https://github.com/statelyai/agent

Create state-machine-powered LLM agents using XState
https://github.com/statelyai/agent

agents ai llm state-machine statechart workflow

Last synced: 3 days ago
JSON representation

Create state-machine-powered LLM agents using XState

• Host: GitHub
• URL: https://github.com/statelyai/agent
• Owner: statelyai
• Created: 2023-12-21T22:03:31.000Z (about 1 year ago)
• Default Branch: next
• Last Pushed: 2024-12-28T04:30:05.000Z (10 days ago)
• Last Synced: 2024-12-28T12:09:29.923Z (10 days ago)
• Topics: agents, ai, llm, state-machine, statechart, workflow
• Language: TypeScript
• Homepage: https://stately.ai/docs/agents
• Size: 1.16 MB
• Stars: 198
• Watchers: 11
• Forks: 14
• Open Issues: 5
• Metadata Files:
  • Readme: readme.md
  • Changelog: CHANGELOG.md

Awesome Lists containing this project

README

        
# Stately Agent

Stately Agent is a flexible framework for building AI agents using state machines. Stately agents go beyond normal LLM-based AI agents by:

- Using state machines to guide the agent's behavior, powered by [XState](https://stately.ai/docs/xstate)

- Incorporating **observations**, **message history**, and **feedback** to the agent decision-making and text-generation processes, as needed

- Enabling custom **planning** abilities for agents to achieve specific goals based on state machine logic, observations, and feedback

- First-class integration with the [Vercel AI SDK](https://sdk.vercel.ai/) to easily support multiple model providers, such as OpenAI, Anthropic, Google, Mistral, Groq, Perplexity, and more

**Read the documentation: [stately.ai/docs/agents](https://stately.ai/docs/agents)**