kitaru — MCP Server by zenml-io

by zenml-io · MCP Server · ★ 229

Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h

🔒 Is kitaru safe to install? View the security audit →

About kitaru

The runtime layer underneath your agent stack. Kitaru (来る, "to arrive") is a self-hosted, framework-agnostic runtime for autonomous agents — underneath the harness your team already picked. You keep your agent SDK, your prompts, your tools, your model. Kitaru adds durable execution: checkpoints, replay, resume, wait(), versioned deployments, and isolated runtimes, running on your own infrastructure. Docs &middot; Quick Start &middot; Examples &middot; Getting Started Guide &middot; Roadmap &middot; Community <img src="assets/dashboard.png" alt="Kitaru Dashboa

agent-frameworkai-agentscheckpointsdurable-executionllmmcpmlopsobservabilitypydanticpydantic-ai

Quick Facts

Stars229
Forks16
LanguagePython
CategoryMCP Server
LicenseApache-2.0
Quality Score65.0823036936784/100
Open Issues41
Last Updated2026-08-07
Created2026-03-05
Platformsmcp, python
Est. Tokens~15k

Compatible Skills

These tools work well together with kitaru for enhanced workflows:

  • pydantic-ai-todo — semantic(0.38)+complementary+rare_topics+same_lang+similar_pop+shared_platform (67%)
  • pydantic-ai-shields — semantic(0.33)+complementary+rare_topics+same_lang+similar_pop+shared_platform (65%)
  • pydantic-ai-skills — semantic(0.32)+complementary+rare_topics+same_lang+similar_pop+shared_platform (61%)

kitaru alternative? Top 6 similar tools

Looking for a kitaru alternative? If you're comparing kitaru with other mcp server tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.

  • pydantic-deepagents by vstorm-co · ⭐ 1.0k

    Open-source, self-hosted Claude Code - a terminal AI assistant and the Python framework behind it. Tool-callin

  • orloj by OrlojHQ · ⭐ 111

    An orchestration runtime for multi-agent AI systems. Declare agents, tools, and policies as YAML; Orloj schedu

  • pydantic-ai-shields by vstorm-co · ⭐ 87

    Guardrail capabilities for Pydantic AI — cost tracking, prompt injection detection, PII filtering, secret reda

  • pydantic-ai-todo by vstorm-co · ⭐ 74

    Task Planning and Tracking toolset for Pydantic AI agents, enabling hierarchical task management with subtasks

  • OmoiOS by kivo360 · ⭐ 71

    Turn feature specs into merged PRs with a self-supervising swarm of coding agents — parallel execution, isolat

  • subagents-pydantic-ai by vstorm-co · ⭐ 58

    Subagent Delegation framework for Pydantic AI, enabling nested subagents that can spawn their own specialists

More MCP Server Tools

Explore other popular mcp server tools:

View all MCP Server tools →

Popular Python Agent Tools

Frequently Asked Questions

What is kitaru?

kitaru is Record, replay, and improve AI agents in production, built on ZenML. It is categorized as a MCP Server with 229 GitHub stars.

What programming language is kitaru written in?

kitaru is primarily written in Python. It covers topics such as agent-framework, ai-agents, checkpoints.

How do I install or use kitaru?

You can find installation instructions and usage details in the kitaru GitHub repository at github.com/zenml-io/kitaru. The project has 229 stars and 16 forks, indicating an active community.

What license does kitaru use?

kitaru is released under the Apache-2.0 license, making it free to use and modify according to the license terms.

What are the best alternatives to kitaru?

The top alternatives to kitaru on Agent Skills Hub include pydantic-deepagents, orloj, pydantic-ai-shields. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.

View on GitHub → Browse MCP Server tools