[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"news-slug-ollama-0-24-codex-app-local-open-source":3,"topics-all":36,"news-related-73bd4795-6651-425b-b407-372d1ec0e793":55},{"id":4,"title":5,"summary":6,"content":6,"original_url":7,"source_id":8,"tags":9,"translations":23,"news_slug":29,"published_at":30,"created_at":31,"modified_at":32,"is_published":33,"publish_type":34,"image_url":13,"view_count":35},"73bd4795-6651-425b-b407-372d1ec0e793","Ollama 0.24 解锁新玩法：一行命令让 OpenAI Codex 跑在本地开源模型上","本地大模型运行工具 Ollama 近日发布 0.24 版本，最大亮点是一条命令：ollama launch codex-app。执行后，OpenAI 的桌面客户端 Codex App 会自动配置好一切，将推理请求重定向到本地 Ollama 运行时，而非 OpenAI 云端 API。\n\n这意味着什么？此前，Codex App 是 OpenAI Pro 用户的专属——需要有效 API Key、流向 api.openai.com 的出站流量，以及按 token 计费的账单。Ollama 0.24 解开了这个绑定：Codex App 继续扮演交互前端的角色，但推理请求被重定向到本地，模型运行在用户自己的 GPU 上，所有文件读取留在用户自己的文件系统里。\n\n这不是简单的「本地运行 OpenAI 应用」，而是开源社区持续数月努力的又一个节点。几个月前 Ollama 就支持了 Codex CLI 的 --oss 模式，指向 OpenAI 兼容端点，但需要手动配置 ~\u002F.codex\u002Fconfig.toml 和各种环境变量，门槛不低。ollama launch codex-app 把这一切封装成一条命令，开箱即用。\n\n对于受 NDA、GDPR 或企业安全政策约束的开发者而言，这是实质性飞跃。代码不出本地机器，不经过第三方服务器，这在以前只有完全自建推理基础设施才能实现，现在通过 Ollama 加上开源模型就能搞定。\n\n从生态角度看，这条路正在变得清晰：Ollama → Codex App → 本地开源模型，三个层次各自标准化，又通过 OpenAI 兼容 API 串联起来。随着 Claude Code、OpenAI Codex 这类桌面 Agent 工具相继支持本地路由，开源模型的 Agent 能力边界正在从「能跑」向「好用」迁移。本地 Agent 开发的环境一致性与隐私保障，是云端方案难以复制的优势。","https:\u002F\u002Fpasqualepillitteri.it\u002Fen\u002Fnews\u002F2574\u002Follama-codex-app-local-models","a1e592fe-9e08-48a2-aaa9-a6cd1c1def3b",[10,14,17,20],{"id":11,"name":12,"slug":12,"description":13,"color":13},"e82b2d09-81b2-43d1-977e-e018443b3c14","coding-agent",null,{"id":15,"name":16,"slug":16,"description":13,"color":13},"0ef8513a-0a26-42f0-b6f9-5b6dadded45c","efficiency",{"id":18,"name":19,"slug":19,"description":13,"color":13},"01598627-1ea6-4b27-a5d8-874971571a71","llm",{"id":21,"name":22,"slug":22,"description":13,"color":13},"b9bd9039-fcdb-41a8-b85b-fc1587def2b9","open-source",[24],{"id":25,"lang":26,"title":27,"summary":28,"content":13},"95b6a1e6-9644-4bb3-a410-8121abcf74c7","en","Ollama 0.24: run OpenAI Codex on local open-source models","Ollama 0.24 introduces a \"Codex mode\" that lets OpenAI's Codex CLI run on local open-source models through Ollama, with a single command. The release makes open-source models a drop-in replacement for OpenAI's closed-source programming assistant, with privacy and cost benefits.","ollama-0-24-codex-app-local-open-source","2026-05-27T22:01:00Z","2026-05-27T22:07:56.443730Z","2026-08-19T02:08:40.142862Z",true,"agent",285,[37,46],{"slug":38,"tag_slug":38,"title_zh":39,"title_en":40,"intro_zh":41,"intro_en":42,"id":43,"is_active":33,"created_at":44,"modified_at":45},"ai-for-science","AI for Science 2026：从 UniPert 到 GPT-Rosalind 的硬核进化","AI for Science 2026: from UniPert to GPT-Rosalind","生命科学、化学材料、物理世界模型——AI 正在从\"语言工具\"变成\"实验伙伴\"。本专题收录 AI 在三大科学方向的关键节点：UniPert 统一基因与化学扰动空间、GPT-Rosalind 端到端生命科学推理、达摩院 AI 智能体 28 小时找到 4 种超导新材料、Anthropic Claude Science 把工作台做成标准品。","From language tool to lab partner — AI is reshaping life sciences, chemistry\u002Fmaterials, and physical world models. This topic covers the key milestones: UniPert unifying genetic-chemical perturbation spaces, GPT-Rosalind's end-to-end life-sciences reasoning, DAMO's AI agent discovering 4 superconducting materials in 28 hours, and Anthropic's Claude Science workbench going mainstream.","988a4300-5fab-41c4-b5d8-63711a2dc757","2026-09-10T01:34:15.296649Z","2026-09-10T01:34:15.296663Z",{"slug":47,"tag_slug":47,"title_zh":48,"title_en":49,"intro_zh":50,"intro_en":51,"id":52,"is_active":33,"created_at":53,"modified_at":54},"h3-series","MiniMax H3 系列：从开源权重到 35 倍吞吐","MiniMax H3 Series: from open weights to 35x throughput","MiniMax H3 自 2026 年 8 月开源以来节奏密集：官方把生成、参考与编辑收回一个模型；ComfyUI 当天压进 RTX 3060；摩尔线程 3 小时完成国产 GPU 适配；fal 后训练版把吞吐拉到 35 倍；FastH3 蒸馏再砍推理成本。本专题持续追踪 H3 的发布—开源—蒸馏—部署全链路。","Since MiniMax open-sourced H3 in August 2026 the pace has been relentless: one unified omni-modal model, same-day ComfyUI support down to an RTX 3060, a 3-hour Day-0 port to Moore Threads GPUs, fal's post-trained H3 Max at 35x throughput, and FastH3 distillation cutting inference cost further. This topic tracks the full H3 chain — release, open weights, distillation, deployment.","83ef0daa-3c31-4cb3-86ed-e5ee58654d5f","2026-09-08T07:33:19.942193Z","2026-09-08T07:33:19.942209Z",{"items":56},[57,62,67,72,77,82],{"id":58,"title":59,"news_slug":60,"published_at":61},"436fb2b9-4c48-4631-977c-c9539650f975","Kimi K2.7-Code 开源:Moonshot 把\"过度思考\"砍掉三成,长程编程更经济","kimi-k2-7-code-moonshot-30pct-token-cut","2026-06-13T02:00:00+00:00",{"id":63,"title":64,"news_slug":65,"published_at":66},"c696208b-6535-4eb9-b1ed-2e4f835d2f88","NVIDIA SoL-Pi 把 coding agent 的 token 砍掉 44%,harness 开始变天","nvidia-sol-pi-harness-token-compression","2026-09-19T03:00:00+00:00",{"id":68,"title":69,"news_slug":70,"published_at":71},"28c41f06-d20f-481c-b133-cd109af3aed1","答对之后停不下来:微软团队揪出在线蒸馏的 EOS 错配元凶","eos-mismatch-opd-length-inflation","2026-09-18T21:09:06+00:00",{"id":73,"title":74,"news_slug":75,"published_at":76},"2e27016d-b90e-45c7-825a-41fd1e435c80","JHU 新研究:组合持续学习机制,百任务记忆留存从 1.2% 提到 34.9%","compose-cl-long-horizon-memorization","2026-09-16T15:10:00+00:00",{"id":78,"title":79,"news_slug":80,"published_at":81},"30fca629-bace-4832-9789-b44aa8c8989d","学生团队从零训出开源 7B 模型 ZGCM-1:数学推理硬刚 235B 前沿","zgcm-1-open-7b-foundation-model","2026-09-15T19:10:00+00:00",{"id":83,"title":84,"news_slug":85,"published_at":86},"5535b4e4-21de-4ed6-a9bb-2b4d824e6568","F-Droid 一次更新的 102 款应用,72.5% 主要是 AI 写的","f-droid-72-percent-ai-written-audit","2026-09-15T15:12:16+00:00"]