# Flowise review

> Flowise is an open source TypeScript platform for building AI agents, chatbots and multi-agent workflows visually. The project is now archived.

Devtoolwatch Board, the week of Oct 25–31, 2026. Canonical page: https://index.devtoolwatch.com/tools/flowise/

## TL;DR

Flowise is a visual, low-code platform for building AI agents, chatbots with tool calling and RAG, and multi-agent workflows. It suits developers who want to self-host or embed LLM apps through an API, SDK or chat widget. The repository is archived and the company says it is sunsetting Flowise.

## Flowise at a glance

- **Category:** [Agent frameworks](https://index.devtoolwatch.com/categories/agent-frameworks/)
- **Maintained by:** FlowiseAI (organization, [@FlowiseAI](https://github.com/FlowiseAI) on GitHub)
- **Language:** TypeScript, JavaScript, HTML
- **Repository:** [github.com/FlowiseAI/Flowise](https://github.com/FlowiseAI/Flowise)
- **Website:** [flowiseai.com](https://flowiseai.com)
- **npm package:** [flowise](https://www.npmjs.com/package/flowise) 3.1.4
- **Latest release:** [flowise@3.1.4](https://github.com/FlowiseAI/Flowise/releases/tag/flowise%403.1.4) on GitHub, Jul 29, 2026
- **First published:** Mar 31, 2023

## What Flowise does

- Flowise Agentflow builds multi-agent systems with workflow orchestration across multiple coordinated agents.
- Flowise Chatflow builds single-agent chatbots with tool calling and knowledge retrieval (RAG) from various data sources.
- Flowise supports human-in-the-loop review, so people can review tasks agents perform within the feedback loop.
- Flowise provides execution traces and supports Prometheus, OpenTelemetry and other observability tools.
- Flowise exposes flows through APIs, an embedded chat widget, and TypeScript and Python SDKs.
- Flowise can turn a chatflow into an MCP server and supports custom MCP stdio commands.
- Flowise integrates LLMs, embeddings and vector databases, including nodes for Vertex AI, AWS Bedrock, Cerebras, Cloudflare Workers AI and Ollama Cloud.

### How it works

Flowise is a Node.js monorepo with a server backend, a React UI and a components package for third-party node integrations. You install it with npm or run it in Docker, then open the editor at localhost:3000. Applications call flows through the prediction API at /api/v1/prediction/:id. It can be self-hosted on AWS, Azure, GCP and other platforms, and can scale horizontally with a message queue and workers.

## How to install Flowise

**With npm**

```
npm install -g flowise
```

**With Docker Compose (from the docker folder)**

```
docker compose up -d
```

**Run a locally built Docker image**

```
docker run -d --name flowise -p 3000:3000 flowise
```

### Requirements

- Node.js: the README asks for version 20.0.0 or later, while the npm package declares engines node ^24.
- PNPM is required for building Flowise from source.
- Docker is needed for the Docker Compose or Docker image setup.

### First steps

1. Flowise starts with this command after installing it globally: npx flowise start
2. Open http://localhost:3000 in a browser to reach the Flowise editor.
3. Configure the instance with environment variables in the .env file inside the packages/server folder.
4. Call a flow from your app by sending a POST with a question to /api/v1/prediction/:id.

## Who Flowise is for

- Developers who want to prototype LLM chatbots with tool calling and RAG in a visual editor.
- Teams self-hosting AI agent workflows on their own infrastructure or cloud provider.
- Developers embedding a chat widget or calling agents through an API or SDK in their apps.

### Limitations

- Flowise has been archived on GitHub, and the homepage says the company is sunsetting Flowise.
- Flowise 3.1.0 enables HTTP security checks by default, blocking requests to localhost and internal addresses unless reconfigured.
- Building from source can fail with JavaScript heap out of memory, which requires raising the Node.js heap size.

## Usage data (the week of Oct 25–31, 2026)

- Board rank: #368 overall, #43 in Agent frameworks, momentum score 16
- Downloads that week: 5.6k (+76% vs 4-week average)
- New GitHub stars per week (last 12 weeks): Aug 9: 143; Aug 16: 37; Aug 23: 32; Aug 30: 53; Sep 6: 56; Sep 13: 34; Sep 20: 50; Sep 27: 45; Oct 4: 43; Oct 11: 47; Oct 18: 39; Oct 25: 39

## Flowise alternatives

| Rank | Tool | Stars | Downloads/wk |
|---|---|---|---|
| #1 | [Harness²](https://index.devtoolwatch.com/tools/google-research-harness2/) | 21.7k | – |
| #2 | [HyperFrames](https://index.devtoolwatch.com/tools/heygen-com-hyperframes/) | 76.6k | 1.5M |
| #3 | [AgentScope](https://index.devtoolwatch.com/tools/agentscope-ai-agentscope/) | 35k | 51.4k |
| #4 | [AG-UI](https://index.devtoolwatch.com/tools/ag-ui/) | 16.9k | 4.6M |
| #5 | [LangGraph](https://index.devtoolwatch.com/tools/langgraph/) | 44.2k | 18.5M |
| #6 | [Bifrost](https://index.devtoolwatch.com/tools/maximhq-bifrost/) | 9.3k | – |

## Flowise FAQ

### Is Flowise free and open source?

Flowise's code is on GitHub (FlowiseAI/Flowise), but the repository doesn't declare a standard open-source license. Check its license file before using it commercially. Its website links to a pricing page: https://flowiseai.com/#pricing.

### How do I install Flowise?

Run `npm install -g flowise`. It needs Node.js ^24. The install section above has the other options from the project's README.

### Is Flowise still maintained?

No. The FlowiseAI/Flowise repository is archived, so it's read-only.

### How popular is Flowise?

Flowise has 55.5k GitHub stars as of Nov 1, 2026. It gained 39 new stars in the week of Oct 25–31, 2026, against a 12-week average of 52 a week. Its main package had about 5.6k downloads that week, +76% against its own 4-week average. That made it #43 among AI agent frameworks on the Devtoolwatch Board.

### Flowise vs n8n: how do they compare?

Flowise and n8n are both tracked by Devtoolwatch as AI agent frameworks. Flowise has 55.5k GitHub stars and n8n has 209.2k. In the week of Oct 25–31, 2026, Flowise's main package had 5.6k downloads and n8n's had 147.7k. n8n is a fair-code workflow automation platform for building AI agents and workflows with a visual canvas plus custom code, self-hosted or cloud. [n8n review](https://index.devtoolwatch.com/tools/n8n/)

### Flowise vs Langflow: how do they compare?

Flowise and Langflow are both tracked by Devtoolwatch as AI agent frameworks. Flowise has 55.5k GitHub stars and Langflow has 156.2k. In the week of Oct 25–31, 2026, Flowise's main package had 5.6k downloads and Langflow's had 8.3k. [Langflow review](https://index.devtoolwatch.com/tools/langflow/)

### What are the best alternatives to Flowise?

Other AI agent frameworks on the Devtoolwatch Board in the week of Oct 25–31, 2026, by momentum: Harness² (#1), HyperFrames (#2), AgentScope (#3), AG-UI (#4), LangGraph (#5). The alternatives table above has their numbers.

### Is Flowise still maintained?

No. Flowise is archived on GitHub, and its homepage says the company is sunsetting it. The README points to a "Future of Flowise" discussion for details. The last listed release is flowise@3.1.4, dated 2026-07-29.

### Does Flowise support MCP?

Yes. Flowise 3.1.3 added the ability to turn a chatflow into an MCP server. Release 3.1.4 made the custom MCP stdio command allowlist operator-controlled.

### How does Flowise work?

Flowise runs a Node.js server and a React editor where you assemble agents and chatbots from modular nodes. Chatflow covers single-agent chatbots with tools and RAG. Agentflow covers multi-agent orchestration. Finished flows are called through APIs, SDKs or an embedded widget.

### How do I use the Flowise API?

Flowise exposes each flow at the prediction endpoint /api/v1/prediction/:id. You send a POST request with a JSON payload such as a question, and the response returns the flow's output. TypeScript and Python SDKs are also available.

### How do I use Flowise?

Install Flowise with npm, start it with npx flowise start, and open http://localhost:3000. From there you build flows visually in the editor. Docker Compose and Docker image setups are also documented.

## Sources

1. [FlowiseAI/Flowise on GitHub](https://github.com/FlowiseAI/Flowise)
2. [Flowise README](https://github.com/FlowiseAI/Flowise/blob/main/README.md)
3. [flowise on npm](https://www.npmjs.com/package/flowise)
4. [Flowise website](https://flowiseai.com)
5. [Release flowise@3.1.4 (Jul 29, 2026)](https://github.com/FlowiseAI/Flowise/releases/tag/flowise%403.1.4)
6. [Release flowise@3.1.3 (Jun 25, 2026)](https://github.com/FlowiseAI/Flowise/releases/tag/flowise%403.1.3)
7. [Release flowise@3.1.2 (Apr 14, 2026)](https://github.com/FlowiseAI/Flowise/releases/tag/flowise%403.1.2)
8. [Hacker News: Flowise is shutting down](https://news.ycombinator.com/item?id=49176920)
9. [Devtoolwatch Board, the week of Oct 25–31, 2026](https://index.devtoolwatch.com/)