# beenuar/AiSOC

Open-source AI-powered Security Operations Center — alert fusion, purple-team drills, agent-assisted triage, MITRE ATT&CK investigation. MIT-licensed, self-hostable.

Repository: https://github.com/beenuar/AiSOC
Canonical: https://ross.abutalabs.com/products/aisoc
Homepage: https://tryaisoc.com
Language: Python
License: MIT
License Family: permissive
Topics: ai-security, alert-triage, cybersecurity, detection-engineering, incident-response, mitre-attack, open-source, purple-team, security-operations, self-hosted, siem, soar, soc, threat-detection, threat-intelligence, agentic-ai, clickhouse, langgraph, neo4j, investigation-ledger
Last push: 2026-08-24T06:14:35+00:00

## Health v2 (maintenance only)
Score: 80/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 99, release rhythm 96, longevity 8
- inputs: {"age_days": 123, "days_push": 9, "days_rel": 30, "gap_med": 8.0, "n_releases_24m": 9}
- flags: young
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2408, forks 254 (observed 2026-08-28T04:06:44.197761+00:00)

## What it is
AiSOC is an open-source, self-hostable AI-powered Security Operations Center that fuses alerts, performs agent-assisted triage, purple-team drills, and MITRE ATT&CK-aligned investigations with replayable agent traces. It includes a deterministic triage CLI, 70+ data connectors for SIEM/EDR/cloud/identity sources, and is MIT-licensed.

## Use cases
- triage security alerts with AI agents
- fuse and correlate alerts from SIEM and EDR
- investigate incidents mapped to MITRE ATT&CK
- run purple-team detection drills
- score alert batches to escalate/review/suppress verdicts
- self-host a SOC platform with replayable agent audit trails
- hunt threats with plain-language queries across connected sources

## When to choose
- you want an open-source, self-hostable alternative to commercial SIEM/SOAR triage
- your team needs agent-assisted alert triage with auditable, replayable reasoning
- you need integrations across Splunk, Sentinel, CrowdStrike, Defender, and cloud logs
- you want a deterministic CLI triage scorer without LLM keys

## When to avoid
- you need a fully managed multi-tenant MSSP platform with SLAs and compliance reports
- you require guaranteed vendor support and SOC 2/ISO attestations from the open-source edition
- your environment cannot run Python/ClickHouse/Neo4j self-hosted components

## Facets
- artifact type: application
- maturity: active
- function: security, monitoring, alerting, agent-framework, search-engine, analytics, self-hosted, cli
- domain: security, artificial-intelligence, monitoring, developer-tools
- platform: self-hosted, python, cli, cross-platform
- tags: soc, siem, soar, alert-triage, incident-response, mitre-attack, purple-team, threat-intelligence, detection-engineering, agentic-ai, clickhouse, neo4j, langgraph, ai-agents, docker, web-server

## Member repositories
- beenuar/AiSOC (main) score 80

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:44.197761+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T02:34:02.890597+00:00, confidence not recorded.
  - readme: https://github.com/beenuar/AiSOC (fetched 2026-08-28T04:06:44.197761+00:00, sha a50bf438ee13)
  - homepage: https://tryaisoc.com (fetched 2026-08-29T10:14:16.695160+00:00, sha 1cd5494290b0)
  - site_page: https://tryaisoc.com/about (fetched 2026-08-29T10:14:16.708151+00:00, sha 65114b0ae1ad)
  - site_page: https://tryaisoc.com/integrations (fetched 2026-08-29T10:14:16.704073+00:00, sha 91d9f06cddeb)
  - site_page: https://tryaisoc.com/pricing (fetched 2026-08-29T10:14:16.706116+00:00, sha 954eacc80e8a)
- Data as of 2026-08-30T08:39:29.467469+00:00.