Back to directory

Spring AI Agent Utils

Spring AI Agent Utils reimplements Claude Code's core agent tools, including file operations, shell execution, web access, task management and skills, as Spring AI tools for Java AI applications.

Visit website (opens in a new tab)spring-ai-community.github.io
Spring AI Agent Utils

Spring AI Agent Utils is a library of Spring AI tools that bring Claude Code-style agent capabilities to Java applications built on Spring AI. Core tools cover reading, writing and editing files; running shell commands with timeout control, background process management and regex output filtering; a pure Java grep implementation for code search; a glob-based file finder; AI-summarized web fetching; and web search with domain filtering.

It also provides a tool for asking the user clarifying multiple-choice questions during agent execution, a skills tool for loading reusable Markdown-with-YAML-front-matter capability modules, and persistent file-based long-term memory tools that survive across conversations, organized into typed memory files with a Markdown index. A companion ChatClient advisor wires the memory tools and their system prompt into the request pipeline automatically.

The project describes itself as a reimplementation of Claude Code's agent features for the Spring AI ecosystem.

More in Agent frameworks

See all 902
  • Recurse

    recurse.run

    A serverless harness that lets a coding agent design, test, and deploy its own specialist sub-agents as tools, MCP servers, or bots, defined by a schema-validated manifest.

  • ProofForge

    shulgin.is-a.dev

    An AI-agent pipeline that decomposes a mathematics problem, proves each piece, and formalizes the result in Lean 4 and Mathlib until the Lean kernel accepts it, with six of its proofs already merged into Google DeepMind's formal-conjectures repository.

  • local-coder

    github.com

    Builds a local coding-agent team on top of Ollama and OpenCode by detecting the machine's hardware, recommending models for seven specialist roles, and testing whether each assigned model can actually use tools, edit a repository and pass verification.