ntd4996/agentpet — A desktop pet for macOS & Windows that monitors your AI coding agents (Claude Code, Codex, Cursor, G…

Description and use

**Brief Summary**
AgentPet is a cross‑platform desktop companion (macOS & Windows) that visualizes the activity of AI coding agents such as Claude Code, Codex, Cursor, Gemini, etc., in real time. As you code, the pet grows, you can feed it tokens, level it up, and compete on a leaderboard, turning AI‑assisted development into a gamified experience.

**Value**
AgentPet gives developers an immediate, low‑friction way to surface the inner workings of AI coding agents—API calls, token usage, model responses—without having to build a custom monitoring stack. By turning these signals into a playful “pet” that evolves with usage, it encourages continuous experimentation, helps teams spot performance or cost anomalies, and makes AI‑augmented development more engaging for both individuals and groups.

**Practical Adoption Path**

1. **Clone & Install** – The project is a Swift‑based desktop app; install via the provided release binaries or build from source on macOS/Windows.
2. **Connect Your Agent** – Use the exposed SDK/CLI configuration to point AgentPet at the desired AI service (Claude, Codex, Gemini, etc.) by supplying API keys or endpoint URLs.
3. **Instrument Your Workflow** – Add the lightweight AgentPet SDK or CLI wrapper to your existing build or editor scripts; the wrapper automatically emits the required telemetry (token count, request latency, language metadata).
4. **Start Coding** – The pet appears on your desktop, reflecting real‑time activity; you can feed tokens, level up, and monitor the leaderboard.
5. **Scale** – For team‑wide adoption, share the same configuration file or run AgentPet in a shared VM/container, allowing multiple developers to see collective progress and compare agent performance.

**Production Readiness**

• **Activity & Community**: 251 stars, 45 forks, recent commits (as of 2026‑06‑23) and a growing issue/PR response rate indicate an active maintainer base.
• **Stability**: The Swift codebase is mature, with clear separation between UI and telemetry layers, making it easy to integrate into CI pipelines or sandbox environments.
• **Ecosystem Fit**: It exposes standard signals (API/SDK/CLI, language metadata) that align with typical RAG or agent‑workflow pipelines, reducing integration effort.
• **Risks**: Licensing and security posture still need a final audit, and long‑term maintainer commitment should be confirmed before mission‑critical deployment.

Overall, AgentPet is a high‑readiness OSS candidate for pilots that want quick visibility into AI coding agents while adding a gamified feedback loop for developers.

Problem

ntd4996/agentpet helps add AI capability without starting from a blank model stack.

Outcome

High for an OSS candidate: recent activity, adoption, and ecosystem signals are strong enough for a serious pilot.

Workflow

• prototype AI features
• build RAG or agent workflows
• evaluate model tooling

Evidence

A desktop pet for macOS & Windows that monitors your AI coding agents (Claude Code, Codex, Cursor, Gemini...) in real time, and grows as you code, feed it tokens, level it up, climb the leaderboard.

Source