Flowise vs sim
The 55k-star visual builder for LLM apps and agents — drag-and-drop chatflows and Agentflows, hundreds of nodes, self-hostable Node.js. Now ARCHIVED upstream (see 'Future of Flowise'). — versus — Visual workspace to build, deploy and orchestrate AI agents — 1,000+ integrations, knowledge bases, built-in tables and files, schedules and run monitoring. Self-host via npx simstudio or Docker.
Direct successor category: same visual canvas for building and deploying agents, sim is actively developed with 1,000+ integrations while Flowise is archived.
| Flowise | sim | |
|---|---|---|
| Stars | 55k | 30k |
| Forks | 25k | 3.8k |
| Language | TypeScript | TypeScript |
| License | NOASSERTION | Apache-2.0 |
| Last activity | 29 days ago | yesterday |
| Topics | orchestration, agents | agents, orchestration |
| Curated connections | 5 | 4 |
Flowise — the curator's take
Flowise is the reference example of the visual-agent-builder category and still runs fine self-hosted, which is the only reason to reach for it today: the repo has been archived and development has stopped, so treat it as frozen. If you are starting new, go to sim or bytechef for the same drag-and-drop model with active maintenance, or to maxkb/claraverse if the RAG/chat-app angle matters more than the canvas. Existing Flowise deployments: plan the migration rather than extending them; the node ecosystem (LangChain/LlamaIndex bindings) will drift out of date quickly. Listed for lineage and for the many teams who still run it.
sim — the curator's take
The n8n-for-agents play at real scale (29k stars): build agents visually, conversationally, or in code, wire them to Slack/Notion/Salesforce-class integrations, and keep tables, files, knowledge bases and scheduled runs in the same workspace — it's a platform, not a library. Self-hosting is honest but heavy: Docker with 12GB+ RAM recommended, Postgres + pgvector, and note that the Chat/copilot feature remains a Sim-managed service even self-hosted (you fetch a COPILOT_API_KEY from sim.ai). Ollama/vLLM local models supported. Pick it when non-engineers need to build and operate agents; pick a code-first control plane (agentfield) when engineers do, and skip the platform entirely for a single agent.