Skip to content

astron-agent

AI Agents & Assistants

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

Java Latest v1.0.7 · 19d ago Security brief →

Features

  • Enterprise‑grade high availability for building scalable AI agent applications
  • Native intelligent RPA integration enabling cross‑system process automation
  • Ready‑to‑use tool ecosystem with plug‑and‑play access to iFLYTEK models and tools

Recent releases

View all 8 releases →
Config change
v1.0.7 Breaking risk
Auth Breaking upgrade

Automation scheduling + skill sandbox

v1.0.6 New feature
Notable features
  • Skill system: manage and use skills via resource management UI and Agent node plugins
  • Workflow export integrated with SKILL feature
Full changelog

What's Changed

Based on PRs merged into main since v1.0.5.

New Features

  • feat(knowledge): expose optional RAGFlow retrieval parameters (#1231)
  • feat: Added skill system,you can now manage skills in the resource management interface and use skills in the plugins of the workflow’s Agent nodes (#1239)
  • feat(knowledge): route RAGFlow ops by per-repo datasets (#1242)
  • feat: add workflow export to SKILL feature (#1249)

Fixes

  • fix(knowledge): forward documentId in /document/split for Ragflow upsert (#1206)
  • fix(knowledge): paginate RAGFlow chunks and use id filter for lookups (#1211)
  • fix(knowledge): propagate RAGFlow failures instead of swallowing to empty results (#1222)
  • fix(ragflow): honor explicit dataset id during upload (#1240)

Improvements

  • refactor(knowledge): unify RAGFLOW_DEFAULT_GROUP fallback loader (#1208)
v1.0.5 Security relevant
Security fixes
  • HTTPS protocol verification issue
Notable features
  • Parallel execution support for iteration nodes
  • Workflow export as template feature
  • Agent removal function
Full changelog

What's Changed

Based on PRs merged into main since v1.0.4.

New Features

  • feat(engine): add parallel execution support for iteration nodes (#1131)
  • feat: 新增迭代节点并行模式 (#1134)
  • feat: Add agent removal function (#1147)
  • feat: Add workflow export as template feature (#1201)
  • feat: Add workflow export as template feature (#1203)

Fixes

  • fix: Modify the release workflow (#1136)
  • fix: chat_bot_list Data synchronization (#1154)
  • fix: Fix HTTPS protocol verification issue (#1156)
  • fix: Fix the invalid session ID issue (#1159)
  • fix: Extend model to add form field length (#1163)
  • fix:Fix the issue of missing link logs during API calls (#1166)
  • fix:Fix the issue of the MCP tool displaying blank (#1170)
  • fix:fix hub ci (#1176)
  • fix(core-link): mock create_engine in database initialization unit tests (#1184)
  • fix: resolve Python CI formatting failures and fix workflow unittest (#1185)
  • fix(knowledge): RAGFlow RAG重新切片时出现重复的RAGFlow文档 (#1181)
  • fix(knowledge): RAGFlow RAG重新切片时出现重复的RAGFlow文档 (#1189)
  • fix(knowledge): RAGFlow RAG重新切片时出现重复的RAGFlow文档 (#1190)
  • fix(knowledge): RAGFlow RAG重新切片时出现重复的RAGFlow文档 (#1192)
  • fix(knowledge): RAGFlow RAG重新切片时出现重复的RAGFlow文档 (#1193)

Improvements

  • chore: add GitHub-reward form, scripts & actions (#1152)
  • chore: fix some nits for make check-python (#1169)
  • chore: fix some nits for make check-typescript (#1172)
  • fix:fix hub ci (#1177)
  • chore: fix some nits for make check-java (#1179)
  • Delete irrelevant content (#1093)
  • refactor(console-backend): improve code quality and make test-java passes (#1182)
  • Bugfix/superteam (#1188)
v1.0.4 New feature
Notable features
  • MySQL compatibility improvements
  • Localization image push
  • Workflow trace panel
v1.0.3 New feature
Notable features
  • Memory nodes and asynchronous task support to workflow engine
  • Variable Aggregation Node for data processing
  • Hot-reload and asynchronous Kafka features

Weekly OSS security release digest.

The CVE patches and breaking changes that affected production tools this week. One email, every Sunday.

No spam, unsubscribe anytime.

About

Stars
8,527
Forks
847
Languages
Java TypeScript Python

Install & Platforms

Install via
docker-compose

Beta — feedback welcome: [email protected]