eliasoulkadi/shokunin/agent-tools

inference.sh

Run 150+ AI apps in the cloud with a simple CLI. No GPU required.

[Image: [inference.sh]](https://cloud.inference.sh/app/files/u/4mg21r6ta37mpaz6ktzwtt8krr/01kgjw8atdxgkrsr8a2t5peq7b.jpeg)

Install CLI

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

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):

```bash

# 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
infsh app run falai/flux-dev-lora --input '{"prompt": "a cat astronaut"}'
 
# Generate a video
infsh app run google/veo-3-1-fast --input '{"prompt": "drone over mountains"}'
 
# Call Claude
infsh app run openrouter/claude-sonnet-45 --input '{"prompt": "Explain quantum computing"}'
 
# Web search
infsh app run tavily/search-assistant --input '{"query": "latest AI news"}'
 
# Post to Twitter
infsh app run x/post-tweet --input '{"text": "Hello from AI!"}'
 
# Generate 3D model
infsh 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
infsh app run falai/topaz-image-upscaler --input '{"image": "/path/to/photo.jpg", "upscale_factor": 2}'
 
# Image-to-video from local file
infsh app run falai/wan-2-5-i2v --input '{"image": "./my-image.png", "prompt": "make it move"}'
 
# Avatar with local audio and image
infsh app run bytedance/omnihuman-1-5 --input '{"audio": "/path/to/speech.mp3", "image": "/path/to/face.jpg"}'
 
# Post tweet with local media
infsh app run x/post-create --input '{"text": "Check this out!", "media": "./screenshot.png"}'

Commands

What's Available

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, Kimi, GLM via OpenRouter)
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

• Authentication & Setup
• Discovering Apps
• Running Apps
• CLI Reference

Documentation

• Agent Skills Overview - The open standard for AI capabilities
• Getting Started - Introduction to inference.sh
• What is inference.sh? - Platform overview
• Apps Overview - Understanding the app ecosystem
• CLI Setup - Installing the CLI
• Workflows vs Agents - When to use each
• Why Agent Runtimes Matter - Runtime benefits

Workflow

1. Discover — infsh app list --search "<keyword>" or infsh app list --category <image|video|llm|search|3d|x|utility> to find the right app
2. Inspect — infsh app get <app-id> for description, pricing, input schema, and rate limits
3. Generate sample input — infsh app sample <app-id> --save input.json to get a valid input template pre-filled with defaults
4. Customize — edit the JSON input file: replace prompts, file paths, or configuration values
5. Run — infsh app run <app-id> --input input.json for synchronous execution, or --no-wait for long-running tasks
6. Check status — infsh task get <task-id> to poll progress of async tasks; infsh task logs <task-id> for streaming output
7. Retrieve output — outputs are URLs (images, videos) or text responses; download with infsh task download <task-id>

For multi-step pipelines, chain apps: run the first app, extract its output URL, feed it as input to the next app (e.g., generate image → upscale, or generate video → add audio).

Error Handling

Checklist

• [ ] App is authenticated before running (infsh login check)
• [ ] Model supports the requested input format (image/video/text sizes)
• [ ] Task ID saved for async operations to retrieve results later
• [ ] Credit cost checked before bulk operations
• [ ] Output format confirmed (URL, file, or stdout) before passing to next step

Sources

• inference.sh CLI documentation — installation, commands, authentication
• inference.sh Apps Catalog — full app library with schemas and examples
• OpenRouter API — LLM model routing and pricing
• FLUX documentation (fal.ai, replicate.com) — image generation parameters and best practices
• Veo API (Google DeepMind) — video generation capabilities and limitations
• Tavily Search API (tavily.com) — web search and extraction endpoints
• Exa API (exa.ai) — semantic search and content extraction
• x.com Developer API — Twitter/X posting, DMs, and engagement endpoints

Anti-Patterns