SeaShell Cloud is the optional commercial control plane for SeaShell. It manages accounts, entitlements, release manifests, and allowlisted telemetry, while the agent keeps running on your machine with your own model keys. By design the control plane never requires repo contents, prompts, diffs, terminal output, local indexes, embeddings, model outputs, provider request bodies, file paths, filenames, or credentials.
What the control plane does
SeaShell Cloud is split into three services: a cloud API for accounts, entitlements, releases, devices, sync, and telemetry intake; a model router for optional hosted routing; and a worker for billing reconciliation, usage rollups, and release validation.
This is the commercial layer around the local agent. It answers questions like is this seat entitled, what is the current stable release, and which devices are registered. It is deliberately separate from the runtime: the local product consumes SeaShell Cloud through published API contracts only, so cloud availability never blocks local work.
What it is designed never to see
The privacy boundary is explicit. Ordinary control-plane operations must not require repo contents, prompts, diffs, terminal output, local indexes, embeddings, model outputs, provider request bodies, file paths, filenames, or credentials.
That list is a design constraint, not a policy promise. Because your source, prompts, and keys are never part of a control-plane request, there is nothing of that kind for the cloud to log, cache, train on, or leak. Privacy is preserved by what the API accepts, not by what a retention policy says will be discarded later.
Telemetry stays allowlisted
Telemetry intake accepts only an allowlisted event envelope. It rejects values that look like prompts, model output, provider bodies, or file paths before they are ever stored.
Install and usage signals move through a narrow, typed contract so product analytics never becomes a backdoor for code or content. Entitlement and usage reads are gated by token in staging; release and installer manifests expose only public, non-entitlement artifact metadata.
Frequently asked questions
- Does SeaShell Cloud see my code or prompts?
- No. The control plane is designed so ordinary operations never require repo contents, prompts, diffs, embeddings, model outputs, provider request bodies, file paths, or credentials.
- Is SeaShell Cloud required to use SeaShell?
- No. The agent runs locally with your own model keys. SeaShell Cloud is the optional commercial control plane for accounts, entitlements, releases, and telemetry.
- What is SeaShell Cloud actually for?
- Accounts and entitlements, release and installer manifests, device registration and sync, optional hosted model routing, and allowlisted telemetry and billing.
- What telemetry does it collect?
- Only an allowlisted event envelope. Values that look like prompts, model output, provider bodies, or file paths are rejected before storage.
Try SeaShell in your terminal
The terminal-native AI coding agent. Free core, single binary.
Install SeaShellRelated guides
Atlas for Julia: A Terminal-Native AI Coding Agent for Project.toml Packages in 2026
Atlas is a terminal-native AI coding agent for Julia in 2026. It reads dispatch signatures and Project.toml [deps], fixes type instabilities, runs Pkg.test(), and applies JuliaFormatter.
Atlas with DeepSeek V4 Flash in 2026
Explore DeepSeek V4 Flash for Atlas in 2026. This model offers a 1M token context window and robust reasoning at an input cost of $0.14 per Mtok, ideal for driving Atlas's subagents and complex coding tasks.
Atlas for Groovy: A Terminal-Native AI Coding Agent for Gradle, Spock, and Jenkins in 2026
Atlas is a terminal-native AI coding agent for Groovy in 2026. It reads build.gradle closures and Jenkinsfiles, writes Spock specs, runs ./gradlew test, and applies Spotless.
Atlas vs Poolside: Terminal AI Coding Agents in 2026
Compare Atlas and Poolside in 2026. Atlas offers a terminal-native TUI with permission-gated tools and a free core. Poolside provides open-weight Laguna models and on-prem deployment options.
Atlas for OCaml: A Terminal-Native AI Coding Agent for dune and opam Projects in 2026
Atlas is a terminal-native AI coding agent for OCaml in 2026. It reads dune stanzas and .mli signatures, runs dune runtest behind a prompt, and finishes with ocamlformat.
Atlas vs Aider: Terminal AI Coding Agents in 2026
Compare Atlas and Aider, two terminal AI coding agents for 2026. Atlas offers a rich TUI, interactive plan approval, and plugin support. Aider features git-revision commits and repo-map awareness.
Atlas with Command A Plus in 2026
Explore Atlas with Cohere's Command A Plus in 2026. This model offers private VPC/on-prem deployment and strong RAG capabilities, ideal for regulated teams, despite its 128K context window and generalist nature.
Atlas with Command R+ in 2026
Explore Command R+ for Atlas in 2026. This Cohere frontier model offers strong multi-step tool use and a 128,000 token context, ideal for Atlas's code indexing and agent actions.