# agents-flex/agents-flex

Agents-flex is A lightweight Java AI agent development framework (positioned as a counterpart to Spring AI). It supports features such as RAG, MCP, Skills, Text2SQL , LLM Wiki, Sub-agents, Web Search, TTS (synchronous and streaming), and STT.

Repository: https://github.com/agents-flex/agents-flex
Canonical: https://ross.abutalabs.com/products/agents-flex
Homepage: https://agentsflex.com
Language: Java
License: Apache-2.0
License Family: permissive
Topics: llm, agent, ai, chatbot, chatgpt, gpt, langchain4j, llama3, ollama, spring-ai
Last push: 2026-09-02T11:56:01+00:00

## Health v2 (maintenance only)
Score: 93/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 100, release rhythm 98, longevity 68
- inputs: {"age_days": 964, "days_push": 0, "days_rel": 16, "gap_med": 7.0, "n_releases_24m": 33}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1046, forks 144 (observed 2026-09-03T02:15:08.852597+00:00)

## What it is
Agents-Flex is a lightweight, modular Java framework for building AI applications and agents, positioned as a Java counterpart to Spring AI. It provides unified abstractions for chat models, tool calling, durable agent runtimes, RAG pipelines, MCP, Skills with sandboxed execution, multimodal models (image, TTS, STT, video, OCR), Text2SQL, and OpenTelemetry observability.

## Use cases
- build ai agents in java
- add llm chat to a spring boot app
- build a rag knowledge base chatbot
- connect multiple llm providers with one api
- tool calling and function calling in java
- streaming chat responses in a web app
- extract text from pdfs and office docs with ocr
- run durable long-running ai tasks that survive restarts

## When to choose
- you are a Java/JVM developer building LLM-powered applications or agents
- you want a Spring AI or LangChain4j alternative that works without Spring
- you need production features like retries, load balancing, circuit breaking, and observability out of the box
- you need durable, recoverable agent runs and async task tracking across restarts
- you want RAG, MCP, Skills, and multimodal capabilities in one modular framework

## When to avoid
- your stack is Python, JavaScript, or another non-JVM language
- you only need a simple one-off script calling an LLM API
- you need a ready-made end-user chat application rather than a development framework
- you are locked to JDK 8 but need the MCP module, which requires JDK 17+

## Facets
- artifact type: framework
- maturity: active
- function: agent-framework, llm-inference, rag, mcp, chatbot, ocr, tts, speech-recognition, image-processing, video-processing, web-framework, sdk, monitoring, tracing, search-engine, workflow-automation, prompt-engineering, nlp
- domain: artificial-intelligence, large-language-models, chatbots, machine-learning, developer-tools, backend, apis, self-hosted
- platform: jvm, cross-platform, self-hosted
- tags: java, spring-ai-alternative, tool-calling, text2sql, skills, sub-agents, vector-store, embedding, multimodal, openai-compatible, streaming, async-tasks, sandbox, opentelemetry, ai-agents, retrieval-augmented-generation, natural-language-processing, spring, docker

## Member repositories
- agents-flex/agents-flex (main) score 93

## Provenance
- Observed fields: from GitHub, fetched 2026-09-03T02:15:08.852597+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T07:02:35.937223+00:00, confidence not recorded.
  - readme: https://github.com/agents-flex/agents-flex (fetched 2026-09-03T02:15:08.852597+00:00, sha 92beb11f29cc)
  - homepage: https://agentsflex.com (fetched 2026-08-29T13:03:54.087285+00:00, sha 127cd2ed3236)
  - site_page: https://agentsflex.com/zh/chat/getting-started.html (fetched 2026-08-29T13:03:54.096368+00:00, sha 17263049e326)
  - site_page: https://agentsflex.com/zh/agent/getting-started.html (fetched 2026-08-29T13:03:54.098622+00:00, sha 69b2572e720e)
  - site_page: https://agentsflex.com/zh/skills/getting-started.html (fetched 2026-08-29T13:03:54.100378+00:00, sha c48b71b7ad42)
  - site_page: https://agentsflex.com/zh/observability/getting-started.html (fetched 2026-08-29T13:03:54.102403+00:00, sha 13e26992b84f)
  - site_page: https://agentsflex.com/zh/ocr/getting-started.html (fetched 2026-08-29T13:03:54.104240+00:00, sha 7194697310fe)
  - site_page: https://agentsflex.com/zh/async-task/getting-started.html (fetched 2026-08-29T13:03:54.106160+00:00, sha 01d78f3604d7)
- Data as of 2026-08-30T08:39:29.467469+00:00.