[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"article-mistral-medium-35-remote-coding-agents-en":3,"article-related-mistral-medium-35-remote-coding-agents-en":29,"series-ai-agent-d458d1cb-e488-480e-b8f7-b63583a9d02b":82},{"id":4,"slug":5,"title":6,"content":7,"summary":8,"source":9,"source_url":10,"author":11,"image_url":12,"cover_image":12,"category":13,"language":14,"translated_content":11,"related_article_id":15,"keywords":16,"key_takeaways":22,"views":26,"created_at":27,"published_at":28,"topic_cluster_id":11},"d458d1cb-e488-480e-b8f7-b63583a9d02b","mistral-medium-35-remote-coding-agents-en","Mistral Medium 3.5 powers remote coding agents","\u003Cp data-speakable=\"summary\">Mistral launched Medium 3.5 and moved its \u003Ca href=\"\u002Fnews\u002Fwhy-ai-coding-agents-need-an-architecture-compiler-en\">coding agents\u003C\u002Fa> into the cloud.\u003C\u002Fp>\u003Cp>\u003Ca href=\"https:\u002F\u002Fmistral.ai\" target=\"_blank\" rel=\"noopener\">Mistral AI\u003C\u002Fa> just pushed its \u003Ca href=\"\u002Ftag\u002Fagent\">agent\u003C\u002Fa> story into a more practical shape: coding work can now run remotely, in parallel, and keep going after you close the tab. The company says \u003Ca href=\"https:\u002F\u002Fmistral.ai\u002Fnews\u002Fvibe-remote-agents-mistral-medium-3-5\" target=\"_blank\" rel=\"noopener\">Mistral Medium 3.5\u003C\u002Fa> is the default model for \u003Ca href=\"https:\u002F\u002Fmistral.ai\u002Fproducts\u002Fle-chat\" target=\"_blank\" rel=\"noopener\">Le Chat\u003C\u002Fa> and \u003Ca href=\"https:\u002F\u002Fmistral.ai\u002Fproducts\u002Fvibe\" target=\"_blank\" rel=\"noopener\">Vibe\u003C\u002Fa>, and it comes with a 128B dense architecture, a 256k context window, and open weights.\u003C\u002Fp>\u003Ctable>\u003Cthead>\u003Ctr>\u003Cth>Item\u003C\u002Fth>\u003Cth>Number\u003C\u002Fth>\u003Cth>Why it matters\u003C\u002Fth>\u003C\u002Ftr>\u003C\u002Fthead>\u003Ctbody>\u003Ctr>\u003Ctd>Model size\u003C\u002Ftd>\u003Ctd>128B dense\u003C\u002Ftd>\u003Ctd>Large enough for serious coding and reasoning work\u003C\u002Ftd>\u003C\u002Ftr>\u003Ctr>\u003Ctd>Context window\u003C\u002Ftd>\u003Ctd>256k\u003C\u002Ftd>\u003Ctd>Can keep more code and instructions in view\u003C\u002Ftd>\u003C\u002Ftr>\u003Ctr>\u003Ctd>SWE-Bench Verified\u003C\u002Ftd>\u003Ctd>77.6%\u003C\u002Ftd>\u003Ctd>Signals strong software engineering performance\u003C\u002Ftd>\u003C\u002Ftr>\u003Ctr>\u003Ctd>τ³-Telecom\u003C\u002Ftd>\u003Ctd>91.4\u003C\u002Ftd>\u003Ctd>Shows agentic tool-use strength\u003C\u002Ftd>\u003C\u002Ftr>\u003Ctr>\u003Ctd>API pricing\u003C\u002Ftd>\u003Ctd>$1.5 \u002F $7.5 per million tokens\u003C\u002Ftd>\u003Ctd>Input and output pricing for builders\u003C\u002Ftd>\u003C\u002Ftr>\u003C\u002Ftbody>\u003C\u002Ftable>\u003Ch2>What Mistral actually changed\u003C\u002Fh2>\u003Cp>The headline is not only a new model. Mistral is pairing the model with a different working style for developers: \u003Ca href=\"\u002Ftag\u002Fagents\">agents\u003C\u002Fa> that run in the cloud, continue while you step away, and report back when they finish. That matters because a lot of coding-agent work is repetitive, interrupt-heavy, and slow when it stays pinned to a local terminal.\u003C\u002Fp>\n\u003Cfigure class=\"my-6\">\u003Cimg src=\"https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1778152254133-tdn5.png\" alt=\"Mistral Medium 3.5 powers remote coding agents\" class=\"rounded-xl w-full\" loading=\"lazy\" \u002F>\u003C\u002Ffigure>\n\u003Cp>With Vibe remote agents, a session can start in the CLI or in Le Chat, then move to the cloud runtime without losing task state, approvals, or history. Mistral says you can even “teleport” an ongoing local CLI session into the cloud. That is a small phrase with a big implication: the company wants the same workflow across laptop, browser, and background execution.\u003C\u002Fp>\u003Cp>The practical use cases are the ones teams already know well: module refactors, test generation, dependency upgrades, CI investigations, and bug fixes. Those are the jobs that eat hours because they involve many small edits and checks rather than one clever insight.\u003C\u002Fp>\u003Cul>\u003Cli>Sessions can run in parallel instead of one at a time.\u003C\u002Fli>\u003Cli>Agents can open pull requests on GitHub when they finish.\u003C\u002Fli>\u003Cli>File diffs, tool calls, and progress states stay visible during the run.\u003C\u002Fli>\u003Cli>Local sessions can move to the cloud with state intact.\u003C\u002Fli>\u003C\u002Ful>\u003Ch2>Why Medium 3.5 matters more than the branding\u003C\u002Fh2>\u003Cp>\u003Ca href=\"https:\u002F\u002Fhuggingface.co\u002Fmistralai\" target=\"_blank\" rel=\"noopener\">Hugging Face\u003C\u002Fa> often gets crowded with model launches, but Medium 3.5 has a few details that make it more interesting than a standard flagship release. It is a single dense model that combines instruction-following, reasoning, and coding rather than splitting those abilities across separate weights. Mistral also says reasoning effort is configurable per request, which should help the same model act like a fast chat assistant in one moment and a slower agent in the next.\u003C\u002Fp>\u003Cp>The benchmark numbers are solid enough to matter in real engineering conversations. Mistral says Medium 3.5 scores 77.6% on \u003Ca href=\"\u002Ftag\u002Fswe-bench-verified\">SWE-Bench Verified\u003C\u002Fa> and 91.4 on τ³-Telecom. It also claims self-hosting on as few as four GPUs, which is important for teams that care about deployment control and cost ceilings.\u003C\u002Fp>\u003Cblockquote>“Today we’re moving them to the cloud, where they run on their own, in parallel, and notify you when they’re done.” — Mistral AI\u003C\u002Fblockquote>\u003Cp>That quote captures the product shift better than any marketing slide. Mistral is betting that developers do not want another chat box that writes code. They want a worker that can stay busy while they do something else, then hand back a branch or a draft PR instead of a stream of partial thoughts.\u003C\u002Fp>\u003Ch2>Work mode turns Le Chat into an execution layer\u003C\u002Fh2>\u003Cp>The second half of the release is \u003Ca href=\"https:\u002F\u002Fmistral.ai\u002Fproducts\u002Fle-chat\" target=\"_blank\" rel=\"noopener\">Le Chat\u003C\u002Fa> Work mode, which Mistral says is powered by a new harness plus Medium 3.5. In practice, this makes the assistant more like an execution layer than a simple chatbot. It can read and write across connected tools, call several tools at once, and keep working through multi-step tasks until the job is done.\u003C\u002Fp>\n\u003Cfigure class=\"my-6\">\u003Cimg src=\"https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1778152257056-9bch.png\" alt=\"Mistral Medium 3.5 powers remote coding agents\" class=\"rounded-xl w-full\" loading=\"lazy\" \u002F>\u003C\u002Ffigure>\n\u003Cp>That matters for office work as much as coding. Mistral highlights workflows like catching up across email, messages, and calendar in one run; preparing for meetings with attendee context and recent news; triaging inboxes; drafting replies; creating Jira issues; and sending summaries to Slack or Teams. The company also says connectors are on by default in Work mode, so the agent can pull in the context it needs without a manual setup step every time.\u003C\u002Fp>\u003Cp>There is a real tradeoff here. More autonomy means more speed, but it also increases the need for visibility and approvals. Mistral says every action is visible, with tool calls and reasoning shown to the user, and sensitive actions still require explicit approval based on permissions. That is the right constraint if this is going to be used inside real teams.\u003C\u002Fp>\u003Cul>\u003Cli>\u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fmistralai\" target=\"_blank\" rel=\"noopener\">GitHub\u003C\u002Fa> integration covers code and pull requests.\u003C\u002Fli>\u003Cli>\u003Ca href=\"https:\u002F\u002Flinear.app\" target=\"_blank\" rel=\"noopener\">Linear\u003C\u002Fa> and \u003Ca href=\"https:\u002F\u002Fwww.atlassian.com\u002Fsoftware\u002Fjira\" target=\"_blank\" rel=\"noopener\">Jira\u003C\u002Fa> connect issue tracking to agent work.\u003C\u002Fli>\u003Cli>\u003Ca href=\"https:\u002F\u002Fsentry.io\" target=\"_blank\" rel=\"noopener\">Sentry\u003C\u002Fa> plugs incident data into the workflow.\u003C\u002Fli>\u003Cli>\u003Ca href=\"https:\u002F\u002Fslack.com\" target=\"_blank\" rel=\"noopener\">Slack\u003C\u002Fa> and \u003Ca href=\"https:\u002F\u002Fwww.microsoft.com\u002Fmicrosoft-teams\" target=\"_blank\" rel=\"noopener\">Microsoft Teams\u003C\u002Fa> handle reporting and notifications.\u003C\u002Fli>\u003C\u002Ful>\u003Ch2>The pricing and access details tell you who this is for\u003C\u002Fh2>\u003Cp>Mistral is making Medium 3.5 available today in Vibe and Le Chat on Pro, Team, and Enterprise plans. Through the API, it costs $1.5 per million input tokens and $7.5 per million output tokens. Open weights are on \u003Ca href=\"https:\u002F\u002Fhuggingface.co\u002Fmistralai\u002FMistral-Medium-3.5\" target=\"_blank\" rel=\"noopener\">Hugging Face\u003C\u002Fa> under a modified MIT license, and the model is also available through \u003Ca href=\"https:\u002F\u002Fbuild.nvidia.com\" target=\"_blank\" rel=\"noopener\">NVIDIA Build\u003C\u002Fa> and \u003Ca href=\"https:\u002F\u002Fwww.nvidia.com\u002Fen-us\u002Fai-data-science\u002Fproducts\u002Fnim\u002F","Mistral launched Medium 3.5, a 128B open-weight model, plus remote coding agents in Vibe and Work mode in Le Chat.","mistral.ai","https:\u002F\u002Fmistral.ai\u002Fnews\u002Fvibe-remote-agents-mistral-medium-3-5",null,"https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1778152254133-tdn5.png","ai-agent","en","53cc9013-736c-42dc-a9e7-8a050be2e123",[17,18,19,20,21],"Mistral Medium 3.5","remote coding agents","Le Chat Work mode","open weights","agentic AI",[23,24,25],"Mistral Medium 3.5 is a 128B open-weight model with a 256k context window.","Vibe remote agents can run coding sessions in the cloud and return a PR or branch.","Le Chat Work mode extends the same model into multi-step office workflows with approvals.",2,"2026-05-07T11:10:34.98822+00:00","2026-05-07T11:10:34.961+00:00",{"tags":30,"relatedLang":41,"relatedPosts":45},[31,33,35,37,39],{"name":18,"slug":32},"remote-coding-agents",{"name":17,"slug":34},"mistral-medium-35",{"name":20,"slug":36},"open-weights",{"name":21,"slug":38},"agentic-ai",{"name":19,"slug":40},"le-chat-work-mode",{"id":15,"slug":42,"title":43,"language":44},"mistral-medium-35-remote-coding-agents-zh","Mistral Medium 3.5 讓遠端 coding agent 上線","zh",[46,52,58,64,70,76],{"id":47,"slug":48,"title":49,"cover_image":50,"image_url":50,"created_at":51,"category":13},"5efa67dd-b9f7-4a2f-8c68-3a4bc6a6b7d9","claude-code-dynamic-workflow-ai-harness-en","Claude Code 动态工作流：AI 自写 Harness","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1781035372495-9czj.png","2026-06-09T20:02:22.33375+00:00",{"id":53,"slug":54,"title":55,"cover_image":56,"image_url":56,"created_at":57,"category":13},"2bd28e0e-0f4b-4987-a961-28763c1e1926","agent-orchestration-enterprise-ai-layer-en","Agent orchestration is the missing layer for enterprise AI","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1780984981174-08mj.png","2026-06-09T06:02:31.384174+00:00",{"id":59,"slug":60,"title":61,"cover_image":62,"image_url":62,"created_at":63,"category":13},"95684312-23dc-4a78-a917-df14d132c5fa","ai-agents-use-blockchain-trust-layer-en","AI agents use blockchain as a trust layer","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1780980506080-ki4s.png","2026-06-09T04:48:01.710214+00:00",{"id":65,"slug":66,"title":67,"cover_image":68,"image_url":68,"created_at":69,"category":13},"0208e47f-7d4c-4473-a0f9-4cd193b5c139","8-rag-patterns-demos-into-prod-en","8 RAG patterns that turn demos into prod","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1780971552707-qpl7.png","2026-06-09T02:18:36.760049+00:00",{"id":71,"slug":72,"title":73,"cover_image":74,"image_url":74,"created_at":75,"category":13},"b413d484-6786-4c32-abdc-77f010ac7eba","fine-tuning-beats-rag-style-not-facts-en","Fine-tuning beats RAG when the goal is style, not facts","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1780924681800-5xji.png","2026-06-08T13:17:25.701649+00:00",{"id":77,"slug":78,"title":79,"cover_image":80,"image_url":80,"created_at":81,"category":13},"57beb8b4-c233-400f-b95b-a97be1cf9d02","openclaw-small-business-ai-staff-en","OpenClaw shows how small businesses use AI staff","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1780904882032-yp13.png","2026-06-08T07:47:27.730921+00:00",[83,88,93,98,103,108,113,118,123,128],{"id":84,"slug":85,"title":86,"created_at":87},"03db8de8-8dc2-4ac1-9cf7-898782efbb1f","anthropic-claude-ai-agent-task-automation-en","Anthropic's Claude AI Agent: A New Era of Task Automation","2026-03-25T16:25:06.513026+00:00",{"id":89,"slug":90,"title":91,"created_at":92},"045d1abc-190d-4594-8c95-91e2a26f0c5a","googles-2026-ai-agent-report-decoded-en","Google’s 2026 AI Agent Report, Decoded","2026-03-26T11:15:23.046616+00:00",{"id":94,"slug":95,"title":96,"created_at":97},"e64aba21-254b-4f93-aa21-837484bb52ec","kimi-k25-review-stronger-still-not-legend-en","Kimi K2.5 review: stronger, still not a legend","2026-03-27T07:15:55.385951+00:00",{"id":99,"slug":100,"title":101,"created_at":102},"30dfb781-a1b2-4add-aebe-b3df40247c37","claude-code-controls-mac-desktop-en","Claude Code now controls your Mac desktop","2026-03-28T03:01:59.384091+00:00",{"id":104,"slug":105,"title":106,"created_at":107},"254405b6-7833-4800-8e13-f5196deefbe6","cloudflare-100x-faster-ai-agent-sandbox-en","Cloudflare’s 100x Faster AI Agent Sandbox","2026-03-28T03:09:44.356437+00:00",{"id":109,"slug":110,"title":111,"created_at":112},"04f29b7f-9b91-4306-89a7-97d725e6e1ba","openai-backs-isara-agent-swarm-bet-en","OpenAI backs Isara’s agent-swarm bet","2026-03-28T03:15:27.849766+00:00",{"id":114,"slug":115,"title":116,"created_at":117},"3b0bf479-e4ae-4703-9666-721a7e0cdb91","openai-plan-automated-ai-researcher-en","OpenAI’s plan for an automated AI researcher","2026-03-28T03:17:42.312819+00:00",{"id":119,"slug":120,"title":121,"created_at":122},"fe91bce0-b85d-4efa-a207-24ae9939c29f","harness-engineering-ai-agent-reliability-2026","Harness Engineering: From Bridle to Operating System, The Missing Link in AI Agent Reliability","2026-03-31T06:36:55.648751+00:00",{"id":124,"slug":125,"title":126,"created_at":127},"7a09007d-820f-43b3-8607-8ad1bfcb94c8","mcp-explained-from-prompts-to-production-en","MCP Explained: From Prompts to Production","2026-04-01T09:24:40.089177+00:00",{"id":129,"slug":130,"title":131,"created_at":132},"116d5ee9-a4f1-4b5a-aac5-5d035dd22bbe","amazon-bedrock-agents-multi-agent-workflows-en","Amazon Bedrock Agents Gets Multi-Agent Workflows","2026-04-01T09:30:30.197685+00:00"]