Misaka-Agent
A multi-agent research system for the humanities and social sciences.
Runssource: GitHubPythonApache-2.0commit 3bcf7a33fb33
Python, Apache-2.0 licensed. The project labels itself: agent framework, ai agents, computational social science, digital humanities, history, humanities, literature review and llm.
Misaka-Agent runs. An Argusic agent installed it in 1 minute and hit 3 errors on a clean machine with no GPU, and the whole session was recorded.
MISAKA 0.18.11 installs and launches: --version prints 0.18.11, init creates a git project, the panel opens the setup wizard with fd and pdftotext present from the bundled archive, dm runs real turns that reply, and the test suite passes 4361 tests (the single remaining failure needs the optional ocrmypdf system package, which is absent without root).
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 93.3 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.
- test_pdf_ocr_routing.py::test_a_reread_put_off_and_then_answered_forgets_the_misses fails because it needs the optional ocrmypdf system package on PATH10 minutes
- fd and pdftotext system packages absent (no root); project bundles them in its prebuilt release archive10 minutes
- test_research_missing_session.py expected 'No model is available' but current code raises 'The Sister roster is empty; research tasks cannot be assigned.' first on resume with no Sisters/roster5 minutes
- Install time
- 1 minutes
- Cold machine to finish
- 22 minutes
- Errors hit and fixed
- 3 hit, 2 fixed with no human help
- How the result was proved
- uv run pytest -q returned 4361 passed, 1 failed, 13 skipped, 163 subtests; misaka --version returned 0.18.11; misaka dm last-order 'Hello, confirm you are running.' returned 'Confirmed, I am running and ready to assist.'; misaka update returned 'Up to date with main.'
- Model tokens used
- 145,906
- Exact commit tested
- 3bcf7a33fb33
- 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
Watch the session
The whole run, from a clean machine, at the speed it actually happened. Nothing is cut and nothing is sped up.
A recording of attempt 1, run , the attempt that decided the verdict above. The terminal recording it was made from is the evidence, stored with a sha256 fingerprint; the video is a rendering of it. Nothing loads from the video host until you press play.
The end of the recording
The last lines of the terminal session that decided this verdict, exactly as they were recorded.
- Launch verified: panel opens the setup wizard on the display; `misaka init` creates a project; `m… tokens used 145,906 All work is done. Here's my summary and the required result line. **What I did** - Installed `uv` (user-level, since system pip is PEP-668 managed and there's no root), then ran th… - Installed dev deps with `uv sync --group dev` and ran the suite: `4361 passed, 1 failed, 13 skipp… - Diagnosed both failures: - `test_research_missing_session.py` — a stale assertion: the code now raises `Sister roster is e… - `test_pdf_ocr_routing.py::test_a_reread_put_off_and_then_answered_forgets_the_misses` — environ… - Closed the `fd`/`pdftotext` gaps (system packages, no root) by using the project's prebuilt `misa… - Launch verified: panel opens the setup wizard on the display; `misaka init` creates a project; `m…
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.
- Installed in 1 minute, faster than the median of the 54 comparable projects Argusic has measured.
- Ran without a GPU, so it does not need one to start.
- Licensed Apache-2.0, as reported by its host.
What did not, or is not known
- Hit 3 errors during setup, 1 of which were not solved.
- Measured once so far. A single attempt shows it can run, not that it runs reliably.
Of the 55 agent-framework projects Argusic has installed and timed, Misaka-Agent was the 8th fastest to reach a running state, and 40 of 55 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.
- A quick evaluation: it was running 1 minutes after the clone.
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
Topics (from GitHub)
agent-frameworkai-agentscomputational-social-sciencedigital-humanitieshistoryhumanitiesliterature-reviewllmllm-agentmulti-agentmulti-agent-systemspythonqualitative-researchragresearch-assistantresearch-toolsocial-sciencessociology
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/misaka-agent)Questions
- Does Misaka-Agent run?
- Yes. Misaka-Agent runs. Argusic installed and launched it on a clean machine in 1 minutes, hitting 3 errors on the way, and recorded the session.
- How did Argusic test Misaka-Agent?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 3bcf7a33fb33. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test Misaka-Agent?
- The run that produced this verdict cost $0.16: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does Misaka-Agent take to install?
- 1 minute in the run that decided this verdict, from a clean machine to a running state. That is one measured attempt, not an average.
- Does Misaka-Agent need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing Misaka-Agent?
- 3 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 Misaka-Agent compare with the alternatives?
- Of the 55 agent-framework projects Argusic has installed and timed, Misaka-Agent was the 8th fastest to reach a running state, and 40 of 55 reached one at all.
- Where is the evidence for Misaka-Agent?
- 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.