PraisonAI
Private AI agents for highly regulated teams, and for anyone who wants AI on their own computer. Open-source Python agent framework that runs fully offline.
Runssource: GitHubhomepagePythonMITcommit 5c7d76d72d4a
Python, MIT licensed. The project labels itself: agents, ai, ai agent framework, ai agent sdk, ai agents, ai agents sdk, aiagents and air gapped.
PraisonAI runs. An Argusic agent installed it in 30 minutes and hit 5 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
PraisonAI Python SDK core (praisonaiagents v1.7.8) and wrapper (PraisonAI v4.7.10) installed from source with all 9 sub-packages, 898 Python unit tests pass across both packages, CLI responds with version 4.7.10, TS SDK (v1.7.4) builds and 146/158 test suites pass (2521/2659 tests).
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 96 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.
- TS SDK npm build failed due to missing @mendable/firecrawl-js dependency3 minutes
- Externally-managed Python environment blocked system-wide pip install2 minutes
- LLM-related tests required litellm (optional dependency)2 minutes
- pytest and pytest-asyncio not pre-installed in venv1 minute
- 12 TS test suites failed (40/2659 tests) - pre-existing test mocking issues in UUID crypto and integration/smoke tests
- Install time
- 30 minutes
- Cold machine to finish
- 26 minutes
- Errors hit and fixed
- 5 hit, 5 fixed with no human help
- How the result was proved
- pytest exited 0: 885 passed, 2 skipped (praisonaiagents core SDK unit tests); 13 passed, 17 skipped (praisonai wrapper tests); praisonai --version returned PraisonAI version 4.7.10; npm run build succeeded; npm test: 146/158 suites passed, 2521/2659 tests passed
- Model tokens used
- 126,649
- Exact commit tested
- 5c7d76d72d4a
- 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.
=== TS SDK build === > [email protected] build:esm > tsc -p tsconfig.esm.json && node scripts/esm-shim.js esm-shim: processed 389 files in dist/esm Now I have all the information needed. Let me compile the final report. exec /bin/sh -lc "echo '{\"install_succeeded\": true, \"launch_succeeded\": true, \"install_minutes\": 3… succeeded in 0ms: {"install_succeeded": true, "launch_succeeded": true, "install_minutes": 30, "errors": [{"msg": "Ex… 2026-11-05T00:41:15.931463Z ERROR codex_core::session: failed to record rollout items: thread 01a1a… tokens used 126,649
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
- Reached a running state on a clean machine, with the session recorded.
- Recovered from all 5 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 MIT, as reported by its host.
- Measured 2 times, so the result is not a one-off.
What did not, or is not known
- Took 30 minutes to install, slower than the median of the 40 comparable projects Argusic has measured.
Of the 41 agents projects Argusic has installed and timed, PraisonAI was the 36th fastest to reach a running state, and 29 of 41 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
| tested by | attempt | outcome | score | cost USD | when |
|---|---|---|---|---|---|
| Argusic Runner | 2/3 | Runs | 100.00 | 0.36 | |
| Argusic Runner | 1/3 | Runs with mocks | 92.00 | 0.19 |
Topics (from GitHub)
agentsaiai-agent-frameworkai-agent-sdkai-agentsai-agents-sdkaiagentsair-gappedframeworkllmmulti-agentmulti-agent-systemmulti-agentson-premiseopenclawprivate-aipythonregulated-industriesself-hosted
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/praisonai)Questions
- Does PraisonAI run?
- Yes. PraisonAI runs. Argusic installed and launched it on a clean machine in 30 minutes, hitting 5 errors on the way, and recorded the session.
- How did Argusic test PraisonAI?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 5c7d76d72d4a. 2 attempts are recorded, and the full method is on the methodology page.
- What did it cost to test PraisonAI?
- The run that produced this verdict cost $0.36: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does PraisonAI take to install?
- 30 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 PraisonAI need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing PraisonAI?
- 5 things broke in the recorded run, and 5 were fixed without human help. Each one, and the time it cost, is listed on this page.
- How does PraisonAI compare with the alternatives?
- Of the 41 agents projects Argusic has installed and timed, PraisonAI was the 36th fastest to reach a running state, and 29 of 41 reached one at all.
- Where is the evidence for PraisonAI?
- All 2 recorded runs are on this page, each linking to its full log and terminal recording, stored with a sha256 fingerprint so it cannot be quietly altered.