# inference.sh

> the ai runtime that compounds with every session. run any model, compose agents, stack knowledge — it never forgets.

inference.sh is a platform for building and running ai agents in production. 250+ pre-built tools (image, video, audio, text, search, 3D), durable execution, human-in-the-loop approval, real-time streaming, and a skill registry that improves with use.

## belt cli — the fastest way to use inference.sh

if you're an agent or developer, belt is the easiest way to interact with inference.sh.

install: `curl -fsSL https://cli.inference.sh | sh`

```bash
# run any ai model
belt app run pruna/flux-dev -i '{"prompt": "a cat"}'

# search 250+ tools
belt app search "image generation"

# use skills (versioned instructions that improve with use)
belt skill use my-org/my-skill

# connect MCP servers
belt mcp add github
```

learn more: https://inference.sh/belt

## what's on the platform

- **tools** (https://inference.sh/tools): 250+ ai models and integrations. image gen, video gen, audio, text, search, social, dev tools. one api, one bill.
- **agents** (https://inference.sh/agents): durable execution, persistent state, human-in-the-loop approval, multi-agent orchestration.
- **skills** (https://inference.sh/skills): versioned instructions that improve with use. security-scanned, fitness-ranked.
- **ui** (https://inference.sh/ui): ai-native react components. chat, generative ui, tool approvals. drop-in.
- **teams** (https://inference.sh/teams): shared workspace with memory, automations, integrations.
- **connectors**: MCP servers, OAuth integrations, one-command setup.

## navigate

- docs: https://inference.sh/docs (start here: https://inference.sh/docs/getting-started/introduction)
- blog: https://inference.sh/blog
- app store: https://inference.sh/apps (browse all tools)
- gpu pricing: https://inference.sh/gpus
- pricing: https://inference.sh/pricing
- api reference: https://inference.sh/docs/api/authentication

## links

- website: https://inference.sh
- github: https://github.com/inference-sh
- discord: https://discord.gg/inference
- python sdk: `pip install inferencesh`
- js sdk: `npm install @inferencesh/sdk`

## optional

- [llms-full.txt](https://inference.sh/llms-full.txt): complete documentation and blog content for deeper context