Skip to main content

​
Local Deployment

Run Myrm on your own machine with full control over your data.

​
One-liner install (fastest)

macOS / Linux / Git Bash 
curl -fsSL https://myrmagent.ai/install.sh | bash
myrm start
Windows (PowerShell) 
irm https://myrmagent.ai/install.ps1 | iex
myrm start
Open http://localhost:3000 and add your LLM API key in Settings. Harness comes from PyPI; no separate harness repo required for self-host.

​
Clone and develop (OSS repo)

git clone https://github.com/Pursue-LLL/myrm-agent.git
cd myrm-agent
myrm setup          # uv sync + bun install
myrm start          # backend (terminal 1)
cd myrm-agent-frontend && bun run dev   # frontend (terminal 2)
Dev scripts live under scripts/ in the open-source repo so contributors clone once and run locally.

​
Prerequisites (Docker path)

  • Docker 24+ and Docker Compose v2
  • 4GB RAM minimum (8GB recommended)
  • 10GB disk space

​
Docker Compose

git clone https://github.com/Pursue-LLL/myrm-agent.git
cd myrm-agent/myrm-agent-server
cp .env.example .env   # if present
docker compose up -d

​
Configuration

Edit .env to set your API keys: 
# LLM Provider (at least one required)
OPENAI_API_KEY=sk-...
ANTHROPIC_API_KEY=sk-ant-...

# Optional: Additional providers
DEEPSEEK_API_KEY=...
GOOGLE_API_KEY=...
See Environment Variables for the full reference.

​
Verify Installation

curl http://localhost:3000/api/health
Expected response: 
{ "status": "ok" }

​
Production Docker builds (OSS server image)

When building the open-source server image from pre-built harness wheels, the builder selects the correct platform core wheel via BuildKit TARGETPLATFORM and runs verify-harness-distribution before the image is considered ready. Mismatched or incomplete installs fail at build/startup time—not mid-conversation. See the harness distribution guide in the monorepo: myrm-agent-harness/harness_packaging/DISTRIBUTION_SYSTEM.md.

​
Updating

git pull
docker compose pull
docker compose up -d