Credentials. The admin token and API keys control the whole audit store; keep them out of commits.
Who it is forA team running AI agents in production, especially in regulated settings, that needs a durable record of what each agent did and why.
The problemOrdinary logs can be edited or lost, and they do not link a tool call back to the message and model response that caused it.
The outcomeA local ZizkaDB with a dashboard on port 3001 and API on 8000, where every event is checksummed and chained, so you can prove nothing was edited or removed.
What you need first
- Docker
- Python or TypeScript SDK for integration
Steps
- Run locally:
docker run -d --name zizkadb -e ENV=development -p 127.0.0.1:8000:8000 -p 127.0.0.1:3001:3001 -v zizkadb_data:/data ghcr.io/zizka-ai-sl/zizkadb - Open the dashboard at localhost:3001; development mode signs you in with one click
- Install the SDK:
pip install zizkadb-sdk - Log events from your agent with db.log, passing parent_id so events link into a chain
- For a server, copy .env.example and run
bash scripts/init-secrets.sh, then set ENV=production, a new DEV_API_KEY and SELFHOST_ADMIN_TOKEN - Check integrity with db.verify_chain for an agent
Prompt for your agent
Add ZizkaDB logging to my agent in <file>: log user_message, llm_response and tool_call events with parent_id links using zizkadb-sdk against http://localhost:8000. Then show me how to verify the chain for this agent.
Caveat. In production the API refuses to start if DEV_API_KEY is left at its default.
Use this in your AI agent
Ask your agent
Using the Deduped MCP, get the setup steps for ZIZKA-AI-SL/ZizkaDB and "Self-host a tamper-evident audit log for your agents"
Add Deduped to Claude Code once
claude mcp add --transport http deduped https://dedupedai.com/mcp
Every Monday: the 5 hottest repos and exactly how to use them. Free, one email a week, unsubscribe anytime.
Get them freeShare: X LinkedIn Hacker News Email Copy link
Third-party repos we don't own. AI-written use cases can be wrong. Disclaimer