https://github.com/code-crusher/xume-ai

Open Source framework to build reliable Agentic AIs
https://github.com/code-crusher/xume-ai

agents ai

Last synced: 8 months ago
JSON representation

Open Source framework to build reliable Agentic AIs

• Host: GitHub
• URL: https://github.com/code-crusher/xume-ai
• Owner: code-crusher
• License: mit
• Created: 2024-12-30T11:05:53.000Z (about 1 year ago)
• Default Branch: main
• Last Pushed: 2025-02-07T10:21:40.000Z (about 1 year ago)
• Last Synced: 2025-02-07T11:26:48.924Z (about 1 year ago)
• Topics: agents, ai
• Language: TypeScript
• Homepage: https://xume.ai
• Size: 141 KB
• Stars: 2
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • Contributing: .github/CONTRIBUTING.md
  • License: LICENSE
  • Code of conduct: .github/CODE_OF_CONDUCT.md
  • Security: .github/SECURITY.md
  • Support: .github/SUPPORT.md

Awesome Lists containing this project

README

          
# Xume AI

![Xume AI](https://res.cloudinary.com/dor5uewzz/image/upload/v1736236211/xume-og-image_cyafxf.png)

Xume AI is a framework for building AI agents with no-code/low-code. You can quickstart with the SaaS version here: https://xume.ai

## Example Agent Flow

1. Chat with LLM to generate greeting message for a new user in Slack Channel

2. Send the message to the new user in Slack Channel

3. Generate a SQL query to save the new user in the database along with slack message id and created at timestamp

4. Execute the SQL query to save the new user in the database

![Example Xume AI Agent Setup](https://res.cloudinary.com/dor5uewzz/image/upload/v1736236211/xume-ai-example_1_eqnznv.png)

## How to run

```bash

npm run dev

```

## How to build

```bash

npm run build

```

## Framework

backend/src/

├── llms // LLM providers

├── integrations // External services

├── workflows // Agent workflows and steps

├── knowledge // Vectorized knowledge base

├── personas // Agent personas

├── guardrails // Agent guardrails

## Supported LLMs

We are using OpenAI SDK which supports `OPEN_AI_URL`, `OPENAI_MODEL`, `OPENAI_API_KEY` and `OPEN_AI_DEFAULT_HEADERS` to be passed as environment variables.

| LLM Provider | Status |

|--------------|--------|

| OpenAI       | ✅     |

| Anthropic    | ✅     |

| Groq         | ✅     |

## Supported External Services

| External Service | Status |

|------------------|--------|

| Slack            | ✅     |

| Github           | ❌     |

| Postgres         | ❌     |

| MongoDB          | ❌     |

| Linear           | ❌     |

## Supported Guardrails

- TBD

## Supported Vector Databases

- TBD