Grux AI Download

Which coding agents can run on a local model on my Mac?

Most of them can: OpenCode, Codex CLI, Cline and Claude Code start on an Ollama model with one command, ollama launch followed by the agent's name, and goose and Aider connect to Ollama in their own settings. Ollama added the launch command in version 0.15.0 in January 2026. Before you judge an agent, set the context window: Ollama's documentation says coding tools should have at least 64000 tokens, and its defaults are lower on a smaller machine. The agent is the open source part, and the model you load decides how good the answers are. This page repeats each project's own instructions and quotes no speed or quality figure, because we have not measured these agents on a local model.

Download Grux AI 3.3.1, free, for macOS 14 or later on Apple silicon.

Grux AI 3.3.1 · sources read 2026-11-19 · published 2026-11-19

One way in for each agent

AgentHow to run it on an Ollama modelSource
OpenCode (MIT)ollama launch opencode. OpenCode also probes a running Ollama at 127.0.0.1:11434 and adds its modelsOllama, OpenCode docs
Codex CLI (Apache 2.0)ollama launch codex, or codex --oss, or codex --oss -m gpt-oss:120b for a named modelOllama
Cline (Apache 2.0)ollama launch cline, or ollama launch cline --model qwen3.5Ollama
goose (Apache 2.0)In Goose, Settings, Configure Provider, Ollama, API host http://localhost:11434. In the command line, goose configure, then OllamaOllama
Aider (Apache 2.0)Set OLLAMA_API_BASE=http://127.0.0.1:11434, then aider --model ollama_chat/<model>Aider docs
Claude Code (all rights reserved)ollama launch claude, covered on its own pageClaude Code with a local model

Ollama's integrations list also has pages for Copilot CLI and Droid, which are not open source agents, and for Claude Desktop, covered on the Claude desktop app with a local model. Gemini CLI's README describes no local model route.

Set the context window first

A coding agent fills a context window fast, because it reads files and runs commands. Ollama's context page says tasks that need large context, agents and coding tools among them, should be set to at least 64000 tokens, and that a larger window needs more memory. Its defaults depend on memory: 4k below 24 GiB of VRAM, 32k from 24 to 48 GiB, 256k from 48 GiB. OpenCode's and Codex CLI's Ollama pages repeat the 64k minimum.

OLLAMA_CONTEXT_LENGTH=64000 ollama serve
ollama ps

The second line is Ollama's own check: ollama ps shows the context each loaded model was given and whether it runs fully on the GPU. Aider's page says it sets Ollama's window for each request itself, so the variable matters most for the others.

Which model to load

Pick a model that supports tools, as large as your memory holds with room for the long context. Best local LLM for coding on a Mac lists coding models by memory, and which LLM can my Mac run gives the sizing rule. Ollama's launch pages also offer cloud models, which run on Ollama's service; choose a model you have pulled when you want it local.

Which agent to start with

That is a question about the agent, not the model. Open source Claude Code alternatives compares the same agents by licence, where they run and what each is for.

Where to check this

ClaimSource
ollama launch arrived in Ollama 0.15.0, for Claude Code, Codex, OpenCode and DroidOllama release v0.15.0
The launch command and the 64k context minimum for OpenCodeOllama documentation, OpenCode
The launch command and the oss flag for Codex CLI; at least 64k tokensOllama documentation, Codex CLI
The launch command for ClineOllama documentation, Cline CLI
The goose steps for OllamaOllama documentation, Goose
The Aider variable and command, and how it sets the context windowAider documentation, Ollama
At least 64000 tokens for coding tools; the context defaults by memory; ollama psOllama documentation, Context length
OpenCode finds a running Ollama by itselfOpenCode documentation, providers

All of these were read on 19 November 2026. Check each project's page for the current commands before you copy one.

Questions

Can OpenCode use Ollama?
Yes. Run ollama launch opencode, or start Ollama and OpenCode, whose documentation says it probes 127.0.0.1:11434 and adds the models it finds.
Can Codex CLI run on a local model?
Yes. Ollama's page gives codex with the oss flag, or ollama launch codex, and asks for a context window of at least 64k tokens.
Does Aider work with a local model on a Mac?
Yes. Aider's documentation gives the OLLAMA_API_BASE variable and aider with an ollama_chat model name, and says Aider sets Ollama's context window for each request.
What context window do coding agents need with Ollama?
Ollama's documentation says at least 64000 tokens for coding tools, and its defaults are 4k below 24 GiB of VRAM, so set it yourself.
Download Grux AI 3.3.1 Read the source

Free, MIT licensed. macOS 14 or later, Apple silicon. 29.1 MB, signed and notarized by Apple. No account, no server, no subscription.