Vision Agents Files

Open Vision Agents by Stream. Build voice and vision agents quickly

This is an exact mirror of the Vision Agents project, hosted at https://github.com/GetStream/vision-agents. SourceForge is not affiliated with Vision Agents.

The interactive file manager requires Javascript. Please enable it or use sftp or scp.
You may still browse the files here.

Name	Modified	Size	InfoDownloads / Week
Parent folder
README.md	2026-08-13	1.1 kB	0
v0.6.9 source code.tar.gz	2026-08-13	122.5 MB	0
v0.6.9 source code.zip	2026-08-13	123.0 MB	0
Totals: 3 Items		245.4 MB	0

What's Changed

[Speechify] Add support for Speechify as a TTS provider by @DaemonLoki in https://github.com/GetStream/Vision-Agents/pull/615
fix(speechify): send Speechify-Caller attribution header by @luke-speechify in https://github.com/GetStream/Vision-Agents/pull/617
[xAI] Add support for grok-voice-think-fast-2.0 by @DaemonLoki in https://github.com/GetStream/Vision-Agents/pull/624
fix(nvidia): default VLM to llama-3.2-11b-vision-instruct by @Nash0x7E2 in https://github.com/GetStream/Vision-Agents/pull/625
Add metadata to agents by @DaemonLoki in https://github.com/GetStream/Vision-Agents/pull/618
feat(telnyx): add Telnyx LLM, STT and TTS by @Nash0x7E2 in https://github.com/GetStream/Vision-Agents/pull/629
docs(telnyx): release polish — README, voice bot example, CI key by @Nash0x7E2 in https://github.com/GetStream/Vision-Agents/pull/631

New Contributors

@luke-speechify made their first contribution in https://github.com/GetStream/Vision-Agents/pull/617

Full Changelog: https://github.com/GetStream/Vision-Agents/compare/v0.6.8...v0.6.9

Source: README.md, updated 2026-08-13

Other Useful Business Software

$300 Free Credits to Build on Google Cloud Icon

$300 Free Credits to Build on Google Cloud

New customers can spin up VMs, build with AI, and query data at no cost.

Put your $300 in credit toward real workloads, then keep building with free monthly usage for 20+ products. No commitment and no charge until you upgrade.

Start Free

Build Agents and Models on One Platform Icon

Build Agents and Models on One Platform

Everything you need to build production-ready agents and models. Access 200+ Google and third-party AI models and tools.

Gemini Enterprise Agent Platform is Google Cloud's comprehensive platform for developers to build, scale, govern, and optimize agents and models. Choose from Google's most advanced models and third-party models like Anthropic's Claude Model Family.

Start Free

$300 Free Credits to Build on Google Cloud

New customers can spin up VMs, build with AI, and query data at no cost.

Put your $300 in credit toward real workloads, then keep building with free monthly usage for 20+ products. No commitment and no charge until you upgrade.

Start Free

Recommended Projects

LiveKit Agents
Framework for building realtime multimodal voice AI agents apps
Pipecat
Framework for building real-time voice and multimodal AI agents
Computer vision projects
computer vision projects | Fun AI projects related to computer vision
AskUI Vision Agent
Enable AI to control your desktop, mobile and HMI devices
TEN
Open-source framework for conversational voice AI agents