Vision Agents
Stream's open framework for building real-time voice and video agents with any model.
Updated
✨ Try AgentScout's free AI image generator →Good for: building AI agents, building voice agents
Use cases
About Vision Agents
Vision Agents is listed in our voice category and is aimed at builders. Stream's open framework for building real-time voice and video agents with any model. Pricing, as the maker states it: Open source. Maturity: Mature. We last checked the official link on 2026-10-16.
What is Vision Agents?
Vision Agents, from Stream, is an open framework for multimodal AI agents that watch, listen and understand video.
It provides building blocks for low-latency video experiences powered by your choice of models.
Sources: the official README and our directory listing, checked 2026-10-18. Official site: visionagents.ai.
Who is Vision Agents for?
Developers building real-time voice and video agents.
Vision Agents at a glance
- Open source: Yes (Apache License 2.0)
- GitHub: GetStream/Vision-Agents · 8,183 stars (as of Oct 21, 2026)
Key features
- Video AI
- Voice
- Any model
- Low latency
Vision Agents FAQ
What is Vision Agents?
Vision Agents, from Stream, is an open framework for multimodal AI agents that watch, listen and understand video.
Who is Vision Agents for?
Developers building real-time voice and video agents.
Is Vision Agents free?
Vision Agents's pricing, as the maker states it: Open source. Open-source tools are free to use, though you may still pay for model API usage or a hosted plan. Check the official site for current plans.
Is Vision Agents open source?
Yes. Vision Agents is released under the Apache License 2.0, according to its GitHub repository.
What are alternatives to Vision Agents?
Similar tools include Vapi, TEN Framework, LiveKit Agents, Bolna, Cartesia Sonic and TryVoice.
Vision Agents ratings and reviews
Be the first to rate Vision Agents: tap 1 to 5 stars below. A written review is optional.
Vision Agents alternatives
Other voice tools in our directory. See all voice tools →
Vapi
Platform for building and deploying phone voice agents.
TEN Framework
Open-source framework for real-time multimodal voice agents, including the TEN Agent demo.
LiveKit Agents
Real-time voice and video infrastructure with an agents framework.
Bolna
Platform for building, deploying and testing voice AI agents for recruitment, sales and customer support.
Cartesia Sonic
Cartesia's real-time text-to-speech API with emotion control, built for low-latency voice agents.
TryVoice
Hands-free voice runtime for coding agents with wake word, push-to-talk and streaming replies.
Popular searches with this tool
🏆 Ranked in: Best AI Voice Agent Platforms
🧭 Task guides: Voice and phone agents for building AI agents
Badge for makers
Built Vision Agents? Add this badge to your README or site. It links back to this page. About badges
