SoloEngine is the first low-code platform that compiles Agentic AI. Staff a team of Agents like a startup — drag them onto the canvas, connect the org chart, compile — they plan, act, and deliver on their own.
No Workflow. No orchestration code. Just Agents that get things done.
English | 简体中文 | Español | Deutsch | Français
Agentic AI is transforming software — one developer now ships the work of ten. But that revolution never left the code editor. Building real AI Agents means writing LangChain pipelines, debugging ReAct loops, and hand-authoring tool schemas. If you can't code, you're locked out.
The alternatives don't help: workflow platforms (Dify, n8n, etc.) run pre-scripted paths, not autonomous agents. Code frameworks (LangChain, CrewAI, etc.) require Python. SoloEngine fills the gap.
| Dify, n8n, Zapier | LangChain, CrewAI, LangGraph | SoloEngine | |
|---|---|---|---|
| Agentic AI | ✗ Scripted workflows only | ✓ ReAct / multi-Agent | ✓ ReAct / multi-Agent |
| No code required | ✓ | ✗ Python mandatory | ✓ |
| Visual composition | Partial | ✗ | ✓ Full canvas |
| Domain expert can build alone | ✓ (but Agent isn't truly Agentic) | ✗ | ✓ |
| Multi-Agent collaboration | ✗ | ✓ | ✓ |
- Not another workflow tool — Agents run Think → Act → Observe → Repeat loops. Decisions happen at runtime. When a research Agent hits a dead end, it re-plans — no hardcoded fallback.
- Domain experts build directly — A lawyer drags a Contract Review Agent onto the canvas, wires it to a Research Agent, hits compile. No programmer in the loop.
- Tools, skills, MCP — pluggable — Each Agent loads tools and skills at runtime. Progressive disclosure saves 85%+ on tokens.
- One adapter, any model — OpenAI, Anthropic, Ollama, DeepSeek, Qwen, Zhipu — same interface, seamless switching.
All Agents are the same primitive — just configured differently. The canvas compiles directly into executable Agent teams.
- Compilation — Visual layout → Agent DAG via topological sort. One compiler, infinite teams.
- One ReAct engine — Every Agent runs the same Think → Act → Observe → Repeat loop.
- Progressive disclosure — Agents only load what they use at runtime, making low-code agentic AI practical.
git clone https://github.com/Sh4r1ock/SoloEngine.git
cd SoloEngine
# Backend (Python 3.11+)
cd backend
pip install -r requirements.txt
python main.py
# Frontend (Node.js 18+) — open another terminal
cd frontend
npm install
npm run devOpen http://localhost:8991 and build your first Agent team.
- VibeLawing — A lawyer drags search, filing, and formatting Agents onto the canvas in sequence. Compiles. Now legal work flows — statutes located, cases organized, documents formatted — the same way developers vibe-code with Cursor.
- VibeMarketing — A marketer drags research, copywriting, and asset Agents onto the canvas. Compiles. Campaigns write themselves, audiences get analyzed autonomously.
- One-click package — Build your Agent team, hit package, one product ready for anyone.
⭐ If you find this useful, give us a star — it helps a lot!
Special thanks to:
We are so excited to meet you.
Every typo fix, new tool plugin, doc tweak, or full-on feature lands — all of it makes SoloEngine better. Big PRs and small ones, both welcome.
📝 Contributing guide · 🐛 Good first issues · 📧 sh4r1ock@qq.com
Apache License 2.0. See LICENSE.
Made with ❤️ by the SoloEngine Team