Director
AI video agents framework for next-gen video interactions and workflows.
Runs with mockssource: GitHubhomepagePythonMITcommit 70e0b3dfdf59
Python, MIT licensed. The project labels itself: agent, agent framework, ai agents, framework, llm, openai, rag and search.
Director runs, with stand-ins for the services it depends on. An Argusic agent installed it in 18 minutes and hit 2 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
Backend serves all 25 agent listings, config check, session CRUD, and collection endpoints via a mock VideoDB server. Frontend dev server builds and serves the Vue app. Both run simultaneously on :8000 and :8080.
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 92 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.
- get_default_llm() falls through to VideoDBProxy which validates VIDEO_DB_API_KEY - empty key crashes /agent/ endpoint5 minutes
- VideoDB connect() requires a live API server for collection/video operations - without it, /videodb/ endpoints crash3 minutes
- Install time
- 18 minutes
- Cold machine to finish
- 16 minutes
- Errors hit and fixed
- 2 hit, 2 fixed with no human help
- Model tokens used
- 129,539
- Exact commit tested
- 70e0b3dfdf59
- 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.
- How the result was proved
- runs before 2026-09-07 did not record the command used to check the result
- 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
- Behaviour against real services
- this run was verified against stand-in services only
The end of the recording
The last lines of the terminal session that decided this verdict, exactly as they were recorded.
1 collections DONE exec /bin/sh -lc '# Clean up all remaining processes pkill -f "python director/entrypoint" 2>/dev/null || true pkill -f videodb_mock 2>/dev/null || true echo "done"' in /work/repo exited 143 in 0ms: Cool, everything is working. Here's the concise final answer. tokens used 129,539 Cool, everything is working. Here's the concise final answer.
Replay 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
- Recovered from all 2 errors without a human stepping in, which says the failures are documented well enough to solve.
- Licensed MIT, as reported by its host.
What did not, or is not known
- Only reached a running state against stand-in services, so nothing here proves it works against the real ones.
- Took 18 minutes to install, slower than the median of the 32 comparable projects Argusic has measured.
- Measured once so far. A single attempt shows it can run, not that it runs reliably.
Of the 33 agent projects Argusic has installed and timed, Director was the 28th fastest to reach a running state, and 25 of 33 reached one at all.
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
| tested by | attempt | outcome | score | cost USD | when |
|---|---|---|---|---|---|
| Argusic Runner | 1/3 | Runs with mocks | 92.00 | 0.10 |
Topics (from GitHub)
agentagent-frameworkai-agentsframeworkllmopenairagsearchtext-to-videovideo-editingvideo-processingvideodb
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/director)Questions
- Does Director run?
- Director runs, with mocks standing in for external services. Argusic installed and launched it on a clean machine in 18 minutes, hitting 2 errors on the way, and recorded the session.
- How did Argusic test Director?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 70e0b3dfdf59. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test Director?
- 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 Director take to install?
- 18 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 Director need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing Director?
- 2 things broke in the recorded run, and 2 were fixed without human help. Each one, and the time it cost, is listed on this page.
- How does Director compare with the alternatives?
- Of the 33 agent projects Argusic has installed and timed, Director was the 28th fastest to reach a running state, and 25 of 33 reached one at all.
- Where is the evidence for Director?
- 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.