reyamira/models

TUI and CLI for browsing models.dev, benchmarks, coding agents, and statuses for AI providers.

What it solves

It provides a centralized terminal-based interface (TUI) and command-line interface (CLI) for developers to discover, compare, and monitor the AI ecosystem. Instead of visiting multiple websites, users can track thousands of AI models, performance benchmarks, coding agents, and the real-time health of AI providers in one place.

How it works

The tool aggregates data from several sources, including models.dev for model specifications, Artificial Analysis, Epoch AI, Arena, and LLM Stats for benchmarks, and official status pages for provider health. It presents this data through a multi-tab TUI with mouse support and a corresponding CLI for programmatic access or quick lookups.

Who it’s for

AI developers and researchers who need to quickly compare model capabilities, pricing, and performance, or track the versions and health of AI coding assistants and infrastructure providers.

Highlights

  • Model Discovery: Browse over 4,000 models across 85+ providers with filters for price, context window, and capabilities.
  • Performance Benchmarking: Compare ~1,000 benchmark entries using scatter plots, radar charts, and head-to-head tables.
  • Agent Tracking: Monitor 12+ AI coding agents with automatic version detection, changelogs, and in-app update capabilities.
  • Provider Monitoring: Live health tracking for 22 AI providers across various status page platforms.

Related

  • Project
    graykode/abtop

    A TUI monitoring dashboard for AI coding agents that tracks token usage, context windows, and rate limits across multiple active sessions.

  • Project
    YoanWai/agent-manager

    A terminal-based manager for AI coding agents that consolidates multiple CLI agents into a single interface with live status tracking and integrated diff reviews.

  • Project
    IvanWng97/pixtuoid

    pixtuoid is a Rust‑based terminal UI that visualises multiple AI coding agents as animated pixel‑art coworkers in a multi‑floor office. It supports many agent CLIs (Claude Code, Codex, etc.), shows token usage, tool activity, and offers themes, weather, pets, and a lofi soundtrack—all locally with no telemetry.

  • Project
    harbor-framework/terminal-bench

    Terminal-Bench is a continuous benchmark for measuring the capabilities of frontier AI agents using a diverse and evolving set of difficult tasks.

  • Project
    SaladDay/cc-switch-cli

    A CLI and TUI switchboard for managing API providers, accounts, and system prompts across multiple AI coding assistants like Claude Code, Codex, and Gemini.