Add AF4J to Artificial Intelligence

AH
14h ago
+1-0

Suggestion type

  • Project
  • Resource

Checklist

  • I searched the list and existing issues for duplicates.
  • I changed README_SOURCE.md, not the generated README.md.
  • This pull request contains one suggestion.
  • The suggestion is relevant to Java or the JVM and fits its chosen category.
  • I used the canonical project or resource link.
  • The suggestion is current and maintained.
  • The concise, neutral description explains its distinguishing value and ends with punctuation.
  • Licensing is clear and any restrictive terms are disclosed where applicable.

Entry

Adds one entry to ### Artificial Intelligence in README_SOURCE.md:

- [AF4J](https://github.com/datallmhub/agentflow4j) - Runtime for governed multi-agent workflows on Spring AI, with an agent graph, checkpoint and resume, tool policies, budgets and human approval gates.

Disclosure: I maintain AF4J, so this is self-promotion. Against the criteria:

  • Java as the primary target. It is a Java 17 library and nothing else, published on Maven Central as io.github.datallmhub:agentflow4j-*.
  • Fills a niche. The agent frameworks already listed focus on building and orchestrating agents. AF4J's distinguishing part is governance inside the runtime: a tool policy checked before each tool call, a budget that caps a run, a human approval gate that pauses a node, and checkpoints so a paused or crashed run resumes.
  • Current and maintained. Stable API since 1.0, latest release 1.0.1 this month, CI on Spring AI 1.0, 1.1 and 2.1.
  • Documentation and licence. English docs at https://datallmhub.github.io/agentflow4j/, Apache-2.0.

It is a young project, public since April 2026, with about 50 stars. I understand if that is too early for the list.


Summary by cubic

Adds AF4J to the Artificial Intelligence section of README_SOURCE.md.