{
 "schema_version": 1,
 "generated": "2026-10-26",
 "repo": "ZIZKA-AI-SL/ZizkaDB",
 "name": "ZizkaDB",
 "owner": "ZIZKA-AI-SL",
 "slug": "zizka-ai-sl-zizkadb",
 "github": "https://github.com/ZIZKA-AI-SL/ZizkaDB",
 "what": "ZizkaDB is an audit trail database for AI agents with tamper-evident, checksum-backed decision logs, session replay, time-travel debugging, drift detection, an MCP server and Python and TypeScript SDKs, aimed at EU AI Act Article 12 record-keeping.",
 "why": "143 stars, talked about in 2 AI sources we track",
 "language": "Python",
 "requirements": [
  "Docker",
  "Python or TypeScript SDK for integration"
 ],
 "audience_note": "Teams running AI agents in production who need to explain and audit what an agent did and why.",
 "risk": "none",
 "section": "earlier",
 "weekly_rank": null,
 "category": "Security and science",
 "url": "https://dedupedai.com/use-cases/zizka-ai-sl-zizkadb/",
 "use_case_count": 3,
 "use_cases": [
  {
   "id": "zizka-ai-sl-zizkadb--self-host-agent-audit-trail",
   "title": "Self-host a tamper-evident audit log for your agents",
   "best": true,
   "url": "https://dedupedai.com/use-cases/zizka-ai-sl-zizkadb/self-host-agent-audit-trail/",
   "json": "https://dedupedai.com/use-cases/u/zizka-ai-sl-zizkadb/self-host-agent-audit-trail.json"
  },
  {
   "id": "zizka-ai-sl-zizkadb--replay-agent-session-to-debug",
   "title": "Trace why your agent made a bad tool call",
   "best": false,
   "url": "https://dedupedai.com/use-cases/zizka-ai-sl-zizkadb/replay-agent-session-to-debug/",
   "json": "https://dedupedai.com/use-cases/u/zizka-ai-sl-zizkadb/replay-agent-session-to-debug.json"
  },
  {
   "id": "zizka-ai-sl-zizkadb--detect-drift-in-agent-behavior",
   "title": "Catch drift in agent behaviour and ask about it over MCP",
   "best": false,
   "url": "https://dedupedai.com/use-cases/zizka-ai-sl-zizkadb/detect-drift-in-agent-behavior/",
   "json": "https://dedupedai.com/use-cases/u/zizka-ai-sl-zizkadb/detect-drift-in-agent-behavior.json"
  }
 ],
 "disclaimer": "Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk."
}