Cyrus

Engineer says "I can't today, I'm busy". We built Cyrus to jump in in those exact moments. Drop a hard Linear issue → ~15 min later: tested PR + deploy preview ready to merge. Day 1 of Launch Week: Cyrus now supports Cursor agent + OpenAI Codex (alongside Claude). ⚡️ Composer 1.5 ~250 tok/s (~4× faster) 🎯 Codex 77.3% Terminal-Bench 2.0 🚅 Codex Spark up to 1,000 tok/s + BYO subscription You pick the agent and the model. Cyrus does the work. atcyrus.com/stories/cursor…

@CyrusAgent stars are growing rapidly. It's because it's the only open source agent that gives you a - @linear agent - @github agent AND - @SlackHQ agent In one installation, to tackle your end-to-end software automation

Cyrus has come to Slack. You can now mention Cyrus directly in Slack. Ask it anything: "What's the status on the tickets you're tracking?" "Review the PR on the auth refactor" "Build me a settings page for the new API" It answers instantly. In the thread. Connected to your Linear, GitHub, and repos. Need something built? Cyrus creates the ticket, writes the code, opens the PR, and pings you back in Slack. People are switching from other agent setups because of this; not just for smarter AI, but better integrations. Launch Week complete: Day 1: Multi-model support (Cursor, Codex, Claude) Day 2: Instant code reviews on GitHub Day 3: Cyrus in Slack Learn more: atcyrus.com/stories/slack-…

The waiting is the most expensive part of shipping software. Not the code. The queue. You know how this goes. You open a pull request, tag a reviewer, and... wait. A day passes. You ping on Slack. Two days. You rebase because main moved ahead. Three days. The review finally lands, but you've already context-switched to the next thing. You barely remember why you made that decision. Today, that changes. You can now @ mention Cyrus directly on any GitHub pull request and get an instant, thorough code review. This isn't a lint check. Cyrus reads the full context of your PR and your repo, then leaves the kind of review your senior engineer would - edge cases caught, architectural trade-offs questioned, concrete improvement suggestions.

Today, on Launch Week Day 2, we are launching something that's been requested many times, and for good reason. Directly @ mention Cyrus on Github (@cyrusagent) to get a response! You can get Cyrus to leave a code review, to answer quick questions about the PR, or to submit a follow up Linear issue for something you see. AND Cyrus now gets notified if you leave a review on a PR opened by Cyrus with a "change request", offering the chance to automatically get those changes in. And we're not done yet, tune in tomorrow for one more major launch to get excited about. Cyrus will be joining the chat.

Exciting customer news 🚀 @mihail_eric the @MonacoGTM team are out of stealth. They’re building the first AI-native revenue engine for startups—automating everything from ICP discovery to personalized outreach to CRM workflows. The incredible team is backed by @foundersfund, @garrytan, and @peterthiel. Monaco uses @CyrusAgent to ship faster. When we first spoke, Mihail shared how context switching was slowing his team down. Watching him solve that—and now launch something that will help thousands of founders—is what startups are all about. Grateful to be part of Monaco’s journey. Can’t wait to see what they ship next with Cyrus!

@jig_young Wow, the code is wholly different. What was your process?

@CyrusAgent Will do! I blame kimi for the copy! Haha

Jinyang.ai lives on @linear and spawns @opencode sessions to ship your tickets with open source models ( Kimi k2.5 and GLM 4.7 ) - had a kimi 2.5 agent swarm (@Kimi_Moonshot) fork @CyrusAgent ‘s community project to make it work with open code and local coding models (llama ccp) - thanks to @dhh for making open code default to @OmarchyLinux

@jig_young This is exciting! We love open models! Can you put up a PR?

All credit goes to the amazing work of @CyrusAgent and their community open source version Simply extended it to work with open code I’m so happy to live in the open source era of software

For product builders, this new world is INSANE. @meetgranola → @claudeai → @linear → @CyrusAgent Granola records all-hands. Claude transforms into actionables, files in Linear with owners. Humans tackle priority, user-facing items with Claude. Cyrus tackles minor issues.

@michaeljelly @luisflarota @linear Using Cyrus now, it's exactly what I want

🚀 Just launched: Skills Marketplace A growing collection of high quality Claude Code skills. One place. 🔧 MCP server building 🧪 Playwright testing 🔒 Trail of Bits security ☸️ Kubernetes manifests ⚡ DevOps automation and more. Stop hunting through GitHub repos. → atcyrus.com/skills

🚀 @CyrusAgent is now SOC 2 Type I compliant. Most AI agents look great in demos. Very few are ready for production. Cyrus is built for long-running, critical workflows. Security is designed in from day one. Fewer security reviews. Less procurement friction. Why this matters for the future of long-running agents 👇 atcyrus.com/stories/cyrus-…

Shipping velocity is fast and furious @CyrusAgent and now we have the receipts: atcyrus.com/changelog If you're still sleeping on the chance to add Claude Code to your @linear workspace you're missing out on major alpha for long-running agents.

BREAKING: Claude Code is soon launching Teammate/Swarms 🤖🤖🤖 and I have the receipts. They'll be bringing rich agent swarm functionality surely before the year end, as it's almost all baked in to the CLI and agent sdk now! Issue tracking, mailboxes, read/write locks. FULL analysis check it out for yourself! git.new/AYVq752

The Toronto Claude Code Meetup was epic fun! Especially demo-ing @CyrusAgent and how we overcame the issue tracker - PR not creating trash PRs problem. Thanks @claudeai @surim0n and @robjama for having me out. Trip from Victoria was 100 worth it to meet the brilliant minds here!

From complexity to simplicity in ten seconds. Struggling to make changes to that complex part of the codebase? Ask Cyrus to map out the state and flow in mermaid and post it to @linear as a comment! Instant understanding.

@PavelDudka's team at @Tiny_Fish recently brought Cyrus into their sprint workflow. The effect was immediate. After shifting to clearer @linear tickets and assigning them to Cyrus, their output jumped. Cyrus worked in parallel while engineers stayed focused, delivering 9 of 83 story points during the first sprint it was introduced in. Cyrus regularly ships PRs that are 90-95% complete on the first pass, needing only minor optimization. The team reports a doubling of efficiency and now recommends routing more tickets to Cyrus and sharing bugs or requests. Early results point to substantial potential as they scale this workflow. “Cyrus has quickly become a force multiplier for our team. By offloading well-specified Linear tickets to the agent, we’re able to make real parallel progress—Cyrus regularly ships PRs that are 90-95% complete on the first pass. It’s already meaningfully boosting our sprint velocity.”