Starting today, you can now use your ChatGPT subscription directly in Devin.
Just sign in to Devin with your ChatGPT Plus or Pro plan and all OpenAI model usage in Devin will drawn down from your quota.
Now live in Devin Cloud, Devin Desktop, and Devin CLI.
We're adding support for AGENTS.md to Claude Code.
Starting today in version 2.1.277, if there is no CLAUDE.md in a folder, Claude will check for and use AGENTS.md.
You can toggle this behavior in /config.
Introducing terminal-code: VS Code inside the terminal
- VS Code compatible CLI
- works over ssh
- syncs with your terminal theme
https://t.co/j3HThPdVPw
Origin, our code hosting platform, is now live.
It's fast, easy to use, and deeply integrated with Cursor.
Get started by syncing your repos from GitHub.
Anthropic Claude CodeチームのBorisが、Claudeを使って日常メンテナンスを自動化する実験をしている話:
Slackチャンネル「proj-claude-maintains-apps」を作り、Claude(Claude Tag / Claude Code)に毎日自動で動くルーチンを複数実行。対象はiOS / Android / Desktop / Web / CLI / Agent SDKなど、複数のアプリ
・Crash fuzzer:実機シミュレータでアプリを開き、適当にタップしてクラッシュを起こし、原因を特定して修正PRを出す
・Dup unifier:似たようなコードを統合するPRを作る
・Dead-code remover:到達不能なコードを削除する
・Logic bugfixer / Logic simplifier:ビジネスロジックのバグ修正や簡略化
・Flaky-test fixer:不安定なテストの根本原因を直す
・その他(抽象化の改善、使われていない機能の削除など)
実際にClaude Tagsで使用しているプロンプト:
> lets start new daily routines for crash fuzzing ios, android, and desktop apps e2e. make routines for each that use workflows to run the real apps (no mocks) and fuzz them to trigger crashes, then put up fix prs for those crashes. each pr must run /verify and post a repro and truth table to the pr. post updates in a new top level Fuzzer thread in this channel
> also make business-logic-bugfixer-daily and business-logic-simplifier-daily and dup-unifier. same story -- separate routine per app, top level thread with updates, always verify e2e with truth table. for all of these, remember to formally model the logic
> also to spot gaps and duplication and to make sure all edge cases are well tested
> also do this for finding and fixing root causes of flaky tests, and deleting useless tests
> also do one for dead code removal
herdr 0.8.0 is out, and it's the first apache-2.0 release 🎉
not a feature-heavy one, it's groundwork for what's coming next. 55 fixes, 18 contributors, and the biggest performance work herdr has had.
what got removed, and why 👇
We removed ~80% of the Claude Code system prompt for our newest models, this is what we've learned about writing system prompts, skills and Claude.MDs for them. https://t.co/6DZwSrZjE9
Introducing Cursor Router, our intelligent model router that selects the right model for the task at hand.
Router delivers frontier-quality results at 60% lower cost.
0.7.5 is out!
herdr is getting used more and more for multi-agent orchestration, so this release ships a native agent cli built exactly for that. more in below 👇
but first, the new agent sidebar: deeper customization with per-token colors, bold and dim, plus full filtering and sorting any way you want. from config, scripts, or plugins, all through the api!