Client Context Profiles is an upcoming Atlas capability for people who work across many client repositories. When you open a client's repository, it will load that client's context automatically: the voice and formatting rules, who the people are, the active constraints, and the open commitments. The aim is that the agent shows up already being the right operator for that client, instead of being told the same context every session.
A different operator in every repo
A consultant is a different operator for each client, with different voice rules, people, and constraints.
Client Context Profiles will switch that context automatically when you open a client's repository, so one client's conventions never leak into another's work and you never have to re-explain who the people are or how the client wants deliverables written.
Always on, never in the way
Client context should be present the moment you start, like the environment around the work.
The capability is designed to load the profile as a persistent part of the session for that client, opt-in per workspace, so the agent is grounded in the right client from the first prompt.
Frequently asked questions
- Is Atlas client context loading available now?
- Not yet. It is a planned Atlas capability described on this page.
- Who is this for?
- Consultants, agencies, and anyone who works across multiple client repositories and needs the agent to adopt each client's context.
- What context will it load?
- Voice and formatting rules, the client's people, active constraints, and open commitments, assembled from the context you already maintain.
- Do I have to write a profile for each client?
- A small per-client profile covers voice and constraints; people and commitments are pulled from your existing knowledge base and filed notes.
Try Atlas in your terminal
The terminal-native AI coding agent. Open source, single binary.
Install AtlasRelated guides
Atlas vs Claude Code: open, model-agnostic vs first-party terminal agent (2026)
A grounded 2026 comparison of Atlas and Claude Code, two terminal-native AI coding agents, across model choice, openness, review, and pricing.
Atlas vs Cursor: terminal AI coding agents compared (2026)
A grounded 2026 comparison of Atlas and Cursor across workflow, change review, extensibility, and pricing for developers choosing an AI coding agent.
Atlas vs GitHub Copilot: agent vs autocomplete (2026)
How Atlas, a terminal-native AI coding agent, compares to GitHub Copilot's editor-embedded autocomplete and chat in 2026.
Atlas vs Aider: terminal AI coding tools compared (2026)
Atlas and Aider are both open-source terminal AI coding tools. A 2026 comparison of their interfaces, review models, and extensibility.