GetStream / Vision-Agents
Open Vision Agents by Stream. Build voice and vision agents quickly with any model or video provider. Uses Stream's edge network for ultra-low latency.
Why this job: topics: tts, stt, voice-ai
What it does
- Video AI. Built for real-time video AI. Combine YOLO, Roboflow, and others with Gemini/OpenAI in real-time.
- Low Latency. Join quickly (500ms) and maintain audio/video latency under 30ms
- Open. Built by Stream, but works with any video edge network.
- Native APIs. Native SDK methods from OpenAI (create response), Gemini (generate), and Claude (
- SDKs. SDKs for React, Android, iOS, Flutter, React Native, and Unity, powered by Stream's ultra-low-latency
Get started
No single install command. Read the steps in the README (opens in new tab)
- Maintenance
- Active
- Last commit 4 days ago
- Stars
- 8,202
- +4 this week
- Licence
- Apache-2.0
- Allows business use
- Downloads for
- None listed
- No release files
- Latest version
- v0.6.9
- Released 2 months ago
- Built with
- Python
- 77% of the code
Is it looked after?
- Contributors
- 4
- Last 90 days
- Issues
- 90% closed
- 3 still open
- Pull requests
- 1,596 merged
- 64 waiting
- Releases
- 54
- 30+ in the last year
- No contributing guide
- Security policy (opens in new tab)
- No code of conduct
Similar repos
| Repo | Stars | Last commit | Licence | Downloads for |
|---|---|---|---|---|
| KoljaB / RealtimeTTS | 4,052 | 3 days ago | MIT | No downloads |
| jianchang512 / pyvideotrans | 19,684 | today | GPL-3.0 | No downloads |
| gojargo / jargo | 109 | 4 days ago | BSD-2-Clause | Linux |
More: languages, topics and project record
Languages
- Python 77%
- Go 23%
- Jinja <1%
- Shell <1%
Topics
- ai
- ai-agents
- vision-ai
- voice-ai
- video-agents
- agentic-ai
- agents
- realtime
- stt
- tts
- video-ai
Project record
- JobSpeech and audio
- StatusListed
- Commits1,167
- Forks700
- Watching49
- Stars in 28 days+52
- CreatedAug 11, 2025
- First seen by usNov 7, 2026
- CheckedNov 9, 2026