zenml-io / kitaru
Instill trust in your agent evals.
Why this job: says: evals; topics: mlops, observability
What it does
Kitaru (来る, "to arrive") reads your agent's traces and shows you the patterns across every session. Import the traces you already collect, or record new runs with an adapter. Turn what you find into checks, then replay a fix against the sessions that failed before it ships. Open source, on your machine, with your keys. Python and TypeScript. From the team behind ZenML.
Get started
curl -fsSL https://kitaru.ai/install | bash - Maintenance
- Active
- Last commit 3 days ago
- Stars
- 317
- +1 this week
- Licence
- Apache-2.0
- Allows business use
- Downloads for
- None listed
- No release files
- Latest tag
- python/kitaru/v0.27.6
- Released 5 days ago
- Built with
- Python
- 80% of the code
Is it looked after?
- Contributors
- 4
- Last 90 days
- Issues
- 83% closed
- 56 still open
- Pull requests
- 931 merged
- 14 waiting
- Releases
- 153
- 30+ in the last year
- Contributing guide (opens in new tab)
- Security policy (opens in new tab)
- No code of conduct
More: languages, topics and project record
Languages
- Python 80%
- TypeScript 18%
- JavaScript 1%
- Shell <1%
Topics
- ai-agents
- checkpoints
- durable-execution
- llm
- mcp
- mlops
- observability
- pydantic
- pydantic-ai
- python
- replay
- agent
Project record
- JobEvals and observability
- StatusListed
- Commits1,285
- Forks31
- Watching1
- Stars in 28 days+11
- CreatedMar 5, 2026
- First seen by usNov 7, 2026
- CheckedNov 9, 2026