Skip to content
← Back to site
Soleri | Docs

Getting Started

Soleri needs two things on your machine, plus one optional setup for native builds. If you already have these, skip to Step 2.

Soleri runs on Node.js. Check if you have it:

Terminal window
node -v

If the command isn’t found or shows a version below 18:

PlatformInstall command
macOSbrew install node (requires Homebrew) or download from nodejs.org
Linuxcurl -fsSL https://deb.nodesource.com/setup_22.x | sudo bash - && sudo apt-get install -y nodejs
WindowsDownload the installer from nodejs.org

npm ships with Node.js — no separate install needed.

Soleri connects to your AI editor via MCP (Model Context Protocol). You need at least one of these installed:

EditorInstall
Claude Code (recommended)npm install -g @anthropic-ai/claude-code — see Claude Code docs
Codexnpm install -g @openai/codex — see Codex docs
OpenCodego install github.com/opencode-ai/opencode@latest — see OpenCode docs

3. Build tools (optional — for the Knowledge Engine)

Section titled “3. Build tools (optional — for the Knowledge Engine)”

Soleri’s Knowledge Engine uses better-sqlite3, which requires native compilation. Scaffolding works without it, but the engine won’t start until build tools are available.

PlatformInstall command
macOSxcode-select --install
Linuxsudo apt-get install -y build-essential python3
WindowsInstall Visual Studio Build Tools or use WSL
Terminal window
node -v # should print v18.x or higher
npm -v # should print 8.x or higher
claude --version # if using Claude Code

One command to scaffold a file-tree agent in your current directory:

Terminal window
npm create soleri my-agent

This creates ./my-agent/ in whatever directory you run it from.

The interactive wizard asks for:

PromptWhat it means
Agent nameYour agent’s identity (e.g., “sentinel”, “architect”)
RoleOne-line description of what it does
DomainsKnowledge areas: frontend, backend, security, or custom
ToneHow the agent communicates: precise, mentor, pragmatic

This generates a folder — no TypeScript, no build step:

my-agent/
├── agent.yaml # Identity + engine config
├── agent-config.yaml # Capabilities, probes, workflow mappings
├── .mcp.json # Connects to Knowledge Engine (Claude Code)
├── opencode.json # Connects to Knowledge Engine (OpenCode)
├── settings.local.json # Claude Code hooks + pre-approved permissions
├── .gitignore # Excludes auto-generated files
├── CLAUDE.md # Auto-generated (never edit)
├── instructions/ # Behavioral rules
│ ├── _engine.md # Engine rules (auto-generated)
│ └── domain.md # Your domain-specific rules
├── workflows/ # Step-by-step playbooks
│ ├── feature-dev/
│ ├── bug-fix/
│ ├── code-review/
│ └── context-handoff/
├── flows/ # Flow YAML definitions
├── knowledge/ # Domain intelligence bundles
├── skills/ # SKILL.md files
├── hooks/ # Your AI editor hooks
├── data/ # Agent runtime data
└── workspaces/ # Workspace contexts

Your agent is ready to use immediately. No npm install, no npm run build.

From inside the agent folder, register the MCP server and start:

Terminal window
cd my-agent
soleri install --target claude # Claude Code (default)
soleri install --target opencode # OpenCode
soleri install --target codex # Codex
soleri install --target all # All editors
soleri dev # Start engine + watch for changes

soleri install registers the Soleri Knowledge Engine in your editor’s MCP config. soleri dev starts the engine and watches your agent folder — CLAUDE.md is regenerated automatically when you edit agent.yaml or instructions/.

After running soleri install, restart your AI editor. Your agent is available as a tool. The .mcp.json in your agent folder looks like:

{
"mcpServers": {
"soleri-engine": {
"command": "npx",
"args": ["@soleri/engine", "--agent", "./agent.yaml"]
}
}
}

Once connected, try these in your AI editor:

# Activate the persona
"Hello, My Agent!"
# Search your agent's knowledge
"Search for patterns about error handling"
# Capture something you learned
"Capture this pattern: always use error boundaries at route level"
# Check agent health
"Run a health check"

Your agent starts with starter knowledge and learns from every session.

Terminal window
# Check for updates
soleri agent status
# Update engine to latest version
npx @soleri/cli agent update
# Regenerate CLAUDE.md with latest engine rules
soleri agent refresh

To re-scaffold from scratch (e.g., after a major version bump):

Terminal window
rm -rf ~/.npm/_npx # clear stale npx cache
npm create soleri@latest my-agent

Edit files directly, no rebuild needed:

  • Add rules by creating a new .md file in instructions/
  • Add workflows by creating a new folder in workflows/ with prompt.md + gates.yaml
  • Add knowledge by dropping a JSON bundle in knowledge/
  • Change identity by editing agent.yaml

Run soleri dev and CLAUDE.md regenerates automatically on save.

If something isn’t working:

Terminal window
npx @soleri/cli doctor

Reports Node version, npm status, agent context, vault health, and engine connectivity.

If you run into issues, check Troubleshooting or reach out at hello@soleri.ai.