illegalstudio

illegalstudio / lazyagent

Public

Monitor all your coding agents from one terminal - Claude Code, Cursor, OpenCode, pi and more

lazyagent.dev agent-dashboard agent-monitoring ai claude-code claude-code-monitor
16
5
100% credibility
Found Mar 12, 2026 at 16 stars -- GitGems finds repos before they trend. Get early access to the next one.
Sign Up Free
AI Analysis
Go
AI Summary

lazyagent is a terminal UI, macOS menu bar app, and HTTP API for monitoring running instances of Claude Code, Cursor, pi coding agent, and OpenCode by observing their session data files without modifications.

Star Growth

See how this repo grew from 16 to 16 stars Sign Up Free
Repurpose This Repo

Repurpose is a Pro feature

Generate ready-to-use prompts for X threads, LinkedIn posts, blog posts, YouTube scripts, and more -- with full repo context baked in.

Unlock Repurpose
AI-Generated Review

What is lazyagent?

lazyagent monitors running AI coding agent sessions from Claude Code (CLI and Desktop), Cursor, pi, and OpenCode by watching their JSONL and SQLite files—no agent changes needed. Launch a terminal UI like lazygit for session lists with activity badges (thinking, writing, idle), sparklines, token costs, git branches, and recent tools/conversations. It also runs as a macOS menu bar app or HTTP API on port 7421 with SSE for real-time updates. Single Go binary handles all modes: `lazyagent --tui --tray --api`.

Why is it gaining traction?

Inspired by lazygit's intuitive TUI, it stands out for multi-agent devs juggling Claude, Cursor, and others—spot waiting sessions or high costs at a glance without tab-switching. Editor integration (o key opens CWD in VS Code/nvim), custom naming, and filters beat basic log tailing. Homebrew install and combinable interfaces hook power users tired of scattered terminals.

Who should use this?

AI coding enthusiasts running parallel agents on complex projects (e.g., full-stack devs with Cursor for frontend, Claude CLI for backend refactors). Ideal for macOS users monitoring token burn during long sessions or teams debugging agent hangs. Skip if you stick to one tool like lazy nvim github setups.

Verdict

Grab it for poly-agent oversight—features punch above 15 stars, with solid TUI and API. 1.0% credibility reflects early stage (no tests in some providers, macOS-only tray), but Homebrew cask and MIT license make it low-risk to try. Watch for notifications and cross-platform tray. (187 words)

Sign up to read the full AI review Sign Up Free

Similar repos coming soon.