cyrusagents/cyrus

The Claude Code background agent for Linear, Slack, Github, GitLab etc. you deploy anywhere. Supports Codex, Cursor and Gemini too.

View on GitHub ↗Jump to charts ↓Open shareable report

Summary Information

Updated 48 minutes ago
Added to GitGenius on August 31st, 2026
Created on April 19th, 2025
Open Issues & Pull Requests: 104 (+0)
Number of forks: 161
Total Stargazers: 793 (+0)
Total Subscribers: 3 (+0)

Repository Insights (GitGenius)

Median issue/PR response: 6.5 hours
Mean response time: 5.4 days
90th percentile: 10.4 days
Tracked items: 76

How this project is maintained

Around half of the issues opened in the past year never receive a reply. 100% of open issues come from outside the core team, so the backlog reflects real-world use rather than internal planning. 39% of tracked open issues have had no activity in three months. Only 8% of issues opened in the past year have been closed. Three people close 73% of everything that gets resolved.

Charts & Analytics

Fetching additional details & charts...

Issue Activity (beta)

Open issues: 48
New in 7 days: 6
Closed in 7 days: 0
Avg open age: 116 days
Stale 30+ days: 33
Stale 90+ days: 19

Recent activity

Opened in 7 days: 6
Closed in 7 days: 0
Comments in 7 days: 0
Events in 7 days: 0

Top labels

  • good first issue (4)
  • bug (1)

Detailed Description

Cyrus is an AI agent that integrates Claude Code with project management and communication platforms to automate engineering tasks across your infrastructure.

The tool solves the problem of disconnected AI assistance in development workflows by acting as a background agent that connects to Linear, Slack, GitHub, GitLab and other platforms. It listens for events and requests across these systems, then uses Claude Code to perform engineering work—such as code analysis, generation, or issue resolution—and reports results back to the originating platform. The agent runs as a self-hosted service, giving you control over where your code and AI interactions execute.

Cyrus suits teams that want AI-assisted engineering integrated directly into their existing toolchain without switching contexts between platforms. It works best for organizations comfortable managing their own deployment and those already using Claude, though the tool also supports alternative AI models including Codex, Cursor, and Gemini. The self-hosted model appeals to teams with security or compliance requirements around code handling, as well as those seeking tighter integration with internal systems than SaaS alternatives typically provide.

Development on the tool shows consistent engagement with regular commits across multiple areas of the codebase. The project maintains active responsiveness to issues and pull requests, indicating the maintainers are present and addressing problems as they arise. Work spans both core agent functionality and integrations with various platforms, suggesting the team prioritizes expanding the tool's reach across different development ecosystems. The codebase demonstrates ongoing refinement rather than abandonment, with changes distributed across features, fixes, and infrastructure rather than concentrated in any single area.