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.
Runssource: GitHubhomepagePythonApache-2.0commit 902db86438aa
Python, Apache-2.0 licensed. The project labels itself: agentic ai, agents, ai, ai agents, realtime, stt, tts and video agents.
Vision-Agents runs. An Argusic agent installed it in 12 minutes and hit 3 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
The vision-agents core framework plus anthropic, gemini, openai, deepgram, elevenlabs, getstream, and smart_turn plugins are installed; 733 unit tests pass, the CLI binary responds, and all selected plugin imports resolve correctly.
What the agent ended up with on a clean machine, in its own words. How this is measured
Measured by Argusic on a fresh machine every time. Every number links to its evidence. Argusic Score 100 of 100 (the mean of this project's run scores).
At a glance
Subject data from GitHub, linked at the top of this page, refreshed . Test data by Argusic (CC BY 4.0); every number links to a run page with the full log, the recording, and their sha256 hashes.
What was measured
From the run that decided this verdict. Every line is a recorded value, not an estimate.
What went wrong, in the agent's own words
The agent's own words, worst first, never rewritten into advice.
- No space left on device while extracting torch/CUDA/nvidia wheels (triton, nvidia-cublas, torch) during full uv sync --all-extras --dev8 minutes
- Docker daemon not available — 10 tests in test_agent_launcher.py and 16 tests in test_redis_store.py raise DockerException on collection2 minutes
- Blockbuster blocks os.path.abspath during anthropic SDK credential loading — 9 errors in plugins/anthropic/tests/test_anthropic_llm.py1 minute
- Install time
- 12 minutes
- Cold machine to finish
- 42 minutes
- Errors hit and fixed
- 3 hit, 3 fixed with no human help
- How the result was proved
- pytest tests/ -m 'not integration' --ignore=tests/test_agents/test_session_registry --ignore=tests/test_agents/test_agent_launcher --skip-blockbuster returned 733 passed, 10 deselected, 10 errors (all Docker). Plugin tests (anthropic+gemini+openai+deepgram+elevenlabs+getstream+smart_turn): 149 passed. CLI: 'uv run --no-sync vision-agents --help' returns usage; 'uv run --no-sync vision-agents --version' returns 0.0.1.dev1+g902db8643.
- Model tokens used
- 83,286
- Exact commit tested
- 902db86438aa
- Container image
- sha256:cdd920bce783
What was not measured
The other half, so you can see exactly how far this evidence goes. A gap is printed as a gap and never filled in.
- Peak GPU memory
- this ran on a CPU machine, so there was no GPU to sample
- Behaviour over a long run
- each attempt uses the smallest documented settings and a fixed time budget, so this measures whether it runs, not how it holds up under load
The end of the recording
The last lines of the terminal session that decided this verdict, exactly as they were recorded.
none 7.8G 2.9G 4.6G 39% /
Now I have all the data needed for the final report. Let me record the full picture
exec
/bin/sh -lc 'export PATH="/home/runner/.local/bin:$PATH" && cd /work/repo && python3 -c "
from datetime import datetime
import time
print(f'"'Script started around: {datetime.now().isoformat()}')
\"" in /work/repo
succeeded in 0ms:
Script started around: 2026-09-28T04:57:28.207512
tokens used
83,286Replay the whole session, every command from a clean machine to this point.
How it was tested
One agent, one container, no human help. It installs the project the way its own documentation says to, runs it, and fixes what breaks. Everything below is recorded as it happened: the terminal session, the log and the exact commit. The full method.
Strengths and limits
Measured facts, not opinions. How this is written.
What went well
- Reached a running state on a clean machine, with the session recorded.
- Recovered from all 3 errors without a human stepping in, which says the failures are documented well enough to solve.
- Ran without a GPU, so it does not need one to start.
- Licensed Apache-2.0, as reported by its host.
What did not, or is not known
- Took 12 minutes to install, slower than the median of the 9 comparable projects Argusic has measured.
- Measured once so far. A single attempt shows it can run, not that it runs reliably.
Of the 10 agentic-ai projects Argusic has installed and timed, Vision-Agents was the 6th fastest to reach a running state, and 7 of 10 reached one at all.
What it is a reasonable choice for
- Trying it on a laptop or a small server: it reached a running state without a GPU.
Also tested, in the same area
Every one of these was installed and run by Argusic on a clean machine. Nothing appears here that was not tested.
Run history
Topics (from GitHub)
agentic-aiagentsaiai-agentsrealtimesttttsvideo-agentsvideo-aivision-aivoice-ai
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/vision-agents)Questions
- Does Vision-Agents run?
- Yes. Vision-Agents runs. Argusic installed and launched it on a clean machine in 12 minutes, hitting 3 errors on the way, and recorded the session.
- How did Argusic test Vision-Agents?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 902db86438aa. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test Vision-Agents?
- The run that produced this verdict cost $0.10: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does Vision-Agents take to install?
- 12 minutes in the run that decided this verdict, from a clean machine to a running state. That is one measured attempt, not an average.
- Does Vision-Agents need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing Vision-Agents?
- 3 things broke in the recorded run, and 3 were fixed without human help. Each one, and the time it cost, is listed on this page.
- How does Vision-Agents compare with the alternatives?
- Of the 10 agentic-ai projects Argusic has installed and timed, Vision-Agents was the 6th fastest to reach a running state, and 7 of 10 reached one at all.
- Where is the evidence for Vision-Agents?
- The recorded run is on this page, each linking to its full log and terminal recording, stored with a sha256 fingerprint so it cannot be quietly altered.