Vigile
SearchContents

The ideas, one at a time, each with a picture

How it works

Nine short pages, one idea each, each with a picture. The first five are the reasons to choose Vigile; the last four say how it runs.

Vigile is one service that holds one plan: items, and links between them. Every change goes through an operation that is checked against the plan before it is stored. What can start, what waits and where the plan contradicts itself are worked out from it whenever someone asks.

Four ways into one service AI agents reach the service over MCP at /mcp. Programs call the HTTP API at /api, and so does the vigile command line. People open the web page, which reads through the API. All of them arrive at one engine, where every operation is defined once with its input, rules and refusals. The engine keeps the plan in one data folder, in SQLite. AI agents tools, over MCP Programs JSON, over HTTP You, and scripts the vigile command People a browser /mcp /api/<operation> / the page reads The engine: every operation, defined once its input, its rules, its refusals, and who may call it ONE SERVICE: ONE PROCESS, ONE PORT One data folder the plan, in one SQLite file
One service holds the plan. Agents, programs, the command line and the page all go through the same operations, and so through the same rules.

The ideas

The plan

The service

These ideas are also why the vision reaches further than the product does today. To run it, go to Install and first run. For the exact input of an operation, a setting or a command, see the documentation.