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.
Runs with mockssource: 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, with stand-ins for the services it depends on. An Argusic agent installed it in 28 minutes and hit 5 errors on a clean machine with no GPU, and the whole session was recorded.
All 7 Python packages install and their 249 tests pass. aisoc-sandbox runs a 4-step investigation offline in 1.3s. aisoc-lite CLI triages 200 demo alerts and translates Sigma rules. Docker is unavailable so the full production stack (make up -> make smoke) cannot run.
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 88 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.
- Python PEP 668 blocks system-wide pip install - needed venv workaround2 minutes
- pnpm not pre-installed (npm -g install needed)1 minute
- Docker is not installed (no root access) - cannot run make up / make smoke / full stack
- Node.js v18.19.1 below >=20.0.0 requirement - vitest test runner fails for TS packages (aisoc-lite, report-card, sdk-ts)
- aisoc-ueba service hatchling metadata generation fails (missing packages directive)
- Install time
- 28 minutes
- Cold machine to finish
- 11 minutes
- Errors hit and fixed
- 5 hit, 4 fixed with no human help
- How the result was proved
- aisoc-lite CLI triaged 200 demo alerts (12 escalate 171 suppress 17 review); aisoc-sandbox demo printed 4-step investigation ledger; all 7 Python test suites passed (249 total); 6 TS packages built; 2 CLI tools reported version numbers
- Model tokens used
- 100,834
- 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
- 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.
1. **Docker not available** — No fix possible (no root). Blocks `make up`, `make smoke`, `make doct…
2. **PEP 668 system-pip block** — Fixed by using a venv at `/tmp/venv`.
3. **pnpm not on PATH** — Fixed via `npm install -g pnpm --prefix $HOME/.local`.
4. **Node.js v18.19.1 is below the `>=20.0.0` engine requirement** for aisoc-lite and other package…
5. **aisoc-ueba service wouldn't pip install** — Hatchling metadata generation failed (missing `pac…
6. **aisoc-ai-sdk first pip install succeeded but import failed** — Re-installing from correct path…
exec
/bin/sh -lc "echo '{\"install_succeeded\": true, \"launch_succeeded\": true, \"install_minutes\": 2…
succeeded in 0ms:
{"install_succeeded": true, "launch_succeeded": true, "install_minutes": 28, "errors": [{"msg": "Do…
tokens used
100,834Replay 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
- 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 28 minutes to install, slower than the median of the 12 comparable projects Argusic has measured.
- Hit 5 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 13 agentic-ai projects Argusic has installed and timed, AiSOC was the 12th fastest to reach a running state, and 9 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 | 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?
- AiSOC runs, with mocks standing in for external services. Argusic installed and launched it on a clean machine in 28 minutes, hitting 5 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. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test AiSOC?
- The run that produced this verdict cost $0.15: 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?
- 28 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?
- 5 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 13 agentic-ai projects Argusic has installed and timed, AiSOC was the 12th fastest to reach a running state, and 9 of 13 reached one at all.
- Where is the evidence for AiSOC?
- 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.