Build privately with SeaShell

SeaShell is a model-agnostic, terminal-native AI coding agent for developers and teams that want control over their model routes, code context, tools, and approval flow.

SeaShell is designed around four operating principles:

• Bring your own models. Use hosted, local, self-hosted, or approved open-source models based on the work.
• Keep private work private. Local embeddings, permission gates, and auditable tool calls help protect client and company code.
• Use agents intentionally. SeaShell can plan, build, review, and coordinate multiple agents when a task is large enough.
• Stay in the terminal. Sessions, diffs, approvals, models, MCP tools, and copy formats are all reachable from the TUI.

SeaShell ships as a single binary. Install it, restart your shell if needed, then run seashell --version to confirm your PATH.

macOS and Linux

curl -fsSL https://seashell.sh/install | sh

Windows PowerShell

irm https://seashell.sh/install.ps1 | iex

SeaShell works without an account. A free account gives this installation an authenticated SeaShell identity and lets SeaShell read the account's effective entitlement when account features are used.

Run seashell signup and enter your email. SeaShell sends a six-digit code: a new email creates a free account, while an existing email signs back in. No password is created or entered in the terminal.

seashell signup

# These names open the same passwordless flow:
seashell signin
seashell login

Open SeaShell in a repository and describe the outcome. SeaShell reads the project, chooses the right context, proposes a plan when needed, and shows work as reviewable terminal output.

cd ~/code/your-project
seashell

> Review this API change, update the tests, and call out any risky migrations.

For larger work, say what you want operationally. Phrases like use multiple agents, parallelize the review, or split this into agents are signals that SeaShell should coordinate separate discovery, implementation, and verification lanes.

SeaShell has a dedicated upgrade command. Use it instead of passing update flags to the default TUI command.

seashell upgrade
atlas --version

If a different machine has newer repository code, pull that repository with git and rebuild from source as needed. If you installed from the public installer, seashell upgrade updates the installed binary.

SeaShell is model-agnostic. List available models, authenticate providers, and select the model that fits the task, budget, and data policy.

seashell providers
seashell models
seashell models --refresh
seashell --model anthropic/claude-sonnet-4-5

SeaShell brings your own keys. Set a provider's environment variable, or run seashell providers to authenticate interactively, and SeaShell registers that provider's models automatically. A provider counts as configured as soon as any one of its environment variables is set.

The table below is providers, not models. SeaShell does not maintain a model list: the catalog comes from models.dev and is refreshed with seashell models --refresh, so any model IDs written here would be stale within a release. Run seashell models <provider> for the live list.

export ANTHROPIC_API_KEY=sk-ant-...
seashell models anthropic
seashell --model anthropic/claude-opus-5

Use a local model route when client requirements or internal policies require model calls to stay on your machine or approved infrastructure. SeaShell can discover Ollama and LM Studio when you explicitly run the local-model command.

ollama list
ollama pull qwen2.5-coder:latest
seashell models --local

Agents are reusable operating modes. Use primary agents for normal work and subagents for focused research, review, migration, or testing lanes.

seashell agent list
atlas agent create

Specialized agents live in SeaShell configuration and can carry their own instructions, model preference, and permission profile. Keep them small and purpose-built: reviewer, migration planner, test fixer, security checker, or documentation writer.

Workflows turn repeated senior-engineering patterns into reusable execution paths. Use them when a task needs coordination across files, tests, reviews, or agents.

Use multiple agents: one for TUI routing, one for tests, one for docs.
Run a review workflow before committing this branch.
Use a workflow to migrate this feature and verify the build.

SeaShell gathers context from the repository, session history, project files, command output, and available tools. For large codebases, ask it to map the relevant area before editing.

• Use /init to create project guidance SeaShell can read later.
• Ask for a file map before broad migrations.
• Prefer scoped prompts that name the subsystem, test, or failure.
• Use local embeddings when code search must stay private.

The resource hubs expand this further with guides for private AI development, local model orchestration, agentic workflows, and codebase intelligence. Browse resource hubs

SeaShell treats tool calls as actions that should be classified and gated. Read-only discovery, file edits, shell commands, network calls, and secret-bearing operations do not carry the same risk.

{
  "permission": "ask",
  "agent": {
    "default_agent": "build"
  }
}

SeaShell reads global configuration plus project-level configuration. Use project config for repository conventions and global config for personal defaults.

{
  "model": "ollama/qwen2.5-coder:latest",
  "theme": "atlas",
  "permission": "ask"
}

Environment variables and command flags can override config when you need a one-off model, session, or server mode.

Plugins extend SeaShell directly. MCP connects SeaShell to external tools and context providers through the Model Context Protocol. Both should follow the same permission discipline as built-in tools.

seashell mcp add
seashell mcp list
seashell mcp auth <name>
seashell mcp debug <name>

Sessions keep work durable across restarts and machines when the same repository and data are available. Continue the last session, resume a known session ID, or fork a session when you want a new branch of work.

seashell --continue
seashell --session ses_abc123
seashell --session ses_abc123 --fork
seashell session list

SeaShell Cloud is the optional commercial control plane. The agent keeps running locally with your own model keys; SeaShell Cloud adds accounts, entitlements, release manifests, device registration, sync, and allowlisted telemetry on top.

It is designed so ordinary control-plane operations never require your repo contents, prompts, diffs, terminal output, local indexes, embeddings, model outputs, provider request bodies, file paths, or credentials. The local product talks to SeaShell Cloud through published API contracts only, so cloud availability never blocks your work.

Learn more: the privacy-preserving control plane.

SeaShell verifies licenses offline against a key built into the binary, so Pro and Company features unlock air-gapped with no phone-home. SeaShell Cloud resolves entitlements and holds billing records, but the runtime does not need a live connection to confirm what a seat is allowed to do.

• Core is free, forever.
• Pro is a one-time, per-seat license you own, including every update within its major version.
• Company is per-seat, annual, with SSO, RBAC, audit logs, and continuous updates while active.

Bring-your-own-keys and local models are the default. For teams that want one place to set provider policy, enforce rate limits, and account for spend, SeaShell Cloud offers an optional hosted model router behind an SeaShell runtime feature flag.

The router manages routing, provider policy, credit checks, rate limits, and usage events, so an organization can standardize and meter model access without distributing raw provider keys to every seat. It records usage (which model, how much), not the content of your requests.

{
  "cloud": {
    "model_router": true
  }
}

Learn more: hosted model routing without giving up bring-your-own-keys.

Telemetry intake accepts only an allowlisted event envelope. Values that look like prompts, model output, provider bodies, or file paths are rejected before they are ever stored, so product analytics never becomes a backdoor for your code or content.

Release and installer manifests expose only public, non-entitlement artifact metadata. Entitlement and usage reads are token-gated. The privacy boundary is a design constraint on what the API accepts, not a policy you have to take on faith.

Treat the model route, SeaShell operating mode, MCP servers, plugins, provider keys, and local services as one data-flow decision. A local model alone does not make every configured integration local.

• Record whether SeaShell will run offline, against a private endpoint, or against a hosted provider.
• List every MCP server, plugin, credential, local service, and network destination enabled for the workflow.
• Choose allow, ask, and deny rules that match the repository and user role.
• Confirm telemetry and update behavior for the selected operating mode.
• Decide whether any Syntora-operated service will receive, maintain, or transmit PHI before discussing a BAA.
• Review the current assurance status instead of assuming a certification from a product feature.

Use the Security and Trust page, integration evidence, and machine-readable security record as the starting packet.

Open the command palette with ctrl p, or type a slash command directly into the prompt.

Use CLI commands for updates, scripting, model inspection, server modes, and managing agents or MCP servers. Every command, flag, and default is listed in the full CLI reference.

SeaShell is keyboard-first. The essentials:

SeaShell ships with its own dark terminal theme and can load custom JSON themes from your SeaShell config directory. Use /themes to switch from the TUI.

{
  "name": "midnight",
  "theme": {
    "primary": "#6aa6f5",
    "background": "#0c0c0c",
    "text": "#e6e9ee"
  }
}

The seashell command is not found

Restart your shell so the updated PATH takes effect, or re-run the install script. On Windows, reopen PowerShell or Windows Terminal.

SeaShell says it is already installed

Use seashell upgrade. If you built SeaShell from source, pull the repo, rebuild the package, and make sure your PATH points at the rebuilt binary.

A model is missing

Run seashell models --refresh. For local models, confirm the model exists with ollama list and that Ollama is running.