Apache-2.0 alternative to n8n for agentic workflow automation. 27K stars in ~4 months, 240 HN points with 61 comments ('Apache-2.0 n8n alternative'). $7M Series A. License differentiator vs n8n's 'fair-code' Sustainable Use License.
Where it wins
27K GitHub stars in ~4 months — strong growth
240 HN points, 61 comments — genuine developer traction
Apache-2.0 license — true open-source vs n8n's 'fair-code' license
$7M Series A funding
Where to be skeptical
Revenue and enterprise evidence is thin — too early to challenge n8n
~4 months old — execution risk remains high
No named enterprise customers
Editorial verdict
The only credible open-source alternative to n8n for workflow automation. Apache-2.0 license is a genuine differentiator for teams that need true open-source. Revenue and enterprise evidence is thin — too early to challenge n8n's 3,000+ enterprise customers, but the trajectory is promising.
Source
Related
Claude Code
98Anthropic's official agentic coding CLI. v2.1.81 (Mar 20) shipped `--bare`, smarter worktree resume, and improved MCP OAuth while the repo crossed 82,204 stars and logged ~14 commits/week across 10+ maintainers. Terminal-native, tool-use-driven, with deep file system + shell access, #1 SWE-bench Pro standardized (45.89%), ~4% of GitHub public commits (SemiAnalysis), $2.5B annualized revenue. 8M+ npm weekly downloads. Opus 4.6 with 1M context.
LangGraph
95#1 Python agent framework by production evidence — 40.2M PyPI downloads/month, Fortune 500 deployments (LinkedIn, Uber, Replit, Elastic, Klarna, Cloudflare, Coinbase), ~400 LangGraph Platform companies, LangSmith rated best-in-class observability. Stable v1.x API, model-agnostic, MCP support.
Pydantic AI
95#3 Python agent framework by downloads — 15.6M PyPI/month. Built by the Pydantic team. Runtime type enforcement is a genuine differentiator no other framework offers. V1 shipped with Temporal integration for durable execution and Logfire observability. Emerging pattern: 'Pydantic AI for agent logic, LangGraph for orchestration' (ZenML).
AutoGen (Microsoft)
95⚠️ MAINTENANCE MODE — Microsoft officially confirmed bug fixes and security patches only, no new features (VentureBeat 2026-02-19). 55.9K stars but only 1.57M PyPI/month — DL/star ratio of 28, the most inflated among active frameworks. Being replaced by Microsoft Agent Framework (AutoGen + Semantic Kernel merge, GA targeted ~Q2 2026). Teams on AutoGen should plan migration.
Public evidence
Positioned explicitly as 'Apache-2.0 n8n alternative' on HN. License differentiator resonated — n8n's 'fair-code' license is a known pain point for self-hosters.
Early-stage funding provides runway but does not yet validate enterprise adoption.
Raw GitHub source
Constrained peek so you can sanity-check the source material without leaving the site.
Your AI command center. Describe what you want in plain language. Mothership knows your entire workspace and takes action: building agents, running them, querying data, and more.
<p align="center"> <img src="https://raw.githubusercontent.com/simstudioai/sim/main/apps/sim/public/static/mothership.gif" alt="Mothership building and running an agent from chat" width="800"/> </p>Generate documents, reports, and presentations from a single prompt, grounded in your workspace data.
<p align="center"> <img src="https://raw.githubusercontent.com/simstudioai/sim/main/apps/sim/public/static/files.gif" alt="Mothership generating a document from a prompt" width="800"/> </p>Upload documents to a knowledge base and let agents answer questions from your own content.
<p align="center"> <img src="https://raw.githubusercontent.com/simstudioai/sim/main/apps/sim/public/static/knowledge.gif" alt="Creating a knowledge base" width="460"/> </p>A database, built in. Store, query, and wire structured data into agent runs.
<p align="center"> <img src="https://raw.githubusercontent.com/simstudioai/sim/main/apps/sim/public/static/tables.png" alt="Tables view with typed columns" width="800"/> </p>Prefer a canvas? Design agents block by block in the visual builder, and let Copilot generate blocks, wire variables, and fix errors from natural language.
<p align="center"> <img src="https://raw.githubusercontent.com/simstudioai/sim/main/apps/sim/public/static/workflow.gif" alt="Workflow builder demo" width="800"/> </p>npx simstudio
→ http://localhost:3000
Docker must be installed and running on your machine.
| Flag | Description |
|---|---|
-p, --port <port> | Port to run Sim on (default 3000) |
--no-pull | Skip pulling latest Docker images |
git clone https://github.com/simstudioai/sim.git && cd sim
docker compose -f docker-compose.prod.yml up -d
Open http://localhost:3000
Sim also supports local models via Ollama and vLLM. See the Docker self-hosting docs for setup details.
Requirements: Bun, Node.js v20+, PostgreSQL 12+ with pgvector
git clone https://github.com/simstudioai/sim.git
cd sim
bun install
bun run prepare # Set up pre-commit hooks
docker run --name simstudio-db -e POSTGRES_PASSWORD=your_password -e POSTGRES_DB=simstudio -p 5432:5432 -d pgvector/pgvector:pg17
Or install manually via the pgvector guide.
cp apps/sim/.env.example apps/sim/.env
# Create your secrets
perl -i -pe "s/your_encryption_key/$(openssl rand -hex 32)/" apps/sim/.env
perl -i -pe "s/your_internal_api_secret/$(openssl rand -hex 32)/" apps/sim/.env
perl -i -pe "s/your_api_encryption_key/$(openssl rand -hex 32)/" apps/sim/.env
# DB configs for migration
cp packages/db/.env.example packages/db/.env
# Edit both .env files to set DATABASE_URL="postgresql://postgres:your_password@localhost:5432/simstudio"
cd packages/db && bun run db:migrate
bun run dev:full # Starts Next.js app and realtime socket server
Or run separately: bun run dev (Next.js) and cd apps/sim && bun run dev:sockets (realtime).
Copilot is a Sim-managed service. To use Copilot on a self-hosted instance:
COPILOT_API_KEY environment variable in your self-hosted apps/sim/.env file to that value