GraphCanon updated Sep 29, 2026 · GitHub synced Sep 29, 2026
40views this month
Decision brief
Kitaru focuses on recording, replaying, and enhancing the performance of AI agents in production environments using technology from ZenML.
Good fit when
- - You need to ensure the continuous improvement of AI agents that are already deployed; Kitaru allows you to replay scenarios with different approaches to identify improvements.
- - Your project leverages PydanticAI or similar frameworks and you require integration capabilities for recording and observing agent behavior over time;
Avoid when
- - If your project is in the early stages of development without a clear need for replaying historical data or improving upon past behaviors;
- - When working outside Python, as Kitaru does not currently offer support for other programming languages.
Observed Jul 17, 2026 · Source: enrich:decision_facts
Verify the decision
Maintenance and security
Full trust report- Maintenance
- Very active (0d since push)
- As of Sep 29, 2026
- Provenance
- Not a fork · Organization account
- As of Sep 29, 2026
- Security (OSV)
- No criticals
- As of Jul 11, 2026
Public GitHub metadata and optional OSV scans. Signals, not a guarantee. Trust methodology.
Install
pip install kitaruSimilar tools
Same-category neighbours. No typed graph edges are catalogued for this tool yet.
Evidence and technical details
Sourced facts, taxonomy, compatibility claims, README excerpt, and machine-readable endpoints.
Overview
A toolset for managing the lifecycle of AI agents including recording, replaying, and improving performance in deployment settings.
Capability facts
- Deploy
- Self-host
Source: dockerfile:docker-compose.yml · Sep 29, 2026
- Docker
- Dockerfile present
Source: dockerfile:docker-compose.yml · Sep 29, 2026
- CLI
- CLI entrypoint
Source: pyproject.toml:[project.scripts] · Sep 29, 2026
- MCP server
- No MCP server detected
Source: repo_scan · Sep 29, 2026
- Languages
- python, javascript, typescript
Source: github.language+package.json+pyproject.toml · Sep 29, 2026
Categories
Compatibility
Sourced claims from the README excerpt - not unsourced marketing copy.
Source: README excerpt (regex_v1, Sep 29, 2026)
and see what improved and what broke before you ship. Open source, self-hosted, Python and TypeScript. From the team behind <a href="https://zenml.io">ZenML</a>.Source link
Source: README excerpt (regex_v1, Sep 29, 2026)
the coding-agent skills, and registers the MCP server with Claude Code, Codex, Cursor, and Windsurf (that part is `kitaru setup`, re-run it after installing a new edSource link
Source: README excerpt (regex_v1, Sep 29, 2026)
agent skills, and registers the MCP server with Claude Code, Codex, Cursor, and Windsurf (that part is `kitaru setup`, re-run it after installing a new editor). It endsSource link
Tags
README
<p align="center" <a href="https://docs.zenml.io/kitaru" <img src="assets/kitaru header.png" alt="Kitaru — Traces you can run, not just read." width="900" </a </p <h3 align="center" Traces you can run, not just read.</h3 <p align="center" Kitaru (来る, "to arrive") gives you replay...
For agents
This page has a .md twin and JSON over the API.