arimxyer / models

models TUI and CLI for browsing AI models, benchmarks, and coding agents. • **Models Tab**: Browse 3,000+ models across 85+ providers from models.dev with capability indicators, adaptive layouts, and provider categorization • **Benchmarks Tab**: Compare model performance across 15+ benchmarks from Artificial Analysis, with head-to-head tables, scatter plots, radar charts, and creator filtering • **Agents Tab**: Track AI coding assistants (Claude Code, Aider, Cursor, etc.) with version detection, changelogs, and GitHub integration > **Video (and screenshots below) are out-of-sync with the current state of the app, I've been moving fast on making changes and so I'll have to record a new one!** What's New • **Models tab redesign** — capability indicators, adaptive provider panel, and detailed model info at a glance • **Benchmark compare mode** — head-to-head tables, scatter plots, and radar charts for selected models • **Benchmarks CLI** — list and inspect benchmark data directly from the terminal • **Linux packages** — native .deb and .rpm packages for x86_64 and aarch64 • **Agents CLI** — track agent releases, view changelogs, and compare versions from the terminal Features Models Tab • **Capability indicators** — see Reasoning, Tools, Files, and Open/Closed status at a glance in the model list • **Provider categories** — filter and group providers by type (Origin, Cloud, Inference, Gateway, Dev Tool) • **Detail panel** — capabilities, pricing, modalities, and metadata for the selected model • **Cross-provider search** to compare the same model across different providers • **Copy to clipboard** with a single keypress • **CLI commands** and **JSON output** for scripting and automation Agents Tab • **Curated catalog** of 12+ AI coding assistants • **Version detection** — automatically detects installed agents • **GitHub integration** — stars, releases, changelogs, update availability • **Styled changelogs** — markdown rendering with syntax highlighting in the detail pane • **Changelog search** — search across changelogs with highlighted matches and / jump-to-match • **Persistent cache** — instant startup with ETag-based conditional fetching • **Customizable tracking** — choose which agents to monitor Benchmarks Tab • **~400 benchmark entries** from Artificial Analysis with quality, speed, and pricing scores • **Compare mode** — select models for head-to-head tables, scatter plots, and radar charts • **Auto-updating** — benchmark data refreshed automatically every 30 minutes • **Creator sidebar** with 40+ creators — filter by region, type, or open/closed source • **Sort & filter** — sort by any metric, filter by reasoning capability, source type, and more • **Detail panel** — full benchmark breakdown with indexes, scores, performance, and pricing Agents CLI • **Status table** — see installed vs latest version, 24h release indicator, and release frequency at a glance • **Inline release browser** — opens an interactive version browser with changelog preview • **Changelogs** — view release notes for any agent by name, latest version, or explicit version • **Tracked-agent manager** — can now manage which curated agents are tracked from the CLI • **Dual entry point** — use as or create an symlink for standalone usage • **Fast** — concurrent GitHub fetching and version detection Benchmarks CLI • **Live benchmark queries** — fetch the current benchmark dataset without launching the TUI • **Interactive list picker** — use to open a filtered benchmark selector, then inspect the selected model immediately • **Detail views** — use for a direct model breakdown, with interactive disambiguation when a query matches multiple variants • **Filtering** — narrow by search text, creator, open/closed source, and reasoning status • **Sorting** — sort by any supported metric, including intelligence, coding, math, GPQA, speed, pricing, and release date • **JSON output** — pipe structured benchmark data into shell scripts and other tools Installation Cargo (from crates.io) Homebrew (macOS/Linux) > **Migrating from the tap?** Run — updates now land through bump PRs and may take a bit to merge. Scoop (Windows) > **Migrating from the custom bucket?** Run — Scoop Extras handles updates automatically. Arch Linux (AUR) > Maintained by @Dominiquini Debian / Ubuntu Download the from GitHub Releases and install: Fedora / RHEL Download the from GitHub Releases and install: > **Verifying downloads**: Each GitHub Release includes a file. After downloading, verify with: Pre-built binaries Download the latest release for your platform from GitHub Releases. Build from source TUI Usage Interactive Browser Run with no arguments to launch the interactive TUI: Keybindings **Global** | Key | Action | |-----|--------| | / | Switch tabs (Models / Agents / Benchmarks) | | | Show context-aware help | | | Quit | **Navigation** | Key | Action | |-----|--------| | / | Move down | | / | Move up | | | Jump to first item | | | Jump to last item | | / | Page down | | / | Page up | | / | Switch panels | | / | Switch panels | **Search** | Key | Action | |-----|--------| | | Enter search mode | | / | Exit search mode | | | Clear search (in normal mode) | Models Tab **Filters & Sort** | Key | Action | |-----|--------| | | Cycle sort (name → date → cost → context) | | | Toggle sort direction (asc/desc) | | | Toggle reasoning filter | | | Toggle tools filter | | | Toggle open weights filter | | | Toggle free models filter | | | Cycle provider category filter (All → Origin → Cloud → Inference → Gateway → Tool) | | | Toggle category grouping | **Copy & Open** | Key | Action | |-----|--------| | | Copy | | | Copy only | | | Open provider docs in browser | | | Copy provider docs URL | | | Copy provider API URL | Agents Tab **Filters & Sort** | Key | Action | |-----|--------| | | Cycle sort (name → updated → stars → status) | | | Toggle installed filter | | | Toggle CLI tools filter | | | Toggle open source filter | **S…