# ZizkaDB

> Updated 2026-09-20 · type: tool · category: mcp-agents · status: active · rev 1

ZizkaDB is a self-hosted, tamper-evident audit database for agents: checksum-backed decision logs with causal lineage, replayable to see how an agent decided.

- Open source: yes (AGPL-3.0)
- Self-hostable: yes
- Pricing model: freemium
- Best for: A team running agents against real systems that needs to answer 'why did the agent do that' after the fact, and wants a verifiable, self-hosted record of every decision for debugging or compliance rather than scrollback in a chat log.
- Last verified: 2026-09-20

- **Canonical:** https://gtmstacker.com/registry/tool/zizkadb/
- **Source:** [github · ZIZKA-AI-SL/ZizkaDB](https://github.com/ZIZKA-AI-SL/ZizkaDB)
- **Tags:** mcp-agents, agent-security, governance, audit, self-hostable
- **Repository:** https://github.com/ZIZKA-AI-SL/ZizkaDB

## Is ZizkaDB open source?

Yes, ZizkaDB is open source under the AGPL-3.0 license.

## How much does ZizkaDB cost?

ZizkaDB has a free tier plus paid plans. The open-source version can be self-hosted with no license cost; you pay only for your own infrastructure.

## Can I self-host ZizkaDB?

Yes, ZizkaDB can be self-hosted (the source is available under the AGPL-3.0 license).

## Alternatives & related

- [Talos](https://gtmstacker.com/registry/tool/talos/)
- [Agent Governance Toolkit](https://gtmstacker.com/registry/tool/agent-governance-toolkit/)


---

AGPL-3.0 audit-trail database for AI agents (Python) that records every agent decision and session as tamper-evident, checksum-backed logs, tracks the causal lineage between them, and lets you replay a session to see how the agent reached a decision. Each entry carries a checksum that changes if the record is altered, so the trail is verifiable for debugging and compliance. It self-hosts via Docker for free, with a managed cloud tier as a separate paid option.

## Provenance

- AGPL-3.0, Python, ~81 stars, ~527 commits, and the checksum-backed tamper-evident logs with causal lineage and replay independently WebFetch-verified on the repo 2026-09-20 (github.com/ZIZKA-AI-SL/ZizkaDB).
- Surfaced via the 2026-09-20 daily pull (Show HN: "tamper-evident, checksum-backed decision and session replay").
- Curated from the GTM Stacker signal registry (2026-09-20 pass); license independently verified 2026-09-20.

## Why it matters for a GTM stack

Once an agent is touching the CRM, the sending domain or billing, "why did it do that" stops being a curiosity and becomes a question you have to answer, to a customer, a teammate or an auditor. ZizkaDB is the record for that: every decision and session logged in a way that shows if it was altered, linked by cause, and replayable after the fact. For a GTM or RevOps team that has moved past demos into agents doing real work, that verifiable trail is the difference between an incident you can reconstruct and one you can only guess at. Two honest notes: it is AGPL, so read the copyleft terms against how you deploy, and it is an audit layer, not a gate, so it tells you what happened rather than stopping it. As the memory that makes agent actions accountable, it fills a real slot.