{"id":35882922,"url":"https://github.com/arimxyer/models","last_synced_at":"2026-03-08T21:15:07.240Z","repository":{"id":331762105,"uuid":"1130545281","full_name":"arimxyer/models","owner":"arimxyer","description":"CLI and TUI for browsing AI models, benchmarks, and coding agents. Compare 2000+ models across 85+ providers, explore ~400 benchmark entries from Artificial Analysis, and track 12+ coding agents with version detection.","archived":false,"fork":false,"pushed_at":"2026-02-26T00:18:47.000Z","size":10157,"stargazers_count":115,"open_issues_count":1,"forks_count":5,"subscribers_count":0,"default_branch":"main","last_synced_at":"2026-02-26T00:41:33.790Z","etag":null,"topics":["ai","anamolyco","artificial-analysis","benchmarks","claude-code","codex","coding-agents","gemini-cli","llm","models","models-dev","opencode","ratatui","rust","sst","sst-inspired","tui"],"latest_commit_sha":null,"homepage":"","language":"Rust","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/arimxyer.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2026-01-08T16:53:39.000Z","updated_at":"2026-02-26T00:18:50.000Z","dependencies_parsed_at":"2026-02-26T00:05:13.630Z","dependency_job_id":null,"html_url":"https://github.com/arimxyer/models","commit_stats":null,"previous_names":["arimxyer/models"],"tags_count":22,"template":false,"template_full_name":null,"purl":"pkg:github/arimxyer/models","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/arimxyer%2Fmodels","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/arimxyer%2Fmodels/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/arimxyer%2Fmodels/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/arimxyer%2Fmodels/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/arimxyer","download_url":"https://codeload.github.com/arimxyer/models/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/arimxyer%2Fmodels/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":29994805,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-03-02T01:47:34.672Z","status":"online","status_checked_at":"2026-03-02T02:00:07.342Z","response_time":60,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["ai","anamolyco","artificial-analysis","benchmarks","claude-code","codex","coding-agents","gemini-cli","llm","models","models-dev","opencode","ratatui","rust","sst","sst-inspired","tui"],"created_at":"2026-01-08T19:18:45.717Z","updated_at":"2026-03-08T21:15:07.222Z","avatar_url":"https://github.com/arimxyer.png","language":"Rust","funding_links":[],"categories":["Applications","💻 Apps","Rust","Terminal","Table of Contents","AI Tools"],"sub_categories":["🚀 Productivity and Utilities","CLI Utilities"],"readme":"# models\n\n\u003cp align=\"center\"\u003e\n  \u003ca href=\"https://crates.io/crates/modelsdev\"\u003e\u003cimg src=\"https://img.shields.io/crates/v/modelsdev.svg?label=version\" alt=\"Version\"\u003e\u003c/a\u003e\n  \u003ca href=\"https://github.com/arimxyer/models/actions/workflows/ci.yml\"\u003e\u003cimg src=\"https://github.com/arimxyer/models/actions/workflows/ci.yml/badge.svg\" alt=\"CI\"\u003e\u003c/a\u003e\n  \u003ca href=\"https://opensource.org/licenses/MIT\"\u003e\u003cimg src=\"https://img.shields.io/badge/License-MIT-yellow.svg\" alt=\"License: MIT\"\u003e\u003c/a\u003e\n\u003c/p\u003e\n\nA fast CLI and TUI for browsing AI models, benchmarks, and coding agents.\n\n- **Models Tab**: Browse 2000+ models across 85+ providers from [models.dev](https://models.dev), categorized by type (Origin, Cloud, Inference, Gateway, Dev Tool)\n- **Agents Tab**: Track AI coding assistants (Claude Code, Aider, Cursor, etc.) with version detection and GitHub integration\n- **Agents CLI**: View changelogs, check release status, and compare versions for AI coding tools — `agents status`, `agents claude`, and more\n- **Benchmarks Tab**: Compare model performance across 15+ benchmarks from [Artificial Analysis](https://artificialanalysis.ai), with creator filtering by source, region, and type\n\n\u003cvideo src=\"https://github.com/user-attachments/assets/07c750f4-ca47-4f89-8a32-99e0be5004d8\" controls width=\"100%\"\u003e\u003c/video\u003e\n\n## What's New\n\n### Agents CLI\n- **`agents` command** — view changelogs, check status, browse versions for AI coding tools directly from the terminal\n- **Status table** — see installed vs latest version, 24h release indicator, and release frequency at a glance\n- **Interactive picker** — fuzzy-select any version with `--pick`, view its changelog\n- **Dual entry point** — use as `models agents` or create an `agents` symlink for standalone usage\n\n### Recent Highlights\n- **Free models filter** — press `4` on the Models tab to show only free models\n- **Sort direction toggle** — press `S` to flip sort direction on Models/Benchmarks tabs\n- **Changelog search** — `/` searches across agent changelogs with highlighted matches and `n`/`N` navigation\n- **Styled markdown** — agent changelogs rendered with headers, bold, inline code, and URLs\n- **Corporate proxy support** — TLS now uses OS trust store, fixing `UnknownIssuer` errors behind corporate proxies\n- **Fast agents CLI** — concurrent GitHub fetching and version detection, on par with native Go tooling\n- **91% open weights match rate** — three-stage Jaro-Winkler pipeline for per-model open/closed detection\n- **~400 benchmark entries** from Artificial Analysis with creator filtering by region and type\n\n## Features\n\n### Models Tab\n- **CLI commands** for scripting and quick lookups\n- **Interactive TUI** for browsing and comparing models\n- **Provider categories** — filter and group providers by type (Origin, Cloud, Inference, Gateway, Dev Tool)\n- **Cross-provider search** to compare the same model across different providers\n- **Copy to clipboard** with a single keypress\n- **JSON output** for scripting and automation\n\n### Agents Tab\n- **Curated catalog** of 12+ AI coding assistants\n- **Version detection** — automatically detects installed agents\n- **GitHub integration** — stars, releases, changelogs, update availability\n- **Styled changelogs** — markdown rendering with syntax highlighting in the detail pane\n- **Changelog search** — search across changelogs with highlighted matches and `n`/`N` jump-to-match\n- **Persistent cache** — instant startup with ETag-based conditional fetching\n- **Customizable tracking** — choose which agents to monitor\n\n### Benchmarks Tab\n- **~400 benchmark entries** from Artificial Analysis with quality, speed, and pricing scores\n- **Auto-updating** — data fetched fresh from CDN on every launch; GitHub Action refreshes source data every 30 minutes\n- **Creator sidebar** with 40+ creators — group by region or type with colored section headers\n- **Per-model open weights detection** — runtime matching against models.dev, with source filter toggle\n- **Quick-sort keys** — instantly sort by Intelligence, Date, or Speed\n- **Dynamic columns** — list columns adapt to show the most relevant benchmarks for the active sort\n- **Detail panel** — full benchmark breakdown with indexes, scores, performance, and pricing\n\n## Installation\n\n### Cargo (from crates.io)\n\n```bash\ncargo install modelsdev\n```\n\n### Homebrew (macOS/Linux)\n\n```bash\nbrew install arimxyer/tap/models\n```\n\n### Scoop (Windows)\n\n```powershell\nscoop install extras/models\n```\n\n\u003e **Migrating from the custom bucket?** Run `scoop bucket rm arimxyer` — Scoop Extras handles updates automatically.\n\n### Arch Linux (AUR)\n\n```bash\nparu -S models-bin   # or: yay -S models-bin\n```\n\n\u003e Maintained by [@Dominiquini](https://aur.archlinux.org/packages/models-bin)\n\n### Debian / Ubuntu\n\nDownload the `.deb` from [GitHub Releases](https://github.com/arimxyer/models/releases) and install:\n\n```bash\n# Download the latest .deb for your architecture (amd64 or arm64)\nsudo dpkg -i modelsdev_*_amd64.deb\n```\n\n### Fedora / RHEL\n\nDownload the `.rpm` from [GitHub Releases](https://github.com/arimxyer/models/releases) and install:\n\n```bash\n# Download the latest .rpm for your architecture (x86_64 or aarch64)\nsudo rpm -i modelsdev-*.x86_64.rpm\n```\n\n\u003e **Verifying downloads**: Each GitHub Release includes a `SHA256SUMS` file. After downloading, verify with: `sha256sum -c SHA256SUMS --ignore-missing`\n\n### Pre-built binaries\n\nDownload the latest release for your platform from [GitHub Releases](https://github.com/arimxyer/models/releases).\n\n### Build from source\n\n```bash\ngit clone https://github.com/arimxyer/models\ncd models\ncargo build --release\n./target/release/models\n```\n\n## TUI Usage\n\n### Interactive Browser\n\nRun `models` with no arguments to launch the interactive TUI:\n\n```bash\nmodels\n```\n\n![Models tab screenshot](public/assets/models-screenshot.png)\n\n### Keybindings\n\n**Global**\n| Key | Action |\n|-----|--------|\n| `]` / `[` | Switch tabs (Models / Agents / Benchmarks) |\n| `?` | Show context-aware help |\n| `q` | Quit |\n\n**Navigation**\n| Key | Action |\n|-----|--------|\n| `j` / `↓` | Move down |\n| `k` / `↑` | Move up |\n| `g` | Jump to first item |\n| `G` | Jump to last item |\n| `Ctrl+d` / `PageDown` | Page down |\n| `Ctrl+u` / `PageUp` | Page up |\n| `Tab` / `Shift+Tab` | Switch panels |\n| `←` / `→` | Switch panels |\n\n**Search**\n| Key | Action |\n|-----|--------|\n| `/` | Enter search mode |\n| `Enter` / `Esc` | Exit search mode |\n| `Esc` | Clear search (in normal mode) |\n\n### Models Tab\n\n**Filters \u0026 Sort**\n| Key | Action |\n|-----|--------|\n| `s` | Cycle sort (name → date → cost → context) |\n| `S` | Toggle sort direction (asc/desc) |\n| `1` | Toggle reasoning filter |\n| `2` | Toggle tools filter |\n| `3` | Toggle open weights filter |\n| `4` | Toggle free models filter |\n| `5` | Cycle provider category filter (All → Origin → Cloud → Inference → Gateway → Tool) |\n| `6` | Toggle category grouping |\n\n**Copy \u0026 Open**\n| Key | Action |\n|-----|--------|\n| `c` | Copy `provider/model-id` |\n| `C` | Copy `model-id` only |\n| `o` | Open provider docs in browser |\n| `D` | Copy provider docs URL |\n| `A` | Copy provider API URL |\n\n### Agents Tab\n\n![Agents tab screenshot](public/assets/agents-screenshot.png)\n\n**Filters \u0026 Sort**\n| Key | Action |\n|-----|--------|\n| `s` | Cycle sort (name → updated → stars → status) |\n| `1` | Toggle installed filter |\n| `2` | Toggle CLI tools filter |\n| `3` | Toggle open source filter |\n\n**Search**\n| Key | Action |\n|-----|--------|\n| `/` | Search agents and changelogs |\n| `n` | Jump to next match |\n| `N` | Jump to previous match |\n\n**Actions**\n| Key | Action |\n|-----|--------|\n| `a` | Open tracked agents picker |\n| `o` | Open docs in browser |\n| `r` | Open GitHub repo |\n| `c` | Copy agent name |\n\n### Customizing Tracked Agents\n\nBy default, models tracks 4 popular agents: Claude Code, Codex, Gemini CLI, and OpenCode.\n\nPress `a` in the Agents tab to open the picker and customize which agents you track. Your preferences are saved to `~/.config/models/config.toml`.\n\nYou can also add custom agents not in the catalog:\n\n```toml\n# ~/.config/models/config.toml\n[[agents.custom]]\nname = \"My Agent\"\nrepo = \"owner/repo\"\nbinary = \"my-agent\"\nversion_command = [\"--version\"]\n```\n\nSee [Custom Agents](docs/custom-agents.md) for the full reference.\n\n### Benchmarks Tab\n\n![Benchmarks tab screenshot](public/assets/benchmark-screenshot.png)\n\n**Quick Sort** (press again to toggle direction)\n| Key | Action |\n|-----|--------|\n| `1` | Sort by Intelligence index |\n| `2` | Sort by Release date |\n| `3` | Sort by Speed (tok/s) |\n\n**Filters \u0026 Grouping**\n| Key | Action |\n|-----|--------|\n| `4` | Cycle source filter (All / Open / Closed) |\n| `5` | Toggle region grouping |\n| `6` | Toggle type grouping |\n\n**Sort (full cycle)**\n| Key | Action |\n|-----|--------|\n| `s` | Cycle through all 20 sort columns |\n| `S` | Toggle sort direction (asc/desc) |\n\n**Actions**\n| Key | Action |\n|-----|--------|\n| `c` | Copy benchmark name |\n| `o` | Open Artificial Analysis page |\n\n---\n\n## CLI Usage\n\n### Agents CLI\n\nTrack AI coding agent releases from the command line. Install the `agents` alias during setup, or use `models agents` as a fallback.\n\n```bash\n# Create the agents alias (one-time setup)\nmkdir -p ~/.local/bin\nln -s $(which models) ~/.local/bin/agents\n```\n\n\u003e **Note:** Make sure `~/.local/bin` is in your `PATH`. For example, in **bash/zsh** add `export PATH=\"$HOME/.local/bin:$PATH\"` to your shell config, or in **fish** run `fish_add_path ~/.local/bin`.\n\n#### Status table\n\n```bash\nagents status\n```\n\n```\n┌──────────────┬─────┬───────────┬──────────┬─────────┬───────────────┐\n│ Tool         │ 24h │ Installed │ Latest   │ Updated │ Freq.         │\n├──────────────┼─────┼───────────┼──────────┼─────────┼───────────────┤\n│ Claude Code  │ ✓   │ 2.1.42    │ 2.1.42   │ 1d ago  │ ~1d           │\n│ OpenAI Codex │ ✓   │ 0.92.0    │ 0.92.0   │ 6h ago  │ ~3h           │\n│ Goose        │     │ —         │ 1.0.20   │ 3d ago  │ ~2d           │\n└──────────────┴─────┴───────────┴──────────┴─────────┴───────────────┘\n```\n\n#### View changelogs\n\n```bash\nagents claude              # Latest changelog (by CLI binary name)\nagents claude-code         # By agent ID\nagents claude --version 1.0.170  # Specific version\n```\n\n#### Browse versions\n\n```bash\nagents claude --list       # List all versions\nagents claude --pick       # Interactive fuzzy picker\n```\n\n#### Other commands\n\n```bash\nagents latest              # All releases from last 24 hours\nagents list-sources        # List all available agents\nagents claude --web        # Open GitHub releases in browser\n```\n\n### Models CLI\n\n#### List providers\n\n```bash\nmodels list providers\n```\n\n#### List models\n\n```bash\n# All models\nmodels list models\n\n# Models from a specific provider\nmodels list models anthropic\n```\n\n#### Show model details\n\n```bash\nmodels show claude-opus-4-5-20251101\n```\n\n```\nClaude Opus 4.5\n===============\n\nID:          claude-opus-4-5-20251101\nProvider:    Anthropic (anthropic)\nFamily:      claude-opus\n\nLimits\n------\nContext:     200k tokens\nMax Output:  64k tokens\n\nPricing (per million tokens)\n----------------------------\nInput:       $5.00\nOutput:      $25.00\nCache Read:  $0.50\nCache Write: $6.25\n\nCapabilities\n------------\nReasoning:   Yes\nTool Use:    Yes\nAttachments: Yes\nModalities:  text, image, pdf -\u003e text\n\nMetadata\n--------\nReleased:    2025-11-01\nUpdated:     2025-11-01\nKnowledge:   2025-03-31\nOpen Weights: No\n```\n\n#### Search models\n\n```bash\nmodels search \"gpt-4\"\nmodels search \"claude opus\"\n```\n\n#### JSON output\n\nAll model commands support `--json` for scripting:\n\n```bash\nmodels list providers --json\nmodels show claude-opus-4-5 --json\nmodels search \"llama\" --json\n```\n\n## Data Sources\n\nLots of gratitude to the companies who do all the hard work! Shout out to the sources:\n- **Model data**: Fetched from [models.dev](https://models.dev), an open-source database of AI models maintained by [SST](https://github.com/sst/models.dev)\n- **Benchmark data**: Fetched from [Artificial Analysis](https://artificialanalysis.ai) — quality indexes, benchmark scores, speed, and pricing for ~400 model entries\n- **Agent data**: Curated catalog in [`data/agents.json`](data/agents.json) — contributions welcome!\n- **GitHub data**: Fetched from GitHub API (stars, releases, changelogs)\n\n## Roadmap\n\n- **Nix flake** — Nix packaging with a proper `flake.lock` for reproducible builds (PRs welcome!)\n\n## Contributing\n\nContributions are welcome! Please read the [Contributing Guide](CONTRIBUTING.md) before submitting a PR.\n\nThis project follows the [Contributor Covenant Code of Conduct](CODE_OF_CONDUCT.md).\n\n## License\n\nMIT\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Farimxyer%2Fmodels","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Farimxyer%2Fmodels","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Farimxyer%2Fmodels/lists"}