Documentation
Build privately with Atlas
Install Atlas, connect your models, organize agents and workflows, and keep control of code, context, and client data from the terminal.
curl -fsSL https://runatlas.sh/install | shAtlas 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.
Atlas 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. Atlas 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.
Atlas ships as a single binary. Install it, restart your shell if needed, then run atlas --version to confirm your PATH.
macOS and Linux
curl -fsSL https://runatlas.sh/install | shWindows PowerShell
irm https://runatlas.sh/install.ps1 | iexatlas upgrade on each machine. Atlas updates the local binary on that device; repository changes still move through git.Atlas works without an account. A free account gives this installation an authenticated Atlas identity and lets Atlas read the account's effective entitlement when account features are used.
Run atlas signup and enter your email. Atlas 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.
atlas signup
# These names open the same passwordless flow:
atlas signin
atlas loginatlas logout at any time to remove the linked account from this machine.Open Atlas in a repository and describe the outcome. Atlas reads the project, chooses the right context, proposes a plan when needed, and shows work as reviewable terminal output.
cd ~/code/your-project
atlas
> 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 Atlas should coordinate separate discovery, implementation, and verification lanes.
atlas run. For interactive work, use the TUI so you can inspect plans, approvals, sessions, and model choices as the task evolves.Atlas has a dedicated upgrade command. Use it instead of passing update flags to the default TUI command.
atlas upgrade
atlas --versionIf 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, atlas upgrade updates the installed binary.
Atlas is model-agnostic. List available models, authenticate providers, and select the model that fits the task, budget, and data policy.
atlas providers
atlas models
atlas models --refresh
atlas --model anthropic/claude-sonnet-4-5| Hosted provider | Use provider/model IDs after authenticating your provider. |
| Local Ollama | Use local models and embeddings when client data must stay on your machine. |
| Model picker | Switch providers, models, variants, and effort without rebuilding the project. |
| Per-run override | Pass --model provider/model when launching Atlas or atlas run. |
Atlas brings your own keys. Set a provider's environment variable, or run atlas providers to authenticate interactively, and Atlas 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. Atlas does not maintain a model list: the catalog comes from models.dev and is refreshed with atlas models --refresh, so any model IDs written here would be stale within a release. Run atlas models <provider> for the live list.
export ANTHROPIC_API_KEY=sk-ant-...
atlas models anthropic
atlas --model anthropic/claude-opus-5claude-3-5-sonnet and gpt-4o still appear in setup guides across the web and no longer resolve. atlas models <provider> reads the live catalog and is the only list worth copying from.AnthropicANTHROPIC_API_KEY
Claude models. Strong on long-horizon agentic coding.
atlas models anthropicCurrent models include claude-opus-5, claude-sonnet-5, claude-haiku-4-5.
OpenAIOPENAI_API_KEY
GPT models, plus the o-series reasoning models.
atlas models openaiRun the command above for this provider's current models. Atlas reads the live catalog rather than a list maintained here.
GoogleGOOGLE_GENERATIVE_AI_API_KEY
Gemini models via Google AI Studio.
atlas models googleRun the command above for this provider's current models. Atlas reads the live catalog rather than a list maintained here.
OpenRouterOPENROUTER_API_KEY
One key, most models. The fastest way to try a model you do not have a key for.
atlas models openrouterRun the command above for this provider's current models. Atlas reads the live catalog rather than a list maintained here.
xAIXAI_API_KEY
Grok models.
atlas models xaiRun the command above for this provider's current models. Atlas reads the live catalog rather than a list maintained here.
Azure OpenAIAZURE_OPENAI_API_KEY
OpenAI models under an Azure tenancy, for teams with an existing Azure agreement.
atlas models azureRun the command above for this provider's current models. Atlas reads the live catalog rather than a list maintained here.
Amazon BedrockAWS_BEARER_TOKEN_BEDROCK
Also accepts standard AWS credentials and container credential roles.
atlas models amazon-bedrockRun the command above for this provider's current models. Atlas reads the live catalog rather than a list maintained here.
Cloudflare Workers AICLOUDFLARE_API_TOKEN
Models hosted on Cloudflare's edge network.
atlas models cloudflareRun the command above for this provider's current models. Atlas reads the live catalog rather than a list maintained here.
Ollama or LM Studio (local)
No provider key is required. Atlas probes Ollama on port 11434 and then LM Studio on port 1234 when you run atlas models --local. You can also point ATLAS_LOCAL_MODEL_URL at an OpenAI-compatible local endpoint.
atlas models --localUse a local model route when client requirements or internal policies require model calls to stay on your machine or approved infrastructure. Atlas can discover Ollama and LM Studio when you explicitly run the local-model command.
ollama list
ollama pull qwen2.5-coder:latest
atlas models --localAgents are reusable operating modes. Use primary agents for normal work and subagents for focused research, review, migration, or testing lanes.
atlas agent list
atlas agent createSpecialized agents live in Atlas 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.
| Single task | Ask Atlas to make a focused change, then review the plan and diff. |
| Review | Use /review for branches, uncommitted work, PR prep, and delivery checks. |
| Parallel agents | Ask Atlas to use multiple agents when discovery, migration, testing, or review can run in parallel. |
| Large codebase | Use workflows and context-aware search so Atlas can narrow the right files before editing. |
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.Atlas 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
/initto create project guidance Atlas 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
Atlas 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"
}
}Atlas 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 Atlas directly. MCP connects Atlas to external tools and context providers through the Model Context Protocol. Both should follow the same permission discipline as built-in tools.
atlas mcp add
atlas mcp list
atlas mcp auth <name>
atlas 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.
atlas --continue
atlas --session ses_abc123
atlas --session ses_abc123 --fork
atlas session listAtlas Cloud is the optional commercial control plane. The agent keeps running locally with your own model keys; Atlas 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 Atlas Cloud through published API contracts only, so cloud availability never blocks your work.
| cloud-api | Accounts, entitlements, releases, devices, sync, and telemetry intake. |
| model-router | Optional hosted model routing, provider policy, credits, and rate limits. |
| cloud-worker | Billing reconciliation, usage rollups, retention, and release validation. |
Learn more: the privacy-preserving control plane.
Atlas verifies licenses offline against a key built into the binary, so Pro and Company features unlock air-gapped with no phone-home. Atlas 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, Atlas Cloud offers an optional hosted model router behind an Atlas 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, Atlas 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.
| Local and offline | Use a local model endpoint plus atlas --offline or ATLAS_OFFLINE=1 to block other outbound Atlas traffic. |
| Private endpoint | Use an approved OpenAI-compatible endpoint with the organization's network, identity, logging, and retention controls. |
| Hosted provider | Treat the selected provider as an external data boundary and review its contract and data policy. |
- Record whether Atlas 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.
| /models | Switch model, provider, variant, or reasoning mode |
| /agents | Choose a primary agent or specialized subagent |
| /workflow | Open repeatable workflows for review, refactor, and multi-agent work |
| /review | Review uncommitted changes, branches, PRs, or delivery state |
| /mcps | Inspect configured Model Context Protocol servers |
| /sessions | Resume, fork, or continue previous sessions |
| /themes | Switch Atlas themes |
| /copy-as-slack | Copy the last assistant message as Slack-ready mrkdwn |
| /copy-as-gmail | Copy the last assistant message as email-ready text |
| /help | Open the in-app help surface |
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.
| atlas | Start the TUI in the current directory |
| atlas signup | Create or sign in to a free Atlas account with a six-digit email code |
| atlas upgrade | Update Atlas to the latest or a specific version |
| atlas models [provider] | List available models from configured providers |
| atlas providers | Manage provider credentials and authentication |
| atlas mcp | Add, list, authenticate, debug, and remove MCP servers |
| atlas agent | Create and list reusable Atlas agents |
| atlas run [message] | Run Atlas non-interactively for scripts and automation |
| atlas session | List, resume, fork, export, or delete sessions |
| atlas serve | Start a headless Atlas server |
| atlas web | Start the server and open the web interface |
Atlas is keyboard-first. The essentials:
| tab | Move between prompt, agents, and command surfaces |
| ctrl p | Open the command palette |
| enter | Submit the current prompt |
| esc | Cancel the current interaction or close a dialog |
| ctrl c | Quit Atlas |
Atlas ships with its own dark terminal theme and can load custom JSON themes from your Atlas config directory. Use /themes to switch from the TUI.
{
"name": "midnight",
"theme": {
"primary": "#6aa6f5",
"background": "#0c0c0c",
"text": "#e6e9ee"
}
}The atlas 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.
Atlas says it is already installed
Use atlas upgrade. If you built Atlas from source, pull the repo, rebuild the package, and make sure your PATH points at the rebuilt binary.
A model is missing
Run atlas models --refresh. For local models, confirm the model exists with ollama list and that Ollama is running.
Ready to work privately?
Install Atlas, choose your model route, and open it in your next repo.