmniAgent?

OmniAgent is OmniAgent (ICML 2026): the first native omni-modal agent for active video perception — a 7B agent that beats Qwen2.5-VL-72B with 73% fewer frames.. It is categorized as a Agent Tool with 38 GitHub stars.

What programming language is OmniAgent written in?

OmniAgent is primarily written in Python. It covers topics such as agent, audio-visual, icml2026.

How do I install or use OmniAgent?

You can find installation instructions and usage details in the OmniAgent GitHub repository at github.com/HarryHsing/OmniAgent. The project has 38 stars and 3 forks, indicating an active community.

What license does OmniAgent use?

OmniAgent is released under the Apache-2.0 license, making it free to use and modify according to the license terms.

View on GitHub → Browse Agent Tool tools