Website: https://statespace.com
Documentation: https://docs.statespace.com
AI doesnβt know your data, but it knows Unix and filesystems. Statespace lets you transform your files and CLI tools into shareable data apps that any agent can discover and use. Build database explorers, share business rules, or document legacy APIs. Once youβve created an app, deploy and monitor it with our cloud platform.
$ curl -fsSL https://statespace.com/install.sh | bash
Run statespace init in the current directory:
$ statespace init
Add constrained CLI tools to README.md or any other Markdown file:
---
tools:
- [grep]
- [python, scripts/summarize.py]
- [sqlite3, data/app.db, { regex: "^(SELECT|EXPLAIN)\\b.*" }]
---
# Instructions
- Only run read-only queries against the database
- Use `summarize.py` for aggregations and report generation
- Use `grep` to search across local files and logs
Alternatively, let your coding agent build it out for you:
$ claude "Document my database schema and add tools to query it"
Run your app locally:
$ statespace run --port 8000
Agents and HTTP clients can now read pages and execute tools:
# Read a page
$ curl http://localhost:8000/README.md
# Execute a CLI tool
$ curl -X POST http://localhost:8000/README.md \
-H "Content-Type: application/json" \
-d '{"command": ["grep", "-r", "revenue", "."]}'
Deploy your app to the cloud:
$ statespace deploy --name demo
Your app is now live at a public URL:
$ curl https://demo.statespace.app/README.md
Point any agent at the URL directly:
$ claude "Use the API at https://demo.statespace.app to break down revenue by region"
Or wire it up as an MCP server:
"mcpServers": {
"statespace": {
"command": "npx",
"args": ["-y", "statespace-mcp", "https://demo.statespace.app"]
}
}
psql, sqlite3, grep, python β if it runs in a shell, it worksThis project is licensed under the terms of the MIT license.