# spring-ai-alibaba/Lynxe

A high-determinism, code-free 'Prompt Programing'  studio built with Java 一个高确定性的 无代码 'Prompt编程'工作站，以 Java 编写

Repository: https://github.com/spring-ai-alibaba/Lynxe
Canonical: https://ross.abutalabs.com/products/lynxe
Language: Java
License: Apache-2.0
License Family: permissive
Last push: 2026-06-28T14:54:01+00:00

## Health v2 (maintenance only)
Score: 76/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 89, release rhythm 87, longevity 25
- inputs: {"age_days": 355, "days_push": 66, "days_rel": 84, "gap_med": 2, "n_releases_24m": 38}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1077, forks 244 (observed 2026-08-28T04:03:29.567330+00:00)

## What it is
Lynxe (formerly JManus) is a Java-based, code-free 'Prompt Programming' studio implementing a Manus-style multi-agent system with high execution determinism. It supports a Func-Agent mode for precisely controlled repetitive workflows, native MCP integration, and HTTP APIs for embedding into existing Java applications.

## Use cases
- build deterministic multi-agent workflows without writing code
- extract data from large datasets and load it into a database row
- analyze logs and trigger alerts automatically
- integrate an agent runtime into an existing Java application via HTTP
- connect agents to external tools via MCP
- define repeatable Func-Agent prompt programs for business processes

## When to choose
- you are a Java/Spring shop wanting an agent framework with HTTP integration
- you need highly deterministic, repeatable agent executions rather than free-form autonomy
- you want a no-code studio for prompt-driven automation with MCP tool support

## When to avoid
- you need a Python-first agent ecosystem with broad library support
- you want fully autonomous, exploratory agents with minimal determinism constraints
- you are not tied to the JVM and prefer lightweight scripting-based agent tools

## Facets
- artifact type: application
- maturity: active
- function: agent-framework, llm-inference, mcp, prompt-engineering, http-server, workflow-automation
- domain: artificial-intelligence, large-language-models, developer-tools
- platform: jvm, self-hosted
- tags: prompt-programming, no-code, multi-agent, manus-implementation, spring-ai, func-agent, dashscope, ai-agents, automation, docker, web-server

## Member repositories
- spring-ai-alibaba/Lynxe (main) score 76

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:29.567330+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 2026-08-30T06:53:17.422502+00:00, confidence not recorded.
  - readme: https://github.com/spring-ai-alibaba/Lynxe (fetched 2026-08-28T04:03:29.567330+00:00, sha 2bcf0d0a50fc)
- Data as of 2026-08-30T08:39:29.467469+00:00.