# iflytek/astron-agent

Enterprise-grade, commercial-friendly agentic workflow platform for building next-generation SuperAgents.

Repository: https://github.com/iflytek/astron-agent
Canonical: https://ross.abutalabs.com/products/astron-agent
Homepage: http://astron.ai/
Language: Java
License: Apache-2.0
License Family: permissive
Topics: agent, agentic-workflow, ai, enterprise, low-code, mcp, multi-agent, superagent, workflow, llm, next-gen, orchestration, python, iflytek-astron, agentic-ai, enterprise-automation, llm-ops, rpa, workflow-engine
Last push: 2026-08-26T09:18:24+00:00

## Health v2 (maintenance only)
Score: 83/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 99, release rhythm 96, longevity 24
- inputs: {"age_days": 348, "days_push": 7, "days_rel": 26, "gap_med": 15, "n_releases_24m": 12}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 8911, forks 861 (observed 2026-08-28T04:10:26.247340+00:00)

## What it is
Astron Agent is an enterprise-grade, commercial-friendly agentic workflow platform for building, orchestrating, and deploying multi-agent AI applications. It combines AI workflow orchestration, model management, MCP and AI tool integration, RPA automation, and team collaboration under the Apache 2.0 license.

## Use cases
- build enterprise AI agent applications
- orchestrate multi-agent workflows with low-code tools
- integrate MCP tools and LLMs into business processes
- automate cross-system enterprise processes with RPA-driven agents
- self-host a production-ready agent platform with high availability
- manage and deploy large models on-premises as MaaS

## When to choose
- you need an enterprise-grade, commercially usable (Apache 2.0) agent platform
- you want workflow orchestration combined with RPA and cross-system integration
- you need high-availability self-hosted deployment of agent applications
- you want plug-and-play AI tools and flexible LLM/MaaS model access

## When to avoid
- you only need a lightweight agent library embedded in existing code
- your stack is Python-only and you prefer Python-native agent frameworks
- you need a simple chatbot without workflow orchestration or RPA

## Facets
- artifact type: framework
- maturity: active
- function: agent-framework, workflow-automation, llm-inference, mcp, chatbot
- domain: artificial-intelligence, large-language-models, erp, developer-tools
- platform: self-hosted, cloud, jvm
- tags: agentic-workflow, low-code, multi-agent, rpa, llm-ops, workflow-engine, enterprise-automation, superagent, ai-agents, automation, docker, web-server

## Member repositories
- iflytek/astron-agent (main) score 83

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:10:26.247340+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 2026-08-29T17:24:42.979238+00:00, confidence not recorded.
  - readme: https://github.com/iflytek/astron-agent (fetched 2026-08-28T04:10:26.247340+00:00, sha 651fa6d849e4)
  - homepage: http://astron.ai/ (fetched 2026-08-29T08:24:50.491900+00:00, sha 70de254b08e6)
- Data as of 2026-08-30T08:39:29.467469+00:00.