Atlas is model-agnostic and runs against a local model as easily as a hosted one. Point it at any local OpenAI-compatible server, Ollama or LM Studio, and run atlas models --local: in 2026 Atlas detects the running server, lists its chat models, and registers them as a provider you pick like any other. A local model runs on your machine with no per-token API cost, and pairs with offline mode to run fully air-gapped.
Why run a local model
There are 3 reasons developers point an AI coding agent at a local model in 2026: keeping code on their own machine, avoiding per-token API bills, and not depending on a hosted provider's uptime or pricing.
A local model turns the cost of heavy agent use from a metered API bill into the fixed cost of your own hardware, which matters when an agent makes many calls per task. It also keeps the model side of the loop on your machine, so paired with a local code index there is no third-party in the path at all. Atlas stays model-agnostic either way: you can run local, bring your own hosted keys, or mix them per task.
Ollama and LM Studio
Run atlas models --local. Atlas probes the 2 common local servers, Ollama on port 11434 and LM Studio on port 1234, finds whichever is running, and lists its installed chat models.
It then registers those models as a provider in your config, so they appear in the model picker and in atlas models exactly like a hosted provider. There is no config file to hand-edit and no schema to reverse-engineer. If your server runs on a non-default port, set ATLAS_LOCAL_MODEL_URL and Atlas probes that instead. Embedding-only models are filtered out, so the picker shows only models you can actually chat with.
Model-agnostic by design
Atlas resolves the model per message, so you are never locked to 1 provider. Switch between a local model and a hosted one from the picker, or use different models for different work.
That means a local model is not an all-or-nothing commitment: run a small local model for routine edits and switch to a hosted frontier model for the hard problems, without changing tools. Bring your own keys for the hosted providers you already pay for, and Atlas routes to whichever you pick. The agent, the planning, the diffs, and the permission gating stay the same regardless of which model is behind them.
Local model plus offline mode
A local model is what makes air-gapped work possible. With a local model selected and offline mode on (atlas --offline), the only network Atlas touches is your local model server on your own machine.
This is the combination for developers who cannot send code to a cloud at all: the model is local, the code index can use local embeddings, and offline mode blocks every other outbound call. See the offline mode guide for how the network boundary is enforced. You bring the model; Atlas keeps the rest of the loop on hardware you control.
Frequently asked questions
- Can Atlas use a local model?
- Yes. Atlas works with any local OpenAI-compatible server, including Ollama and LM Studio. Run atlas models --local to detect it and register its models.
- How do I connect Ollama to Atlas?
- Run atlas models --local. Atlas detects Ollama on port 11434, lists your installed chat models, and registers them as a provider you can pick.
- Does Atlas work with LM Studio?
- Yes. LM Studio on port 1234 is auto-detected too. For a non-default port, set ATLAS_LOCAL_MODEL_URL and Atlas probes that endpoint.
- Do I need an API key for a local model?
- No. A local model runs on your machine with no per-token cost. You can still bring API keys for hosted models and switch between them.
- Can I run fully offline with a local model?
- Yes. Pair a local model with offline mode (atlas --offline) so the only network Atlas touches is your local model server.
Try Atlas in your terminal
The terminal-native AI coding agent. Free core, single binary.
Install AtlasRelated guides
Atlas with Claude Sonnet 5: The 2026 Everyday Driver
Claude Sonnet 5 gives Atlas a 1M token window at $2 / $10 per Mtok, 60 percent under Opus 4.8 input pricing. Why it is the default for long agentic sessions in 2026.
Atlas with Amazon Nova 2 Lite: Cost, Context, and Setup in 2026
Amazon Nova 2 Lite drives Atlas from inside your AWS account at $0.33 / $2.75 per Mtok with a 128K context. Setup, real tradeoffs, and when to pick another model.
Atlas with Gemma 4 31B IT: Running Google's Open Weights Locally in 2026
Gemma 4 31B IT in Atlas: Google's April 2026 open-weights release with a 262,144 token window, free self-hosted via ollama pull gemma4:31b, or $0.99 / $1.49 on Cerebras.
Atlas with Azure OpenAI (gateway) in 2026: The GPT-5 Codex Line Under Enterprise IAM
Azure OpenAI (gateway) runs Atlas on the full GPT-5 lineup including gpt-5.3-codex, with up to 1.05M context and passthrough Azure pricing in your own region.
Atlas for dbt: Terminal-Native AI Coding in 2026
Atlas is a terminal-native AI coding agent for dbt. Read the ref() DAG, convert a table model to incremental, run dbt build against dev, and add tests in 2026.
Atlas vs Poolside: Terminal AI Coding Agents in 2026
Compare Atlas and Poolside, two terminal AI coding agents in 2026. Atlas offers a free core and robust safety features, while Poolside provides open-weight Laguna models and on-prem deployment options.
Atlas with OpenAI o4-mini (2026): Cheap Reasoning for Parallel Subagents
OpenAI o4-mini drives Atlas at $1.10 per Mtok input and $4.40 per Mtok output on a 200K context. A strict upgrade over o3-mini at identical price, with real tradeoffs.
Atlas with GPT-5.6 Sol: The High Effort GPT-5.6 Variant in 2026
GPT-5.6 Sol tops the 5.6 line at $5 per Mtok input, $30 per Mtok output on a 1,050,000 token window. Atlas setup, small_model routing, and when Sol is overkill.