Start Pro or Team with a 7-day free trial and experience the power of Cyrus within minutes.
Community
$0USD/ mo
self-hosted
Set up own Linear app
Run Cloudflare proxy worker
All core features included
Community support
Pro
$50USD/ mo
semi-hosted
Managed Linear app and Cloudflare proxies
No hosting setup required
Exclusive webinars and Pro sessions
Up to 5 Linear members
Priority support
7-day free trial
Team
$120USD/ mo
fully hosted
24/7 uptime
Workspace isolation
Live metrics
MCP connections
Exclusive webinars and Pro sessions
Compute add-ons available
Unlimited members
Premium support
7-day free trial
Enterprise
Custom
custom pricing
Everything in Team plan plus:
Dedicated infrastructure
Custom SLA
Training & onboarding
Custom model configuration
Advanced security features
Our team has been experimenting with asynchronous (no human in-the-loop) coding agents with various CLI offerings and MCP servers. Our high-level goal has been to interface with an LLM CLI like Gemini, Cursor, or Claude and Linear MCP for R&D then hand over the ticket to a coding agent in another process. We were very much limited by local-only development, eventually needing a human in-the-loop where the agent is running to course correct, the effectiveness of MODEL.md directives, and found that rapid context switching still had too much overhead. Cyrus solved these problems for us elegantly, economically, and securely. We no longer need to engage with LLM-based coding agents in a synchronous fashion and can confidently delegate coding tasks to Cyrus from anywhere we can use Linear.
Mihail Eric
Head of AI, Monaco.co
FAQ
What is Cyrus?
Cyrus is an open-source Linear Claude Agent that automates software development workflows. It processes Linear issues assigned to a specific user, creates isolated Git worktrees for each issue, and uses Claude Code to handle development tasks automatically. It's designed to help development teams save time and increase productivity.
How does Cyrus integrate with Linear?
Cyrus connects to Linear through the Linear API and webhook system. It listens for issues assigned to a designated user, processes them automatically, and posts Claude's responses back as comments. The agent maintains conversation context and can handle follow-up comments through Linear's webhook API.
What programming languages and frameworks does Cyrus support?
Cyrus works with any codebase that Claude Code can understand. This includes most popular programming languages like JavaScript, TypeScript, Python, Java, Go, Rust, and many more. Since it uses Claude Code under the hood, it can work with virtually any text-based programming language or framework.
Do I need to be technical to use Cyrus?
Basic technical knowledge is helpful for initial setup, but once configured, Cyrus can be used by anyone on your team. You'll need to authorize Linear access, configure repository paths and permissions, and optionally set up MCP (Model Context Protocol) integrations. After setup, team members can simply assign issues to Cyrus through Linear's interface.
How secure is Cyrus?
Cyrus is designed with security in mind. It verifies webhook signatures from Linear, uses OAuth for authentication, and provides configurable tool permissions. Since it's open-source, you can review the code and run it in your own secure environment. All AI interactions are done through Anthropic's secure API.
Can I customize what tools Cyrus has access to?
Yes! Cyrus provides configurable tool permissions. You can specify which tools Claude Code can use when processing issues, such as restricting bash commands with patterns like "Bash(npm:*)" for npm-only access or "Bash(git:*)" for git-only access. This gives you full control over what actions the AI agent can perform in your codebase and helps maintain security.
What's the best Claude Code plan to use with Cyrus?
Cyrus works with any Claude Code plan. For teams handling many Linear issues, higher-tier plans provide better value due to increased usage limits. Check Claude Code pricing for the most current plan options and choose based on your team's expected volume of automated issue processing.
Can Cyrus work with other issue tracking systems besides Linear?
Currently, Cyrus is specifically designed for Linear. However, since it's open-source with a modular EdgeWorker architecture, developers can fork the project and adapt it to work with other issue tracking systems like Jira, GitHub Issues, or GitLab Issues. The core components for session management, Claude Code integration, and workspace creation can be reused.
What happens if Claude makes a mistake?
All of Claude's work is tracked in Git worktrees and Linear comments, so you can review any changes before merging. The agent doesn't automatically merge code - it creates separate worktrees for each issue, allowing human review. You maintain full control over what gets merged into your main branch.
How do I get started with Cyrus?
Getting started is straightforward: First, install Cyrus globally with "npm install -g cyrus-ai" then run "cyrus" to start the setup wizard. This will guide you through Linear OAuth setup, repository configuration, and tool permissions. Alternatively, you can clone the repository from GitHub for development. Detailed setup instructions are available in the GitHub repository.
Ready to automate your development workflow?
Join product teams shipping 10x faster with Cyrus.
