uclanlp / OpenVLHarness
Official Code for OpenVLHarness: Real-World Visual Agentic Tool‑Use with Multimodal Memory
Why this job: topics: coding-agent, agent-harness, harness-engineering
What it does
- Consistent gains. Across 22 benchmarks in four domains, seven backbones
- Cost efficiency. With GPT-6 Luna, OpenVLHarness at low reasoning effort
- Flexible capabilities. Customizable capabilities and backend models based on
- Multimodal memory. Images, boxes, masks, depth maps and web references stay
- Any model. Gains validated on eight backbones across five open-weight and
Get started
No single install command. Read the steps in the README (opens in new tab)
- Maintenance
- Active
- Last commit 11 days ago
- Stars
- 431
- +75 this week
- Licence
- MIT
- Allows business use
- Downloads for
- None listed
- No release files
- Latest version
- None yet
- No releases
- Built with
- Python
- 100% of the code
Is it looked after?
- Contributors
- 2
- Last 90 days
- Issues
- 0% closed
- 2 still open
- Pull requests
- 2 merged
- 0 waiting
- Releases
- None
- Never published
- No contributing guide
- Security policy (opens in new tab)
- No code of conduct
More: languages, topics and project record
Languages
- Python 100%
- Shell <1%
Topics
- agent-harness
- agentic-ai
- ai-agents
- coding-agent
- deep-research
- grounded-reasoning
- harness-engineering
- harness-optimization
- llm
- llm-agents
- mllm
- multimodal
Project record
- JobCoding agents
- StatusNew to our list
- Commits824
- Forks24
- Watching5
- CreatedOct 15, 2026
- First seen by usNov 7, 2026
- CheckedNov 9, 2026