ollama

v0.32.0 Breaking

This release includes 1 breaking change for platform teams planning a safe upgrade.

Published 16d Model Serving & MLOps

View tool

✓ No known CVEs patched

Read the diff → Tool health → What is this tool? →

✓ No known CVEs patched in this version

Topics

deepseek gemma gemma3 glm go gpt-oss

+8 more

llama llama3 llm llms minimax mistral ollama qwen

ReleasePort's take

Moderate signal

editorial:auto 11d

Running `ollama` now launches an interactive coding assistant, and the Codex App integration has been renamed to ChatGPT.

Why it matters: The new default launch behavior introduces a productive agent for developers; renaming the integration requires updating scripts that invoked `Codex`. Deprecation warnings flag older models (CodeLlama, Qwen2.5‑coder, Llama 3.x, Mistral, StarCoder, DeepSeek‑R1) to prompt migration before they are removed.

Summary

AI summary

Running ollama now launches an interactive coding assistant.

Changes in this release

Type	Severity	Summary	CVE
Feature
Feature	Medium	Running `ollama` now launches an interactive agent for coding and work delegation Running `ollama` now launches an interactive agent for coding and work delegation Source: llm_adapter@2026-07-15 Confidence: high	—
Feature	Medium	Renamed Codex App integration to ChatGPT; use `ollama launch chatgpt` Renamed Codex App integration to ChatGPT; use `ollama launch chatgpt` Source: llm_adapter@2026-07-15 Confidence: low	—
Feature	Low	Simplified ollama launch menu to show only the most popular integrations Simplified ollama launch menu to show only the most popular integrations Source: llm_adapter@2026-07-15 Confidence: high	—
Deprecation	Low	Deprecation warning added before launching older agent models (CodeLlama, Qwen2.5‑coder, Llama 3.x, Mistral, StarCoder, DeepSeek‑R1) Deprecation warning added before launching older agent models (CodeLlama, Qwen2.5‑coder, Llama 3.x, Mistral, StarCoder, DeepSeek‑R1) Source: llm_adapter@2026-07-15 Confidence: high	—

Full changelog

What's Changed

New interactive agent experience: running ollama now launches an agent to help you code and delegate work

❯ ollama
Ollama 0.32.0

▸ Chat, Code, & Work (glm-5.2:cloud)
    Chat with models, code, search the web, and delegate real work

Renamed the Codex App integration to ChatGPT: use ollama launch chatgpt (and --restore to return to your usual ChatGPT profile)
Simplified integration selection: the ollama launch menu now only offers the most popular integrations (other integrations can be accessed through ollama launch
Warns before launching older agent models: CodeLlama, Qwen2.5(-coder), Llama 3.x, Mistral, StarCoder, and the base DeepSeek-R1 tags now prompt a deprecation warning before ollama launch continues

Full Changelog: https://github.com/ollama/ollama/compare/v0.31.2...v0.32.0

Breaking Changes

Renamed Codex App integration to ChatGPT (use `ollama launch chatgpt`).

View diff on GitHub

Weekly OSS security release digest.

The CVE patches and breaking changes that affected production tools this week. One email, every Sunday.

No spam, unsubscribe anytime.

Share this release

Share on X Share on Bluesky

Track ollama

Get notified when new releases ship.

About ollama

Get up and running with Kimi-K2.5, GLM-5, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.

All releases →