Install & first run
Two commands put Stele on your machine; one more, inside the agent you already use, wires it into a project. After that you don't run anything special — you just keep prompting, and the record fills in around you.
1. Install the CLI
The stele CLI is a single binary that wires into your shell. One line installs it on macOS, Linux, or Windows — no runtime to set up, nothing to configure.
2. Sign in
Sign in once with GitHub, Google, or an email link. There's no separate account to create and no key to paste — the CLI opens your browser, you approve, and you're in.
Stele is invite-only while we open up gradually, and free during the beta. Sign in with the email your invite was sent to. If you're on the waitlist, you'll get an email the moment a spot opens.
3. Wire it into a project
Open the project in the agent you already use and run the start command once. Stele binds itself to the project, maps the codebase and any docs it finds, and builds the first record. You approve what it's about to do before it does it.
The way you invoke it depends on the harness, but the behavior is identical everywhere:
- Claude Code and Cursor —
/stele:startand the other/stele:*slash commands. - Codex, Antigravity, and Copilot — the same commands as skills.
- OpenCode — an in-process plugin.
- Any other MCP-compatible client — connects to the Stele MCP server directly and walks the same record.
Already have history in the repo? Backfill seeds the record from your existing code, git history, and docs — your agent reads them and writes what it finds into the graph.
4. Keep working
That's the whole setup. From here you prompt your agent the way you always have. Before each answer, Stele quietly pulls the decisions, lessons, and risks that bear on what you asked; as work happens, it writes new knowledge and tasks back. Nothing to remember, nothing to maintain by hand.
A good first move is to ask the agent to take stock — it'll read the record and tell you where things stand.
What's the current state of this project? Check Stele for open tasks, recent decisions, and any risks I should know about before I start.