Atlas Cloud is the optional commercial control plane for Atlas. 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
Atlas 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 Atlas 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 Atlas 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 Atlas Cloud required to use Atlas?
- No. The agent runs locally with your own model keys. Atlas Cloud is the optional commercial control plane for accounts, entitlements, releases, and telemetry.
- What is Atlas 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 Atlas in your terminal
The terminal-native AI coding agent. Free core, single binary.
Install AtlasRelated guides
Atlas with Gemini 2.0 Flash-Lite: The Cheapest Google Model in the Registry (2026)
Gemini 2.0 Flash-Lite in Atlas: $0.075 per Mtok input, $0.3 per Mtok output, a 1,048,576 token context, an 8,192 token output cap, and no reasoning mode.
Research a Third-Party API Before Integrating It with Atlas in 2026
How to research a third-party API with Atlas in 2026: websearch finds the current docs, webfetch pulls the page as markdown or text, and grep checks repo conventions.
Atlas with GPT-OSS 120B (local via Ollama): Offline Reasoning for Air-Gapped Work in 2026
GPT-OSS 120B is the strongest fully offline reasoning model for Atlas: a 65GB MXFP4 download, 131,072 token context, free self-hosted, or $0.15 / $0.60 per Mtok on Groq.
Atlas with GPT-5.5: The 1.05M Token Jump, Reviewed for 2026
GPT-5.5 took the GPT-5 line to a 1,050,000 token context at $5 per Mtok input, $30 per Mtok output. Atlas setup, the price rise from $1.75, and when GPT-5.6 wins.
Atlas with GPT-5.2: The 400K General Purpose GPT in 2026
GPT-5.2 runs Atlas on a 400K context with 128K max output at $1.75 per Mtok input, $14 per Mtok output. Setup, the price rise from GPT-5.1, and the Codex tradeoff.
Atlas vs Trae: AI Coding Agents in 2026
Atlas and Trae offer distinct AI coding agent experiences in 2026. Atlas provides terminal-native control and local data privacy, while Trae offers a full IDE with SOLO Builder and cloud tasks.
Atlas for Blazor: Terminal-Native AI Coding for .razor Components in 2026
Atlas is a terminal-native AI coding agent for Blazor developers in 2026. Work across .razor components, render modes, and the C# and JS interop boundary safely.
Atlas with GPT-5.1: The Cheapest Full Size GPT-5 Input Price in 2026
GPT-5.1 in Atlas: 400K context, $1.25 per Mtok input and $10 per Mtok output, cheaper on input than every GPT-5 release that followed it in 2026.