Shared memory for AI coding agents

Stele is shared memory for AI coding agents: one record of what your project has decided, what it is working on, and what it has learned the hard way. Every agent reads it before it acts and writes back to it as it works. Switch tools or start a new session, and the context stays.

Claude Code, Cursor, Codex, Antigravity, Copilot, OpenCode, Grok Build, Kimi Code CLI, Pi, DeepSeek Harness, and Meta Muse, plus any MCP-compatible client and the stele CLI. They all read and write the same project record, so it stops mattering which one you happen to be in.

Yes. Running stele install sets Stele up in Meta Muse, Meta's coding agent, as a plugin with the same commands and skills as in Claude Code, automatic recall before each answer, and the Stele tools. The memory lives in your project, not in the model, so it works the same whichever Muse model you run, Muse Wonder included, and it carries over when you switch between Muse and another agent.

Because that memory is yours and Stele's is the project's. Built-in agent memory learns what you do inside one tool, so a teammate on a different agent starts cold, and so do you the moment you switch. A file like CLAUDE.md or AGENTS.md gets further, since it lives in the repo where the whole team can see it, but it holds the house rules you want followed, and it is a document somebody has to keep writing by hand. Stele holds what the project has decided, tried, and learned, and it belongs to the project itself, so it reaches whoever is working and whatever they are working in. A decision one person's agent recorded on Tuesday is there for someone else's agent on Friday. The two do different jobs, so keep the file and add the record.

Create an account at stele-ai.dev and you're in. The Free plan is $0 forever: unlimited public projects, one private project, 500 new entries a month with 5,000 stored, and a monthly assistant allowance. Reading, searching and editing what you have already saved are never capped. Sign in with GitHub, Google, or an email link, and the account is created the first time. When a project outgrows Free, Indie is $5.99 a month for three private projects, Pro is $12 a month and Team is $20 a person a month, with the full comparison at stele-ai.dev/pricing.

Yes. Public projects are open to read with no account at app.stele-ai.dev/explore, so you can see the decisions, lessons, and tasks real projects keep for their agents. You can also add Stele to ChatGPT from its app directory, which works on a phone, and connect your coding agent later with the same account. The command line tool only comes in when you want the coding agent on your computer to use Stele.

A file has no opinion about what's still true. You reverse a decision, but the old one is still sitting there, and weeks later an agent reads it, believes it, and rebuilds the thing you tore out. Nothing flagged it, because a file can't tell when it has gone wrong. Stele can. A reversed decision is retired: still visible, still explaining itself, but no longer served as truth, and whatever replaced it comes back alongside, carrying the reason for the change. Resolved risks retire themselves, and facts that have drifted get flagged for review. Any of those tools will hold the note perfectly well. The open question is what keeps it true a year later. Full walkthrough at stele-ai.dev/docs/conflicting-facts.

Yes. Stele is hosted, so you reach your project from any device without opening the repo. Create tasks, jot ideas, and get detailed answers with no source code or computer in front of you. Non-coding agents like ChatGPT connect over MCP and get the same context your coding agent has, down to the task in progress.

Those give you a store or a retrieval library. You still have to wire and operate the whole loop yourself: read context before every prompt, write it back mid-task, claim tasks, keep it current, and make it work across every agent. Stele is that loop, already built, hosted, and shared across your tools and teammates. If the open tools already fit your needs, they're the right choice, and an open, SQLite-backed version of Stele is planned for self-hosting. The managed version is for when you want the cross-agent record that just works everywhere.

Yes. A project is visible only to its members unless you publish it, and your source code stays on your machine. We never sell your data. You can export or delete everything yourself, anytime.

We do not use what you store in Stele to train machine-learning models, except to improve a feature you have explicitly turned on in your own account. Nothing is used for training by default, and we never sell your data. The privacy policy at stele-ai.dev/privacy sets out this commitment.

No. Stele is hosted, so there's nothing to run. Install the CLI, sign in, and point it at a project; a new contributor, human or agent, is productive from day one.