agno
Build, run, and manage agent platforms.
Runs with mockssource: GitHubhomepagePythonApache-2.0commit 660c0ee8c5cc
Python, Apache-2.0 licensed. The project labels itself: agents, ai, ai agents, developer tools and python.
agno runs, with stand-ins for the services it depends on. An Argusic agent installed it in 8 minutes and hit 6 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
Agno v3.0.11 installs and builds successfully in the dev venv. The framework core (Agent, Team, Workflow, tools) and 1595 unit tests pass. 109 unrelated test files show collection errors due to missing optional SDK packages. The format and ruff validation pipelines pass cleanly.
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.
- Disk space insufficient to install 'agno[tests]' extra (torch/triton ~5GB)2 minutes
- Missing google-api-python-client for gdrive mime types test (collection error)1 minute
- Missing pymongo for async mongo DB test (collection error)1 minute
- 22 tool test files failed collection (cassio, oxylabs, crawl4ai, chonkie, cartesia, etc. not installed)1 minute
- 12 workflow test_run_logging tests fail (assert 0 == 1 - pre-existing, not caused by install)
- 109 total collection errors across vectordb, models, reader, knowledge, db, os, fs, context test dirs
- Install time
- 8 minutes
- Cold machine to finish
- 43 minutes
- Errors hit and fixed
- 6 hit, 6 fixed with no human help
- How the result was proved
- pytest libs/agno/tests/unit/agent/ -q --tb=no returned 716 passed; pytest libs/agno/tests/unit/memory/ -q --tb=no returned 75 passed; pytest libs/agno/tests/unit/team/ returned 235 passed; pytest on 18 core tool test files returned 569 passed; total ~1595 verified passing. ruff check libs/agno - All checks passed. ./scripts/format.sh - 2481 files left unchanged. Core API imports (Agent, Team, Workflow, OpenAIResponses, CalculatorTools, SqliteDb) all verified
- Model tokens used
- 667,349
- Exact commit tested
- 660c0ee8c5cc
- 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
- 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.
/bin/sh -lc 'SECONDS=0 # Time since start - not tracked exactly. Let me estimate from the session. echo "Script started at unknown time" echo "Current time:" && date +%s' in /work/repo succeeded in 0ms: Script started at unknown time Current time: 1790333898 Let me now compile the final report with all findings. tokens used 667,349 Let me now compile the final report with all findings.
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 6 errors without a human stepping in, which says the failures are documented well enough to solve.
- Licensed Apache-2.0, 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 8 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 agents projects Argusic has installed and timed, agno was the 8th fastest to reach a running state, and 6 of 10 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 | 0.15 |
Topics (from GitHub)
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/agno)Questions
- Does agno run?
- agno runs, with mocks standing in for external services. Argusic installed and launched it on a clean machine in 8 minutes, hitting 6 errors on the way, and recorded the session.
- How did Argusic test agno?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 660c0ee8c5cc. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test agno?
- The run that produced this verdict cost $0.15: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does agno take to install?
- 8 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 agno need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing agno?
- 6 things broke in the recorded run, and 6 were fixed without human help. Each one, and the time it cost, is listed on this page.
- How does agno compare with the alternatives?
- Of the 10 agents projects Argusic has installed and timed, agno was the 8th fastest to reach a running state, and 6 of 10 reached one at all.
- Where is the evidence for agno?
- 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.