JobRunr Introduces ClawRunr, an Open-Source Java AI Agent

2026-05-01 · Source: InfoQ · Field: Technology & Digital — Artificial Intelligence & Machine Learning, Software Development & Engineering · Depth: Intermediate, short

Summary

JobRunr has launched ClawRunr, an open-source Java AI agent designed for executing scheduled, recurring, and one-off background tasks on users' own hardware. Built on Java 25, Spring Boot, Spring AI, and JobRunr, ClawRunr supports OpenAI, Anthropic, and Ollama as LLM providers, with state persisted in an embedded H2 database. The agent combines conversational interaction with persistent task execution, enabling users to create reminders, automate work, and connect tools via Model Context Protocol (MCP). Architecturally, it uses Spring Modulith for modularity and handles asynchronous task execution through JobRunr, storing user-created and recurring tasks as Markdown files. It ships with tools for task management, shell execution, file access, web scraping, and optional Playwright integration for browser automation, also featuring dynamic tool discovery and a file-based skill system.

Key takeaway

For AI Architects evaluating platforms for persistent, scheduled AI agent deployments, ClawRunr offers a robust, open-source Java-based solution. Its integration with JobRunr for task management, support for multiple LLM providers including local Ollama, and modular Spring architecture provide a strong foundation. You should consider its file-based skill system and dynamic tool discovery for flexible agent customization and efficient resource utilization in your projects.

Key insights

ClawRunr is an open-source Java AI agent for persistent, scheduled background tasks, integrating LLMs and various tools.

Principles

• Persistence and scheduling are first-class concerns for long-running AI agents.
• Modular architecture enhances maintainability and extensibility for agent systems.
• File-based configurations and skills simplify agent customization without code changes.

Method

ClawRunr uses Spring Modulith for architecture, Spring AI for LLM integration, and JobRunr for asynchronous task execution, storing tasks and skills as Markdown files in a workspace.

In practice

• Run AI agents locally with Ollama for data privacy.
• Automate recurring tasks using cron support and dashboard monitoring.
• Extend agent capabilities by adding SKILL.md files to the workspace.

Topics

• ClawRunr
• Java AI Agents
• JobRunr Platform
• Open-Source AI
• Background Task Management

Code references

• jobrunr/JavaClaw

Best for: AI Architect, AI Engineer, Software Engineer, MLOps Engineer

Related on AIssential

• OpenAI Codex App Feels Like Clawdbot Lite — AI agent ecosystems are evolving towards autonomous orchestration and inter-agent economic transactions.
• Clawdbot (Moltbot): How to Actually Run Your Own AI Employee (Without Getting Hacked) — Moltbot provides persistent memory and agency to LLMs, transforming them into proactive, always-on AI agents.
• OpenJarvis: a local-first personal AI is now available to run with Ollama — OpenJarvis provides a local-first, open-source framework for personal AI agents, prioritizing efficiency and user control over cloud reliance.
• ByteDance Releases DeerFlow 2.0: An Open-Source SuperAgent Harness that Orchestrates Sub-Agents, Memory, and Sandboxes to do Complex Tasks — DeerFlow 2.0 is an open-source SuperAgent framework enabling autonomous AI task execution via sandboxed multi-agent orchestration.
• ClawGym: A Scalable Framework for Building Effective Claw Agents — ClawGym provides a comprehensive framework for developing, training, and evaluating Claw-style personal agents.
• NVIDIA CEO Jensen Huang at Meet-a-Claw in Taipei — Open Claw offers an open-source framework for developing and learning about large language model agents.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by InfoQ.