Loading...
Loading...
Use the belt CLI — run hundreds of AI apps, manage knowledge, search skills, connect MCP servers. Purpose-built CLI interface for agent workflows — typed inputs, schema validation, no raw API calls needed.
npx skill4agent add belt-sh/skills beltwhich belt && belt --versionbrew install inference-sh/tap/belt # macos / linux (homebrew tap, signed)
scoop bucket add belt https://github.com/belt-sh/scoop-belt && scoop install belt # windows
npm install -g @inferencesh/belt # node.js (global install, pinned in package.json)curl -fsSL https://cli.inference.sh -o /tmp/belt-install.shdist.inference.shcat /tmp/belt-install.sh # review the script
sh /tmp/belt-install.sh # run after reviewbelt login
belt mebelt plugin init claude # claude code
belt plugin init codex # openai codex
belt plugin init cursor # cursorbelt suggest "what tool should i use" # unified search across apps, skills, knowledge
belt app store # browse ai apps
belt app store --category video # filter by category
belt app get <namespace/name> # see schema, pricing, functions
belt app sample <namespace/name> # generate sample input json
belt app run <namespace/name> --input input.json # run an app
belt balance # check creditsbelt app get bytedance/seedance-2-0 # check schema — file fields accept local paths
belt app sample bytedance/seedance-2-0 --save input.json
# edit input.json, then:
belt app run bytedance/seedance-2-0 --input input.jsonfilebelt app run bytedance/seedance-2-0 --input '{"image": "./photo.jpg", "prompt": "make it cinematic"}'belt app pricing <namespace/name> # see cost formula
belt app pricing <namespace/name> --json # machine-readablebelt app get heygen/avatar-video # shows all functions with schemas
belt app sample heygen/avatar-video -f list_resources # sample for a specific function
belt app run heygen/avatar-video -f list_resources --input '{}'belt knowledge list --json # your knowledge entries
belt knowledge search "react patterns" # semantic search
belt skill list # your skills
belt skill store search "video" # find skills in the store
belt skill use <namespace/name> # load a skill on-demandbelt mcp list # browse available connectors
belt mcp connect slack # connect one
belt mcp run slack send_message --input '{"channel": "#general", "text": "hello"}'--jsonbelt app list --json
belt app store --json
belt task list --json
belt knowledge list --json
belt skill list --json
belt mcp list --json
belt secrets list --json
belt me --json
belt balance --jsonbelt app sample./your-file.jpgbelt suggestbelt task cost <task-id>belt app run --no-waitbelt task get <id>--session new# .beltsh/config.json
{"hooks_disabled": true}BELT_NO_HOOKS=1