{"slug":"spring-ai-agentx","name":"Spring AI AgentX","vendor":"bigchuidw3","tagline":"Java agent framework on Spring AI with a ReAct engine, layered memory, context compaction, sub-agents and human-in-the-loop","url":"https://agentboards.org/agent/spring-ai-agentx","website":"https://github.com/bigchuidw3/spring-ai-agentx","docs":null,"repo":"https://github.com/bigchuidw3/spring-ai-agentx","category":"framework","execution":["local"],"license":"Apache-2.0","open_source":true,"pricing":{"model":"byok","summary":"Free and open source under Apache-2.0; you pay whichever model provider the Spring AI ChatModel is configured against","from_usd":0,"free_tier":true,"byok":true},"models":{"backbone":["any Spring AI ChatModel"],"bring_your_own_model":true,"local_models":false},"protocols":{"mcp_client":true,"mcp_server":false,"openapi":false},"capabilities":{"terminal_exec":true,"browser":false,"multi_file_edit":true,"git_ops":false,"docker_sandbox":true,"multi_agent":true,"headless_ci":false},"context_window":null,"platforms":["macos","linux","windows"],"install":[{"label":"Maven","command":"<dependency><groupId>com.agentx.ai</groupId><artifactId>spring-ai-agentx-core</artifactId><version>1.0.1-M1</version></dependency>"}],"benchmarks":[],"tags":["open-source","java","spring-ai","react","hitl","mcp","sandbox"],"github_stars":188,"metrics":{"stars":188,"pushed_at":"2026-09-24T08:19:19Z","archived":false,"open_issues":3,"latest_version":null,"latest_version_at":null,"latest_version_url":null,"version_source":null,"checked_at":"2026-10-02T05:02:41.019Z"},"sources":{"overview":"https://github.com/bigchuidw3/spring-ai-agentx","install":"https://github.com/bigchuidw3/spring-ai-agentx","capabilities":"https://github.com/bigchuidw3/spring-ai-agentx","protocols":"https://github.com/bigchuidw3/spring-ai-agentx","models":"https://github.com/bigchuidw3/spring-ai-agentx","license":"https://github.com/bigchuidw3/spring-ai-agentx"},"verified_at":"2026-09-04","adoption":{"score":0,"signals":{"github_stars":187},"measured_at":"2026-09-28"},"scores":{"panel":6.6,"adoption":0,"spread":1.8,"facts":8.3,"board":5.9,"dimensions":{"reliability":6.5,"usefulness":6.5,"cost":8.3,"longevity":5.2},"per_persona":{"amigo":6.8,"critico":6,"profesor":7.5,"inversora":5.8,"jefa":6.5,"hacker":7.3},"community":null},"rank":null,"category_rank":53,"panel_reviews":[{"persona":"juez","persona_name":"El Juez","ai_generated":true,"verdict":"El Profesor and El Crítico agree the design is thoughtful and split on whether a milestone version number should be read as a warning.","scores":null,"evidence":[]},{"persona":"amigo","persona_name":"El Amigo","ai_generated":true,"verdict":"Pick it if you have a Spring application and want the agent inside it; pick a Python framework if you were going to run a separate service anyway.","scores":{"reliability":6,"usefulness":7,"cost":9,"longevity":5},"evidence":["https://github.com/bigchuidw3/spring-ai-agentx","https://github.com/bigchuidw3/spring-ai-agentx"]},{"persona":"critico","persona_name":"El Crítico","ai_generated":true,"verdict":"The published coordinate is a 1.0.1-M1 milestone, and the surface underneath it is enormous for a pre-release artefact with one maintainer.","scores":{"reliability":6,"usefulness":6,"cost":8,"longevity":4},"evidence":["https://github.com/bigchuidw3/spring-ai-agentx","https://github.com/bigchuidw3/spring-ai-agentx"]},{"persona":"profesor","persona_name":"El Profesor","ai_generated":true,"verdict":"Three named context states and a six-level progressive compaction chain make the window a managed resource rather than something that silently runs out.","scores":{"reliability":8,"usefulness":7,"cost":8,"longevity":7},"evidence":["https://github.com/bigchuidw3/spring-ai-agentx","https://github.com/bigchuidw3/spring-ai-agentx"]},{"persona":"inversora","persona_name":"La Inversora","ai_generated":true,"verdict":"167 stars, one personal handle, and a position defined entirely by a large vendor's framework: useful, and structurally somebody else's feature.","scores":{"reliability":5,"usefulness":6,"cost":8,"longevity":4},"evidence":["https://github.com/bigchuidw3/spring-ai-agentx","https://github.com/bigchuidw3/spring-ai-agentx"]},{"persona":"jefa","persona_name":"La Jefa","ai_generated":true,"verdict":"Shell and file tools run in a container or a restricted directory with conversation-level isolation, and trace auditing is in the library rather than in a roadmap.","scores":{"reliability":7,"usefulness":6,"cost":8,"longevity":5},"evidence":["https://github.com/bigchuidw3/spring-ai-agentx","https://github.com/bigchuidw3/spring-ai-agentx"]},{"persona":"hacker","persona_name":"El Hacker","ai_generated":true,"verdict":"Apache-2.0, MCP alongside native function calling, and seven lifecycle hooks, so I can intercept the loop without forking it.","scores":{"reliability":7,"usefulness":7,"cost":9,"longevity":6},"evidence":["https://github.com/bigchuidw3/spring-ai-agentx","https://github.com/bigchuidw3/spring-ai-agentx"]},{"persona":"comediante","persona_name":"El Comediante","ai_generated":true,"verdict":"It ships a TodoWrite tool, so the agent can now maintain a list of things it has not done yet, exactly like everyone else.","scores":null,"evidence":[]}]}