PraisonAI
PraisonAI 🦞, Hire a 24/7 AI Workforce. Stop writing boilerplate and start shipping autonomous self-improving agents that research, plan, code, and execute tasks. Deployed in 5 lines of code with built-in memory, RAG, and support for 100+ LLMs.
Runs with mockssource: GitHubhomepagePythonMITcommit 5c7d76d72d4a
Python, MIT licensed. The project labels itself: agents, ai, ai agent framework, ai agent sdk, ai agents, ai agents framework, ai agents sdk and ai framwork.
PraisonAI runs, with stand-ins for the services it depends on. An Argusic agent installed it in 18 minutes and hit 5 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
Both praisonaiagents and PraisonAI packages install and import successfully. Agent creation works. All core agent unit tests pass (480/480). LLM token tracking race condition fixed with ContextVar. LLM class supports __deepcopy__ for agent cloning. Knowledge tests pass with chonkie installed. 193/194 LLM tests pass. The TypeScript SDK has a pre-existing missing firecrawl-js dependency.
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.
- current_agent_name was a plain shared attribute on LLM, causing race conditions when concurrent agents shared one LLM instance3 minutes
- test_agent_clone.py expected _current_agent_name_var ContextVar that doesn't exist on LLM1 minute
- praisonai-sandbox not installed - 5 sandbox tests fail with ImportError
- TypeScript SDK build fails - @mendable/firecrawl-js dependency missing
- Rate limiter retry test fails - resolve_failover_decision retries unknown errors up to 2 times
- Install time
- 18 minutes
- Cold machine to finish
- 32 minutes
- Errors hit and fixed
- 5 hit, 5 fixed with no human help
- How the result was proved
- cd src/praisonai-agents && python -m pytest tests/unit/agent/ -q = 480 passed 17 skipped; tests/unit/llm/ -q = 193 passed 1 skipped; tests/unit/tools/ -q = 939 passed 3 skipped; tests/unit/workflows/ -q = 1421 passed 2 skipped; tests/unit/task/ -q = 567 passed; tests/unit/rag/ -q = 669 passed; tests/unit/knowledge/ -q = 160 passed 10 skipped; python -c 'from praisonaiagents import Agent; agent = Agent(name="Test", instructions="test", llm="gpt-4o-mini")' = OK
- Model tokens used
- 742,696
- 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
- 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.
tests/unit/gateway/test_recipe_failure_reply.py . [ 29%] tests/unit/goal/test_goal.py ................. [ 30%] tests/unit/goal/test_goal_loop.py ........................ [ 30%] tests/unit/hooks/test_hooks.py ......................................... [ 31%] ... exec /bin/sh -lc 'cd /work/repo/src/praisonai-agents && timeout 90 /home/runner/venv/bin/python -m pytes… Now I have enough data for a complete summary. Let me compile the ARGUSIC_RESULT: 2026-09-27T22:47:23.767772Z ERROR codex_core::session: failed to record rollout items: thread 01a0e… tokens used 742,696 Now I have enough data for a complete summary. Let me compile the ARGUSIC_RESULT:
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 5 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 16 comparable projects Argusic has measured.
- Measured once so far. A single attempt shows it can run, not that it runs reliably.
Of the 17 agents projects Argusic has installed and timed, PraisonAI was the 15th fastest to reach a running state, and 10 of 17 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 | 0.19 |
Topics (from GitHub)
agentsaiai-agent-frameworkai-agent-sdkai-agentsai-agents-frameworkai-agents-sdkai-framworkaiagentaiagentframeworkaiagentsaiagentsframeworkframeworkhermeshermes-agentmulti-agentmulti-agent-systemmulti-agentsmulti-ai-agentsopenclaw
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?
- PraisonAI runs, with mocks standing in for external services. Argusic installed and launched it on a clean machine in 18 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. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test PraisonAI?
- The run that produced this verdict cost $0.19: 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?
- 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 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 17 agents projects Argusic has installed and timed, PraisonAI was the 15th fastest to reach a running state, and 10 of 17 reached one at all.
- Where is the evidence for PraisonAI?
- 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.