BuildersTypeSafe released Jev: a model that returns decisions with probabilities instead of textTypeSafe AI came out of two years in stealth with Jev, a model that takes state and questions and answers with code-ready choices, scores and yes or no, each with a probability. Input costs 4.2 cents ($0.042) per million tokens, output is free.BuildersDevin got its own Mac and now runs iOS apps instead of only compiling themCognition launched macOS support for its agent Devin. It works in virtual Mac machines in the cloud and can launch the app, close it, open it again and check how it behaves.BuildersOpenAI gave every developer the Codex harness as an API and charges nothing on topOn 10 September OpenAI launched the Agents API in public beta. With one call you create a cloud agent with a given task, model, tools and environment, and behind it sits the same harness that powers Codex. There is no extra fee: you pay for tokens and tools.BuildersVS Code 1.137 runs agents on a schedule and lets you interrupt them by voiceThe 9 September release adds Automations, agent tasks that start every hour, day or week. The experimental Voice Mode lets you talk to the agent and interrupt it while it works. GitHub issues and pull requests open in the Agents window without the repository being open.BuildersGrok Bot moves into companies, and Cursor Enterprise customers get it free for two weeksOn 3 September SpaceXAI released Grok Bot for Enterprise with access, network and audit controls. Grok and Cursor Enterprise customers can use it free for two weeks and invite their entire organisation. Six days earlier OpenAI announced it is pulling its models from Cursor.BuildersOpenAI is pulling its models from Cursor on 12 November because it does not trust the new ownerOn 28 August OpenAI notified SpaceX that it is ending the contract under which its models run in Cursor. It is giving the maximum notice the contract allows and withholding future models, Astra included. The reason is stated plainly: its experience with Elon Musk's companies.BuildersJetBrains' Junie now runs entirely on your Mac, no cloud, no tokensJetBrains' code agent now runs locally. No credits, no quota, the code never leaves the machine. The price is the hardware: an M5 chip and at least 64 gigabytes of memory.BuildersJetBrains picked the older Qwen 3.6 over 3.8 because the newer model is slower on a laptopBehind local Junie sits a string of engineering trade-offs: a quantized model, reasoning turned off, remembered context. The most interesting one is the model choice. The newer Qwen 3.8 was dropped because, with reasoning on, it churns out around five times more tokens.
64 stories