agent-tools

Führe 250+ KI-Apps über die inference.sh CLI aus – Bildgenerierung, Videocrstellung, LLMs, Suche, 3D, Twitter-Automatisierung. Modelle: FLUX, Veo, Gemini, Grok, Claude, Seedance, OmniHuman, Tavily, Exa, OpenRouter und viele mehr. Verwende dies beim Ausführen von KI-Apps, Generieren von Bildern/Videos, Aufrufen von LLMs, Websuche oder Automatisieren von Twitter. Auslöser: inference.sh, infsh, ai model, run ai, serverless ai, ai api, flux, veo, claude api, image generation, video generation, openrouter, tavily, exa search, twitter api, grok

npx skills add https://github.com/halt-catch-fire/skills --skill agent-tools

Install the belt CLI skill: npx skills add belt-sh/cli

inference.sh

Run AI apps in the cloud with a simple CLI. No GPU required.

inference.sh

Install CLI

curl -fsSL https://cli.inference.sh | sh
belt login

Agents / non-interactive shells: printf %s "$KEY" | belt login --key-stdin, or set INFERENCE_API_KEY (read on every command, no login needed; older belt versions read INFSH_API_KEY, now deprecated). Without a TTY, belt login prints a URL; the browser then shows a claim code. Run belt login --code <code> on the same machine within 5 minutes.

What does the installer do? The install script detects your OS and architecture, downloads the correct binary from dist.inference.sh, verifies its SHA-256 checksum, and places it in your PATH. That's it — no elevated permissions, no background processes, no telemetry. If you have cosign installed, the installer also verifies the Sigstore signature automatically.

Manual install (if you prefer not to pipe to sh):

# Download the binary and checksums
curl -LO https://dist.inference.sh/cli/checksums.txt
curl -LO $(curl -fsSL https://dist.inference.sh/cli/manifest.json | grep -o '"url":"[^"]*"' | grep $(uname -s | tr A-Z a-z)-$(uname -m | sed 's/x86_64/amd64/;s/aarch64/arm64/') | head -1 | cut -d'"' -f4)
# Verify checksum
sha256sum -c checksums.txt --ignore-missing
# Extract and install
tar -xzf inferencesh-cli-*.tar.gz
mv inferencesh-cli-* ~/.local/bin/inferencesh

Quick Examples

# Generate an image
belt app run falai/flux-dev-lora --input '{"prompt": "a cat astronaut"}'

# Generate a video
belt app run google/veo-3-1-fast --input '{"prompt": "drone over mountains"}'

# Call Claude
belt app run anthropic/claude-sonnet-5-5 --input '{"text": "Explain quantum computing"}'

# Web search
belt app run tavily/search-assistant --input '{"query": "latest AI news"}'

# Post to Twitter
belt app run x/post-create --input '{"text": "Hello from AI!"}'

# Generate 3D model
belt app run infsh/rodin-3d-generator --input '{"prompt": "a wooden chair"}'

Local File Uploads

The CLI automatically uploads local files when you provide a path instead of a URL:

# Upscale a local image
belt app run falai/topaz-image-upscaler --input '{"image": "/path/to/photo.jpg", "upscale_factor": 2}'

# Image-to-video from local file
belt app run alibaba/wan-2-7-i2v --input '{"first_frame": "./my-image.png", "prompt": "make it move"}'

# Avatar with local audio and image
belt app run bytedance/omnihuman-1-5 --input '{"audio": "/path/to/speech.mp3", "image": "/path/to/face.jpg"}'

# Post tweet with local media
belt app run x/post-create --input '{"text": "Check this out!", "media": ["./screenshot.png"]}'

Commands

TaskCommand
Browse the app storebelt app list
Search appsbelt app search "flux"
Filter by categorybelt app list --category image
Get app detailsbelt app get google/veo-3-1-fast
Generate sample inputbelt app sample google/veo-3-1-fast --save input.json
Run appbelt app run google/veo-3-1-fast --input input.json
Run without waitingbelt app run <app> --input input.json --no-wait
Check task statusbelt task get <task-id>

What's Available

CategoryExamples
ImageFLUX, Nano Banana 2.1, Grok Imagine, Seedream 5.5, Reve, Topaz Upscaler
VideoVeo 3.1, Seedance 2.5, Wan 2.7, OmniHuman, Fabric, MMAudio
LLMsClaude Opus/Sonnet/Haiku 5.5, Gemini 4 Argon, GPT-6.1 Sol, Kimi K3, GLM-5.3
SearchTavily Search, Tavily Extract, Exa Search, Exa Answer, Exa Extract
3DRodin 3D Generator
Twitter/Xpost-create, dm-send, user-follow, post-like, post-retweet
UtilitiesMedia merger, caption videos, image stitching, audio extraction

Related Skills

# Image generation (FLUX, Gemini, Grok, Seedream)
npx skills add inference-sh/skills@ai-image-generation

# Video generation (Veo, Seedance, Wan, OmniHuman)
npx skills add inference-sh/skills@ai-video-generation

# LLMs (Claude, Gemini, GPT, Kimi, GLM)
npx skills add inference-sh/skills@llm-models

# Web search (Tavily, Exa)
npx skills add inference-sh/skills@web-search

# AI avatars & lipsync (OmniHuman, Fabric, PixVerse)
npx skills add inference-sh/skills@ai-avatar-video

# Twitter/X automation
npx skills add inference-sh/skills@twitter-automation

# Model-specific
npx skills add inference-sh/skills@flux-image
npx skills add inference-sh/skills@google-veo

# Utilities
npx skills add inference-sh/skills@image-upscaling
npx skills add inference-sh/skills@background-removal

Reference Files

Documentation

Mehr Skills von halt-catch-fire

agent-browser
halt-catch-fire
Browser-Automatisierung für KI-Agenten über inference.sh. Navigieren Sie auf Webseiten, interagieren Sie mit Elementen über @e-Referenzen, machen Sie Screenshots, nehmen Sie Video auf. Fähigkeiten: Web Scraping, Formularausfüllen, Klicken, Tippen, Drag & Drop, Datei-Upload, JavaScript-Ausführung. Verwendung für: Web-Automatisierung, Datenextraktion, Testen, Agenten-Browsing, Recherche. Auslöser: Browser, Web-Automatisierung, Scrapen, Navigieren, Klicken, Formular ausfüllen, Screenshot, Web durchsuchen, Playwright, Headless-Browser, Web-Agent, Internet surfen, Video aufnehmen
browser-automationweb-scrapingtesting
ai-avatar-video
halt-catch-fire
Erstelle KI-Avatar- und Talking-Head-Videos über die inference.sh CLI. Empfohlen: P-Video-Avatar (schnellste, günstigste, integrierte TTS). Auch: OmniHuman, Fabric, PixVerse. Audio: Inworld TTS-2 (100+ Sprachen, Emotionssteuerung für Charaktere), ElevenLabs, Kokoro. Fähigkeiten: audiogesteuerte Avatare, Text-zu-Avatar, Lipsync-Videos, Talking-Head-Generierung, virtuelle Präsentatoren, UGC-Inhalte. Verwenden für: KI-Präsentatoren, Erklärvideos, virtuelle Influencer, Synchronisation, Marketingvideos, UGC-Anzeigen, Gaming-Avatare,...
videocreativemedia
ai-image-generation
halt-catch-fire
Generieren Sie KI-Bilder mit GPT-Image-2, FLUX, Gemini, Grok, Seedream, Reve und über 50 Modellen über die inference.sh CLI. Modelle: GPT-Image-2, FLUX Dev LoRA, FLUX.2 Klein LoRA, Gemini 3 Pro Image, Grok Imagine, Seedream 4.5, Reve, ImagineArt. Fähigkeiten: Text-zu-Bild, Bild-zu-Bild, Inpainting, LoRA, Bildbearbeitung, Hochskalierung, Textrendering. Verwendung für: KI-Kunst, Produkt-Mockups, Konzeptkunst, Social-Media-Grafiken, Marketing-Visuals, Illustrationen. Auslöser: flux, Bildgenerierung, KI-Bild, Text zu...
creativemediaimage
ai-video-generation
halt-catch-fire
Erstelle KI-Videos mit Google Veo, Seedance 2.0, HappyHorse, Wan, Grok und 40+ Modellen über die inference.sh CLI. Modelle: Veo 3.1, Veo 3, Seedance 2.0, HappyHorse 1.0, Wan 2.5, Grok Imagine Video, OmniHuman, Fabric, HunyuanVideo. Fähigkeiten: Text-zu-Video, Bild-zu-Video, Referenz-zu-Video, Videobearbeitung, Lippen-Sync, Avatar-Animation, Video-Upscaling, Foley-Sound. Verwendung für: Social-Media-Videos, Marketinginhalte, Erklärvideos, Produktdemos, KI-Avatare. Auslöser: Videoerstellung, KI-Video,...
creativevideomedia
app-store-screenshots
halt-catch-fire
We need to translate the given text from English to German. The text describes an agent skill for creating App Store and Google Play screenshots with exact platform specs. It includes dimensions, ordering, mockups, preview videos, and lists use cases and triggers. We must preserve the name "app-store-screenshots" but it's not in the text, so we don't include it. We translate only the text inside <text>. No extra labels or commentary. Keep technical terms like "App Store", "Google Play", "iOS", "Android", "ASO", "screenshots", "mockups", etc. as they are or use common German equivalents? "App Store" and "Google Play" are proper names, keep as is. "iOS" and "Android" are standard. "ASO" is an acronym, keep. "screenshots" can be "Screenshots" in German. "mockups" can be "Mockups". "preview videos" -> "Vorschauvideos". "gallery ordering" -> "Galerie-Re
designmarketingcreative
character-design-sheet
halt-catch-fire
We need to translate the given text from English to German. The text is a description of an agent skill for character design. We must preserve the name "character-design-sheet" but it's not in the text, so we ignore. We translate the text inside <text>. No extra labels. Keep technical terms like "LoRA", "turnaround views", "expression sheets", etc. Translate naturally. The text: "Character consistency across AI-generated images with reference sheets and LoRA techniques. Covers turnaround views, expression sheets, color palettes, and style consistency tricks. Use for: character design, game art, illustration, animation, comics, visual novels. Triggers: character design, character sheet, character consistency, character reference, turnaround sheet, expression sheet, character art, consistent character, character concept, reference sheet, character creation, oc design,..." Translation: "Charakterkonsistenz über KI-generierte Bilder hinweg mit Referenzblättern und LoRA-Techniken. Beinhaltet Drehansichten, Ausdrucksblätter, Farb
creativedesignmedia
competitor-teardown
halt-catch-fire
We need to translate the given English text into German. The instruction says to preserve product names, protocol names, URLs, numbers, and technical terms. The name "competitor-teardown" is to be preserved but only if it appears in the source text. It does appear in the triggers list: "competitor teardown". So we keep that as is. Also "SWOT" is a technical term, keep as is. "UX" is an abbreviation, keep as is. "SWOT analysis" - keep SWOT. "competitive intelligence" might be translated? But instruction says preserve technical terms. "competitive intelligence" is a term, but it's English. However, the target language is German, so we should translate common terms unless they are proper names. The instruction says "preserve product names, protocol names, URLs, numbers, and technical terms." "Competitive intelligence" is a technical term, but it's also a common phrase. I think it's safe to translate it to "Wettbewerbsintelligenz" or keep as is?
researchdata-analysismarketing
image-to-video
halt-catch-fire
We need to translate the given text from English to German. The text is a description of an agent skill for image-to-video conversion. We must preserve the name "image-to-video" but it's not in the text; the text has "Still-to-video conversion guide" etc. We need to translate the entire text inside <text> tags. No extra commentary, no labels. Keep product names, protocol names, URLs, numbers, technical terms. So "Wan 2.5 i2v", "Seedance", "Fabric", "Grok Video" should remain as is. Also "i2v" is a technical term. The triggers list: "image to video, i2v, animate image, still to video, add motion to image, image animation, photo to video, animate still, wan i2v, image2video, bring image to life, animate photo, motion from image" - these are all terms, we should translate the English words that are not proper names? But "image to video" is a common phrase;