AiSOC
Open-source AI Security Operations Center: alert fusion, LLM-agent triage, MITRE ATT&CK investigation, and a replayable decision ledger for every agent step. Self-hostable, runs with no API keys, MIT licensed. Ships an MCP server for Claude, Cursor and Continue.
Runssource: GitHubhomepagePythonMITcommit f0e8fec9db8e
Python, MIT licensed. The project labels itself: agentic ai, ai security, alert triage, blue team, cybersecurity, detection engineering, incident response and langgraph.
AiSOC runs. An Argusic agent installed it in 31 minutes and hit 4 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
6423 tests pass across all 7 Python services (api, agents, fusion, actions, connectors, threatintel, ueba). One code fix: _lucene_match in services/api/app/services/rule_engine.py now handles pySigma wildcard patterns. Three missing dev deps installed (aiosqlite, cryptography, respx). Docker is unavailable so make up/smoke cannot proceed; for end-to-end verification Docker Compose v2 is required.
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 94 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.
- _lucene_match in rule_engine.py doesn't handle wildcards from pySigma5 minutes
- Missing aiosqlite dependency in API service1 minute
- Missing cryptography dependency in fusion service1 minute
- Missing respx dependency in actions service1 minute
- Install time
- 31 minutes
- Cold machine to finish
- 14 minutes
- Errors hit and fixed
- 4 hit, 4 fixed with no human help
- How the result was proved
- cd services/<name> && poetry run python -m pytest tests/ -q for each of 7 services; all passed
- Model tokens used
- 132,126
- Exact commit tested
- f0e8fec9db8e
- 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 2, 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.
"license": "MIT",
"main": "./dist/index.js",
"types": "./dist/index.d.ts",
"exports": {
".": {
"types": "./dist/index.d.ts",
All 7 Python services pass their test suites. Here's the final summary:
**ARGUSIC_RESULT:** {"install_succeeded": true, "launch_succeeded": true, "install_minutes": 31, "e…
tokens used
132,126
All 7 Python services pass their test suites. Here's the final summary:
**ARGUSIC_RESULT:** {"install_succeeded": true, "launch_succeeded": true, "install_minutes": 31, "e…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 4 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 31 minutes to install, slower than the median of the 38 comparable projects Argusic has measured.
Of the 39 agentic-ai projects Argusic has installed and timed, AiSOC was the 37th fastest to reach a running state, and 28 of 39 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 | 0.38 | |
| Argusic Runner | 1/3 | Runs with mocks | 88.00 | 0.15 |
Topics (from GitHub)
agentic-aiai-securityalert-triageblue-teamcybersecuritydetection-engineeringincident-responselanggraphllm-agentsmcpmitre-attackmodel-context-protocolpurple-teamsecurity-operationsself-hostedsiemsoarsocthreat-detectionthreat-intelligence
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/aisoc)Questions
- Does AiSOC run?
- Yes. AiSOC runs. Argusic installed and launched it on a clean machine in 31 minutes, hitting 4 errors on the way, and recorded the session.
- How did Argusic test AiSOC?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit f0e8fec9db8e. 2 attempts are recorded, and the full method is on the methodology page.
- What did it cost to test AiSOC?
- The run that produced this verdict cost $0.38: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does AiSOC take to install?
- 31 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 AiSOC need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing AiSOC?
- 4 things broke in the recorded run, and 4 were fixed without human help. Each one, and the time it cost, is listed on this page.
- How does AiSOC compare with the alternatives?
- Of the 39 agentic-ai projects Argusic has installed and timed, AiSOC was the 37th fastest to reach a running state, and 28 of 39 reached one at all.
- Where is the evidence for AiSOC?
- 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.