Agents et multi-agents

TypeSafe Agent Skills

typesafe-ai/skills

Official agent skills for designing applications around TypeSafe typed decisions. Development guidance complements the runtime SDKs and API.

★ 2KÉtoiles
⑂ 109Forks
12Problèmes ouverts
Langue
MITLicence
Q84Score éditorial

Vue d’ensemble

Official agent skills for designing applications around TypeSafe typed decisions. Development guidance complements the runtime SDKs and API. Start with a bounded task, such as choosing a destination for a support ticket, and let application logic control the next action.

Fonctionnalités clés

  • Official repository
  • Typed decision workflows
  • Documentation and examples
  • Decisions composed in application code
  • Works with Jev
  • MIT-licensed code

Prérequis, installation et démarrage rapide

npx skills add typesafe-ai/skills --skill typesafe-ai. Review the repository README and dependencies before installation.

Utilisation

After installation, ask your agent to consult the material when designing a TypeSafe workflow. Runtime API calls still require credentials and a billing review.

Compatibilité des modèles et cas d’usage

For the TypeSafe System One API; this is not Jev weights or a local inference engine.

Licence et notes sur les risques

The repository uses the MIT license. API access, billing and service terms apply separately.

Official client/development repository; not model weights. API access and charges apply separately.

Firecrawl

firecrawl/firecrawl

★ 161,1KTypeScript

LangChain

langchain-ai/langchain

★ 143,6KPython

RAGFlow

infiniflow/ragflow

★ 86,7KGo