Run 150+ AI apps in the cloud with a simple CLI. No GPU required.
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):
# 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"}'
Commands
| Task |
Command |
| List all apps |
infsh app list |
| Search apps |
infsh app list --search "flux" |
| Filter by category |
infsh app list --category image |
| Get app details |
infsh app get google/veo-3-1-fast |
| Generate sample input |
infsh app sample google/veo-3-1-fast --save input.json |
| Run app |
infsh app run google/veo-3-1-fast --input input.json |
| Run without waiting |
infsh app run <app> --input input.json --no-wait |
| Check task status |
infsh task get <task-id> |
What's Available
| Category |
Examples |
| Image |
FLUX, Gemini 3 Pro, Grok Imagine, Seedream 4.5, Reve, Topaz Upscaler |
| Video |
Veo 3.1, Seedance 1.5, Wan 2.5, OmniHuman, Fabric, HunyuanVideo Foley |
| LLMs |
Claude Opus/Sonnet/Haiku, Gemini 3 Pro, Kimi K2, GLM-4, any OpenRouter model |
| Search |
Tavily Search, Tavily Extract, Exa Search, Exa Answer, Exa Extract |
| 3D |
Rodin 3D Generator |
| Twitter/X |
post-tweet, post-create, dm-send, user-follow, post-like, post-retweet |
| Utilities |
Media 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, 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
1---
2name: agent-tools
3description: "Run 150+ AI apps via inference.sh CLI - image generation, video creation, LLMs, search, 3D, Twitter automation. Models: FLUX, Veo, Gemini, Grok, Claude, Seedance, OmniHuman, Tavily, Exa, OpenRouter, and many more. Use when running AI apps, generating images/videos, calling LLMs, web search, or automating Twitter. Triggers: 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"
4allowed-tools: Bash(infsh *)
5metadata:
6 source: https://skillmd.com/skills/neuralblitz/agent-tools
7---
8
9# [inference.sh](https://inference.sh)
10
11Run 150+ AI apps in the cloud with a simple CLI. No GPU required.
12
13](https://cloud.inference.sh/app/files/u/4mg21r6ta37mpaz6ktzwtt8krr/01kgjw8atdxgkrsr8a2t5peq7b.jpeg)
14
15## Install CLI
16
17```bash
18curl -fsSL https://cli.inference.sh | sh
19infsh login
20```
21
22> **What does the installer do?** The [install script](https://cli.inference.sh) 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](https://docs.sigstore.dev/cosign/system_config/installation/) installed, the installer also verifies the Sigstore signature automatically.
23>
24> **Manual install** (if you prefer not to pipe to sh):
25> ```bash
26> # Download the binary and checksums
27> curl -LO https://dist.inference.sh/cli/checksums.txt
28> 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)
29> # Verify checksum
30> sha256sum -c checksums.txt --ignore-missing
31> # Extract and install
32> tar -xzf inferencesh-cli-*.tar.gz
33> mv inferencesh-cli-* ~/.local/bin/inferencesh
34> ```
35
36## Quick Examples
37
38```bash
39# Generate an image
40infsh app run falai/flux-dev-lora --input '{"prompt": "a cat astronaut"}'
41
42# Generate a video
43infsh app run google/veo-3-1-fast --input '{"prompt": "drone over mountains"}'
44
45# Call Claude
46infsh app run openrouter/claude-sonnet-45 --input '{"prompt": "Explain quantum computing"}'
47
48# Web search
49infsh app run tavily/search-assistant --input '{"query": "latest AI news"}'
50
51# Post to Twitter
52infsh app run x/post-tweet --input '{"text": "Hello from AI!"}'
53
54# Generate 3D model
55infsh app run infsh/rodin-3d-generator --input '{"prompt": "a wooden chair"}'
56```
57
58## Commands
59
60| Task | Command |
61|------|---------|
62| List all apps | `infsh app list` |
63| Search apps | `infsh app list --search "flux"` |
64| Filter by category | `infsh app list --category image` |
65| Get app details | `infsh app get google/veo-3-1-fast` |
66| Generate sample input | `infsh app sample google/veo-3-1-fast --save input.json` |
67| Run app | `infsh app run google/veo-3-1-fast --input input.json` |
68| Run without waiting | `infsh app run <app> --input input.json --no-wait` |
69| Check task status | `infsh task get <task-id>` |
70
71## What's Available
72
73| Category | Examples |
74|----------|----------|
75| **Image** | FLUX, Gemini 3 Pro, Grok Imagine, Seedream 4.5, Reve, Topaz Upscaler |
76| **Video** | Veo 3.1, Seedance 1.5, Wan 2.5, OmniHuman, Fabric, HunyuanVideo Foley |
77| **LLMs** | Claude Opus/Sonnet/Haiku, Gemini 3 Pro, Kimi K2, GLM-4, any OpenRouter model |
78| **Search** | Tavily Search, Tavily Extract, Exa Search, Exa Answer, Exa Extract |
79| **3D** | Rodin 3D Generator |
80| **Twitter/X** | post-tweet, post-create, dm-send, user-follow, post-like, post-retweet |
81| **Utilities** | Media merger, caption videos, image stitching, audio extraction |
82
83## Related Skills
84
85```bash
86# Image generation (FLUX, Gemini, Grok, Seedream)
87npx skills add inference-sh/skills@ai-image-generation
88
89# Video generation (Veo, Seedance, Wan, OmniHuman)
90npx skills add inference-sh/skills@ai-video-generation
91
92# LLMs (Claude, Gemini, Kimi, GLM via OpenRouter)
93npx skills add inference-sh/skills@llm-models
94
95# Web search (Tavily, Exa)
96npx skills add inference-sh/skills@web-search
97
98# AI avatars & lipsync (OmniHuman, Fabric, PixVerse)
99npx skills add inference-sh/skills@ai-avatar-video
100
101# Twitter/X automation
102npx skills add inference-sh/skills@twitter-automation
103
104# Model-specific
105npx skills add inference-sh/skills@flux-image
106npx skills add inference-sh/skills@google-veo
107
108# Utilities
109npx skills add inference-sh/skills@image-upscaling
110npx skills add inference-sh/skills@background-removal
111```
112
113## Reference Files
114
115- [Authentication & Setup](references/authentication.md)
116- [Discovering Apps](references/app-discovery.md)
117- [Running Apps](references/running-apps.md)
118- [CLI Reference](references/cli-reference.md)
119
120## Documentation
121
122- [Agent Skills Overview](https://inference.sh/blog/skills/skills-overview) - The open standard for AI capabilities
123- [Getting Started](https://inference.sh/docs/getting-started/introduction) - Introduction to inference.sh
124- [What is inference.sh?](https://inference.sh/docs/getting-started/what-is-inference) - Platform overview
125- [Apps Overview](https://inference.sh/docs/apps/overview) - Understanding the app ecosystem
126- [CLI Setup](https://inference.sh/docs/extend/cli-setup) - Installing the CLI
127- [Workflows vs Agents](https://inference.sh/blog/concepts/workflows-vs-agents) - When to use each
128- [Why Agent Runtimes Matter](https://inference.sh/blog/agent-runtime/why-runtimes-matter) - Runtime benefits