Monitor all your coding agents from one terminal - Claude Code, Cursor, OpenCode, pi and more
# lazyagent   [](https://www.producthunt.com/products/lazy-agent) A terminal UI, macOS menu bar app, and HTTP API for monitoring all your coding agents — [Claude Code](https://claude.ai/code), [Cursor](https://cursor.com/), [Codex](https://developers.openai.com/codex/), [Amp](https://ampcode.com/), [pi](https://github.com/badlogic/pi-mono), and [OpenCode](https://opencode.ai/) — from a single place. No lock-in, no server, purely observational. Inspired by [lazygit](https://github.com/jesseduffield/lazygit), [lazyworktree](https://github.com/chmouel/lazyworktree), and [pixel-agents](https://github.com/pablodelucca/pixel-agents). ## Why lazyagent? Unlike other tools, lazyagent doesn't replace your workflow — it watches it. Launch agents wherever you want (terminal, IDE, desktop app), lazyagent just observes. No lock-in, no server, no account required. > ⭐ If lazyagent is useful to you, consider [starring the repo](https://github.com/illegalstudio/lazyagent) — it helps others discover it! > **Want to support lazyagent's development?** If this project saves you time or you just love it, consider [becoming a sponsor](https://github.com/sponsors/nahime0). It keeps the project alive and growing — every bit counts! ### Terminal UI  ### macOS Menu Bar App  ### HTTP API  ## How it works lazyagent watches session data from coding agents to determine what each session is doing. No modifications to any agent are needed — it's purely observational. **Supported agents:** - **Claude Code CLI** — reads JSONL from `~/.cursor/projects/*/` - **Claude Code Desktop** — same JSONL files, enriched with ses
Agent that generates comprehensive documentation, API references, architecture diagrams, and developer onboarding guides from existing code.
Agent configuration for systematic bug investigation that traces issues from error logs through the codebase to root cause with suggested fixes.
Agent for integrating third-party APIs including SDK setup, type generation, error handling, retry logic, and rate limit management.
Cursor's built-in autonomous coding agent that can make multi-file edits, run terminal commands, search the codebase, and iteratively build features with minimal human intervention.
Cloud-based autonomous coding agent that runs in the background on remote sandboxed environments, handling complex multi-step tasks while you continue working.
Cursor's multi-file editing agent within Composer mode that can create, edit, and delete files across your entire project in a single conversation.