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.
Python agentic-aiai-securityalert-triageblue-teamcybersecuritydetection-engineeringincident-responselanggraphllm-agentsmcpmitre-attackmodel-context-protocolpurple-teamsecurity-operationsself-hostedsiemsoarsocthreat-detectionthreat-intelligence
fix(docs): repair broken benchmark scoreboard link and anchor
Beenu Arora4e5c44141c50
diff --git a/apps/docs/docs/benchmark.md b/apps/docs/docs/benchmark.mdindex 9eb6cb852..2dad4e85a 100644--- a/apps/docs/docs/benchmark.md+++ b/apps/docs/docs/benchmark.md@@ -258,7 +258,7 @@ This catches a broken templating pipeline (e.g. someone removes the MITREreferences from the synthesizer, or the rubric stops matching) — it is**not** a grade of LLM-written response plans.-### 5. Synthetic telemetry corpus — `Schema and coverage gate`+### 5. Synthetic telemetry corpus — `Schema and coverage gate` {#5-synthetic-telemetry-corpus}**Source:** [`services/agents/tests/test_synthetic_telemetry.py`](https://github.com/beenuar/AiSOC/blob/main/services/agents/tests/test_synthetic_telemetry.py)· **Output:** [`synthetic_telemetry.jsonl`](https://github.com/beenuar/AiSOC/blob/main/services/agents/tests/eval_data/synthetic_telemetry.jsonl)@@ -368,7 +368,7 @@ python3 scripts/run_evals.py --json --out report.jsonSubmissions go through a structured GitHub issue template([`.github/ISSUE_TEMPLATE/benchmark_submission.yml`](https://github.com/beenuar/AiSOC/blob/main/.github/ISSUE_TEMPLATE/benchmark_submission.yml)).-Accepted entries are rendered on the [benchmark scoreboard](/benchmark) in the+Accepted entries are rendered on the [benchmark scoreboard](https://tryaisoc.com/benchmark) in theweb console. Submission rules:1. **Same fixed dataset** — run against the deterministic 200-incident dataset on the commit you submit. No private fixtures.