OmniAgent AI Agent

by HarryHsing• 84•• Scanned•Claim this listing•Request removal
Design & Mediaagentaudio visualicml2026llm agentlong video understanding

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 on LVBench.

OmniAgent is an open-source ai agent by HarryHsing, written mainly in Python, with 84 GitHub stars and the Apache-2.0 license. Its code was last updated Sep 18, 2026.

Scan summary: scanned Nov 5, 2026 at commit 0ce93ec. Seen able to run shell commands, run dynamic code. Scan policy

What OmniAgent can touch

  • Run shell commandsFound in the code by our scan
  • Run dynamic codeFound in the code by our scan
  • Read or write filesNot seen in this scan
  • Read environment and secretsNot seen in this scan
  • Control a web browserNot seen in this scan
  • Connect to databasesNot seen in this scan
  • Read or send messagesNot seen in this scan
  • Touch money or tradingNot seen in this scan
  • Connect to the internetNot run in this scan

"Not seen" means our checks did not find it, and the tool may still do it. Covers commit 0ce93ec, Nov 5, 2026. See the scan policy.

Before you install OmniAgent

AgenticMart scanned OmniAgent on Nov 5, 2026 with automated checks for hidden code, known-malicious packages, leaked secrets and vulnerable dependencies. The result covers one commit under our scan policy, so review what access you give it and check any advisories shown here.

What it can access

  • An AI agent decides its own next steps and calls whatever tools you give it, so its risk depends on the access you grant.

Before you install

  1. Pin the version you reviewed instead of always installing the latest release.
  2. Read the tool list or scripts before the first run, and keep approval prompts on for actions that write, send or delete.
  • Maintained by HarryHsing on GitHub, 84 stars and 7 forks. Popularity is not proof of safety.
  • Last code change: Sep 18, 2026.
  • Open-source license: Apache-2.0.

OmniAgent is an open-source ai agent by HarryHsing, written mainly in Python. 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 on LVBench.

At a glance

Stars
84
Forks
7
Language
Python
License
Apache-2.0
Created
Jun 2026
Last update
Sep 18, 2026
Type
AI Agent
Price
Free

Topics

agentaudio-visualicml2026llm-agentlong-video-understandingmllmmultimodalmultimodal-llmomni-modalqwenreinforcement-learningtemporal-groundingvideo-question-answeringvideo-understandingvision-language-model

Questions about OmniAgent

What is 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 on LVBench.

Who maintains OmniAgent?

OmniAgent is maintained by HarryHsing on GitHub (HarryHsing/OmniAgent). AgenticMart lists it from public repository data.

Is OmniAgent safe to use?

AgenticMart scanned OmniAgent on Nov 5, 2026 with automated checks for hidden code, known-malicious packages, leaked secrets and vulnerable dependencies. The result covers one commit under our scan policy, so review what access you give it and check any advisories shown here.

What license does OmniAgent use?

It is published under the Apache-2.0 license.

OmniAgent alternatives

View more →

Similar ai agents in Design & Media, ranked by GitHub stars. Compare licence, recent activity and scan status before you choose.

NameStarsLicenceLast updatedScan
OmniAgent (this page)
HarryHsing
84Apache-2.0Sep 18, 2026Scanned, no flagged issues
Taste Skill
Leonxlnx
107kMITOct 31, 2026Scanned, no flagged issues
Archify
tt-a1i
92kApache-2.0Oct 31, 2026Scanned, no flagged issues
Hyperframes
heygen-com
77kApache-2.0Nov 1, 2026Scanned, no flagged issues
OpenMontage
calesthio
74kAGPL-3.0Oct 28, 2026Scanned, no flagged issues
CopilotKit
CopilotKit
38kMITOct 31, 2026Scanned, no flagged issues