#2828th of 42 in Agent platforms
astron-agent
Agentic workflow platform with model management, MCP tools and RPA nodes
Live demo ↗
(opens in a new tab)Documentation ↗
(opens in a new tab)Website ↗
(opens in a new tab)Repository on GitHub ↗
(opens in a new tab)
- Stars
- 8.9k
- License
- Apache-2.0
- Last commit
- Oct 2026
- Last release
- Sep 2026
- Language
- Java
6,896 on 1 Apr 20268,923 on 21 Oct 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
Astron Agent is a platform for building and running agent workflows, with orchestration, model management, MCP and iFLYTEK tool integration, and RPA steps for driving other enterprise systems. It deploys via Docker Compose with a Casdoor authentication service and an nginx-proxied frontend. Published workflows can be called from other projects over HTTP/SSE.
Who it is for: Teams self-hosting agent workflows with RPA and enterprise integrations
Strengths
- Apache-2.0 with no stated commercial restrictions
- RPA integration (AstronRPA) lets agents act on other systems
- Published workflows callable over HTTP/SSE from existing projects
- Casdoor authentication included in the compose deployment
Weaknesses
- Helm chart is not released; Kubernetes deployment is marked as under development
- Many ready-made tools come from the iFLYTEK Open Platform
- Compose setup requires a manual Casdoor password initialization step first
- README gives no RAM, GPU or model-format requirements
What it needs
- Compose
- Needs Docker Compose, Casdoor, nginx
- Models: API-based models, on-premises MaaS clusters
- port 80
Also in Agent platforms
See all 42| Rank | Project | Score |
|---|---|---|
| 1 | LangflowVisual builder for AI agents and workflows, exposed as API or MCP server | 81 out of 100 |
| 2 | daily_stock_analysisDaily LLM stock analysis for A-share, HK, US and other markets, pushed to chat apps | 81 out of 100 |
| 3 | resume-matcherTailors resumes and cover letters to job descriptions using local or hosted LLMs | 81 out of 100 |
| #4 | vibe-tradingFinance research agent for backtests, market data and broker connectors | 78 out of 100 |
| #5 | deer-flowAgent harness that runs sub-agents, memory and sandboxed skills for long tasks | 77 out of 100 |