Tool · 2026-07-14

Ollama v0.32.0

Ollama v0.32.0 turns the bare ollama command into an interactive agent for chatting, coding, web search, and delegating work — the local runtime is repositioning itself as an agent workbench entry point.

Ollama Releases2026-07-14About 2 min readWorth tracking

Marked important, but published more than 30 days ago, so it moved down to this band.

AI agentsOn-device AIInference & deployment
On this page13 sections

The editors' notes below — why it matters, the context, the learning path — are written in Chinese.

Release line

This signal has a follow-up

#

You are reading an earlier release on this line. 1 more release follows; the latest is “Ollama v0.32.4”.

  1. 2026-07-08Ollama v0.31.2
  2. 2026-07-14Ollama v0.32.0Current
  3. 2026-07-25Ollama v0.32.4Latest

从 v0.31.2 收尾的运行时稳健性,跨到「直接运行即进入交互式智能体」的形态转型。

Record

The signal

#

Ollama v0.32.0 ships a new interactive agent experience: running ollama now launches an agent that can chat, code, search the web, and delegate real work (banner default: glm-5.2:cloud). The Codex App integration was renamed to ChatGPT (ollama launch chatgpt), the launch menu was simplified to the most popular integrations, and older agent models (CodeLlama, Qwen2.5, Llama 3.x, Mistral, StarCoder, base DeepSeek-R1) now trigger a deprecation warning before launch.

Why now

Why it matters

#

装机量巨大的本地运行时把默认入口从「跑模型」换成「用智能体」,意味着智能体交互正在成为 AI 工具的默认形态,而不再是附加功能;本地/云混合的默认配置也预示端侧与云端的分工进入新阶段。

Background

Technical context

#

Ollama 原本封装模型下载、GGUF 加载和本地服务接口。v0.32.0 在此之上叠加了智能体层:命令行入口直接对话、调用工具(写码/搜索/委派),并通过 launch 集成打通外部智能体应用(如 ChatGPT)。默认模型 glm-5.2:cloud 表明它的智能体体验采用本地运行时 + 云端模型的混合架构,而非强制纯本地。

At your level

Have AI explain this signal at your level

Pick your level of experience and AI writes an explanation for it on the spot.

Audience

Who should care

#
本地/端侧应用开发者AI 工具链与开发者体验工程师评估智能体工作流落地的团队
Areas it may affect
开发者工具端侧 AI智能体工作流

Next

Learning path

#
  1. 升级到 v0.32.0,直接运行 ollama 体验智能体入口与旧版的差异。
  2. 结合「工具使用与函数调用」理解智能体委派工作的基本机制。
  3. 对照「模型选型与约束匹配」,理解为什么旧一代模型会被标记弃用、云模型成为默认。
  4. 用「智能体工作流设计」的框架评估:哪些日常任务适合从手动操作迁移到委派给本地智能体。

Getting started

Have AI draft a learning path

From the related knowledge and skills on this page, AI drafts a path from the basics to applying it.

Network

Where it sits in the network

#

How this signal connects to neighbouring technologies, skills and background knowledge. Follow any link to keep exploring.

Comparison

Compare with another technology

Pick another published technology and AI writes a comparison of what they share, how they differ and when to use each.

Further thought

Follow-up questions

#
  • 智能体模式下哪些操作会触碰本地文件系统和网络,权限边界如何配置?
  • 默认 glm-5.2:cloud 云模型时,哪些数据会离开本地设备,隐私敏感场景如何回退纯本地?
  • 被弃用警告的旧模型还能继续用多久,迁移路径是什么?

Publication record

Featured in

#

The briefings that carried this signal, newest first; the last row is the weekly review of its week. The tag is the section it ran in.

  1. 技术简报 - 2026-07-15

    Immediate attention
  2. 技术简报 - 2026-07-14

    Immediate attention

Sources

Ollama Releases

OllamaOpen-source community2026-07-14
Open original sourcehttps://github.com/ollama/ollama/releases/tag/v0.32.0