MiroFlow
🏆 Top-1 on 5+ benchmarks | Web UI | Supports MiroThinker, Claude, Kimi, OpenAI
Runs with mockssource: GitHubhomepagePythonApache-2.0commit fca7b4a7fda3
Python, Apache-2.0 licensed. The project labels itself: agent framework, agents, browsecomp, claude, deep research, futurex, gaia and gpt 5.
MiroFlow runs, with stand-ins for the services it depends on. An Argusic agent installed it in 0.1 minutes and hit no errors on a clean machine with no GPU, and the whole session was recorded.
MiroFlow agent pipeline runs end-to-end with a mock OpenRouter API: uv sync installs all deps, the agent loads config, initializes the LLM client, calls the API, processes tool-using context, and extracts a boxed final answer.
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.
- Install time
- under a minute
- Cold machine to finish
- 10 minutes
- Errors hit and fixed
- 0 hit, 0 fixed with no human help
- How the result was proved
- uv sync installed 135 packages without error; .venv/bin/python main.py trace --config_file_name=agent_quickstart_reading --task=... completed with final boxed answer 'Congo Democratic Republic' extracted successfully
- Model tokens used
- 88,267
- Exact commit tested
- fca7b4a7fda3
- 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.
- **Real credentials**: Only needed if calling real Argusic/Argusic APIs. The mock sufficed to exer…
tokens used
88,267
Everything works. The full end-to-end pipeline completed successfully with the mock Argusic server.…
Here's the summary:
- **Install**: `uv sync` completed in ~5s, all 135 packages installed successfully. âś…
- **Mock server**: A minimal Argusic-compatible HTTP server was stood up. âś…
- **Trace command**: The full agent pipeline ran end-to-end: config loaded → LLM client initialized…
- **Result**: `\boxed{Congo Democratic Republic}` was correctly extracted. âś…
- **Real credentials**: Only needed if calling real Argusic/Argusic APIs. The mock sufficed to exer…
2026-10-01T19:25:59.021990Z ERROR codex_core::session: failed to record rollout items: thread 01a0f…
2026-10-01T19:25:59.023898Z ERROR codex_core::session: failed to record rollout items: thread 01a0f…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
- Installed in 0.1 minutes, faster than the median of the 12 comparable projects Argusic has measured.
- Nothing broke on the way: zero errors between clone and running.
- 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.
- Measured once so far. A single attempt shows it can run, not that it runs reliably.
Of the 13 agent-framework projects Argusic has installed and timed, MiroFlow was the 1st fastest to reach a running state, and 7 of 13 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 | 0.06 |
Topics (from GitHub)
agent-frameworkagentsbrowsecompclaudedeep-researchfuturexgaiagpt-5hleresearch-agentxbench
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/miroflow)Questions
- Does MiroFlow run?
- MiroFlow runs, with mocks standing in for external services. Argusic installed and launched it on a clean machine in 0 minutes, hitting 0 errors on the way, and recorded the session.
- How did Argusic test MiroFlow?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit fca7b4a7fda3. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test MiroFlow?
- The run that produced this verdict cost $0.06: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does MiroFlow take to install?
- 0.1 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 MiroFlow need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing MiroFlow?
- Nothing did, in the recorded run: zero errors between clone and running.
- How does MiroFlow compare with the alternatives?
- Of the 13 agent-framework projects Argusic has installed and timed, MiroFlow was the 1st fastest to reach a running state, and 7 of 13 reached one at all.
- Where is the evidence for MiroFlow?
- 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.