How to use ZizkaDB: what you can do with it

3 use cases

• Self-host a tamper-evident audit log for your agents

  Run ZizkaDB in Docker and log your agent's events through the Python or TypeScript SDK into a hash-chained record you can verify and query.

  • REPO ZIZKA-AI-SL/ZizkaDB
  • Claude Code
  • Codex
  • Cursor
  • Security and science
  • Intermediate
  View prompt

  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.

  Share Email me this

• Trace why your agent made a bad tool call

  Use ZizkaDB's causal chain, session replay and time travel to walk back from a wrong tool call to the message or context that caused it.

  • REPO ZIZKA-AI-SL/ZizkaDB
  • Claude Code
  • Codex
  • Cursor
  • Security and science
  • Intermediate
  View prompt

  Using ZizkaDB, explain why <agent> called <tool> in session <id>: print the db.why chain for that event, rebuild what the agent knew with db.at at that time, and point to the step where the context was wrong.

  Share Email me this

• Catch drift in agent behaviour and ask about it over MCP

  Use ZizkaDB's baseline to flag when an agent starts behaving differently from its history, and query the record from Cursor or Claude through its MCP server.

  • REPO ZIZKA-AI-SL/ZizkaDB
  • Cursor
  • Claude Code
  • Security and science
  • Intermediate
  View prompt

  Connect the ZizkaDB MCP server (uvx zizkadb-mcp, ZIZKADB_HOST=http://localhost:8000). Compare <agent>'s behaviour before and after <date of model change> using its baseline, and list the sessions that drifted most with one sentence each on what changed.

  Share Email me this

Quick start with ZizkaDB

1. Check you have what it needs: Docker; Python or TypeScript SDK for integration.
2. Open ZIZKA-AI-SL/ZizkaDB on GitHub and read the README and license.
3. 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
4. Open the dashboard at localhost:3001; development mode signs you in with one click
5. Install the SDK: pip install zizkadb-sdk
6. Log events from your agent with db.log, passing parent_id so events link into a chain

These steps come from our top use case, Self-host a tamper-evident audit log for your agents, which also has a copy-paste agent prompt.

Using the Deduped MCP, get the setup steps for ZIZKA-AI-SL/ZizkaDB

claude mcp add --transport http deduped https://dedupedai.com/mcp

ZizkaDB alternatives · Best AI repos for Security and science

About this repo

• Who it is forTeams running AI agents in production who need to explain and audit what an agent did and why.
• Why it is hot143 stars, talked about in 2 AI sources we track
• LanguagePython
• Sourcegithub.com/ZIZKA-AI-SL/ZizkaDB · Back to Hot repos

Requirements

• Docker
• Python or TypeScript SDK for integration

Related repos

• #7 this week REPO cloudflare/security-audit-skill Security Audit Skill A coding-agent skill that runs multi-phase security audits on a codebase and writes machine-readable, independently verified findings.
• Trended earlier REPO vxcontrol/pentagi PentAGI PentAGI is an open-source, self-hosted multi-agent system for autonomous penetration testing, for authorized testing only. You describe a target and goal in plain language; specialized agents plan the work, run 20+ tools such as nmap, Metasploit and sqlmap inside an isolated Docker sandbox, keep what they learn in PostgreSQL with pgvector, and produce a report. It works with 10+ cloud LLM providers or local models through Ollama or vLLM, and has REST and GraphQL APIs.
• Trended earlier REPO agentbaseline/agentbaseline Agentbaseline Agent Baseline is a draft framework of six security outcomes and 35 controls an enterprise must evidence to run AI agents safely, kept as machine-readable YAML.