Deploy Now

Stars

1,251

Forks

90

Watchers

96

Developer links

Argus Agentic SOC

Every incident ticket in Argus, an open-source security operations center, comes with its own AI analyst, ready to explain the alert and suggest what to do next. Scheduled pipeline tasks pull alerts in from Elasticsearch and other sources, and tickets carry severity, owner, and SLA clocks that measure MTTA, MTTI, MTTC, and MTTR with color-coded buckets. Decision buttons walk each case from New through Acknowledged, Triaged, and Contained to Resolved. A War Room gathers analyst notes, system logs, files, pasted images, and extracted indicators. One click on Run AI Assistant returns a plain-language alert explanation, a suggested risk level, finished tasks, and next steps; scoped chat plus @ai and @playbook mentions keep the conversation inside the ticket. Built-in MCP tools look up CMDB assets, find similar past cases, and extract IPs, domains, and hashes, and you can register your own MCP servers and SKILL.md skills with usage monitors. A drag-and-drop workflow editor fires playbooks on new alerts, ticket changes, cron schedules, or webhooks. Detection engineers import Sigma rules from GitHub URLs or files, map fields to Splunk and Elastic ECS names, and review a publish history. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. Apache-2.0 licensed.

Argus Agentic SOC
Argus Agentic SOC
Argus Agentic SOC
Argus Agentic SOC
Argus Agentic SOC

Benefits

  • One-click AI analysis per ticket
  • Run AI Assistant reads a ticket's alerts, observables, and history, then writes a plain-language explanation, a risk level with rationale, completed tasks, and recommended next steps for the analyst.
  • Measured response times with SLA clocks
  • Automatic MTTA, MTTI, MTTC, and MTTR calculation uses ticket timestamps, a Pending toggle pauses the clocks, and green, yellow, and red buckets show compliance in the list view.
  • Playbooks without writing code
  • A drag-and-drop editor builds workflows with condition branches and action nodes, triggered by new alerts, ticket events, cron schedules, webhooks, or ticket labels, with step-by-step execution history.
  • Bring your own model and tools
  • Point the assistant at any OpenAI-compatible endpoint, register external MCP servers, and add SKILL.md skills, while built-in tools query tickets, CMDB assets, and indicators on your own server.

Features

  • Sigma Detection Library
  • Import Sigma rules from GitHub URLs, files, or zipped folders, map Sigma fields to Splunk and Elastic ECS names, and audit every publish action in a history table.
  • Ticket War Room
  • A per-incident workspace collects analyst work logs, system handle logs, uploaded files, pasted images, and extracted observables such as IPs, domains, and hashes.
  • MCP Tool Gateway
  • A JSON-RPC gateway exposes ticket_context, ticket_search_similar_cases, cmdb_asset_lookup, and observables_extract plus external servers, with a monitor showing call counts and success rate.
  • Alert Ingestion Pipeline
  • Orchestrator tasks import Elasticsearch alerts on cron schedules, and the platform links them with CMDB asset context for dashboards, searchable alert views, and analyst triage.
  • Visual SOAR Workflows
  • A canvas with Start, Condition, Action, and End nodes builds playbooks that publish to Prefect and bind to ticket labels using AND or OR logic.

Apps Similar to Argus Agentic SOC