https://github.com/unit-mesh/unit-runtime

Unit Runtime 是一个 ChatGPT 等 AI 代码的运行环境，可一键启动并实时交互，帮助您快速构建和测试 AI 代码。Unit Runtime is an efficient and user-friendly AI code execution environment that allows for one-click startup and real-time interaction, helping you quickly build and test AI code.
https://github.com/unit-mesh/unit-runtime

copilot repl

Last synced: 3 months ago
JSON representation

Unit Runtime 是一个 ChatGPT 等 AI 代码的运行环境，可一键启动并实时交互，帮助您快速构建和测试 AI 代码。Unit Runtime is an efficient and user-friendly AI code execution environment that allows for one-click startup and real-time interaction, helping you quickly build and test AI code.

• Host: GitHub
• URL: https://github.com/unit-mesh/unit-runtime
• Owner: unit-mesh
• License: mit
• Created: 2023-03-20T02:09:02.000Z (over 1 year ago)
• Default Branch: master
• Last Pushed: 2023-09-06T12:26:26.000Z (about 1 year ago)
• Last Synced: 2024-06-15T11:32:45.504Z (5 months ago)
• Topics: copilot, repl
• Language: Kotlin
• Homepage:
• Size: 843 KB
• Stars: 112
• Watchers: 10
• Forks: 12
• Open Issues: 2
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

• awesome-ChatGPT-repositories - unit-runtime - Unit Runtime 是一个 ChatGPT 等 AI 代码的运行环境，可一键启动并实时交互，帮助您快速构建和测试 AI 代码。Unit Runtime is an efficient and user-friendly AI code execution environment that allows for one-click startup and real-time interaction, helping you quickly build and test AI code. (CLIs)

README

        
# Unit Runtime

[![CI](https://github.com/prompt-engineering/unit-runtime/actions/workflows/ci.yaml/badge.svg)](https://github.com/prompt-engineering/unit-runtime/actions/workflows/ci.yaml)

> Unit Runtime is an efficient and user-friendly AI code execution environment that allows for one-click startup and real-time interaction, helping you quickly build and test AI code.

Workflow:

```mermaid

sequenceDiagram

    participant Human

    participant LLM/ChatGPT

    participant Unit Runtime

    participant Language REPL

    Human->>+LLM/ChatGPT: Provide prompt for generated code

    LLM/ChatGPT->>+Unit Runtime: Provide code snippets/units

    Unit Runtime->>+Language REPL: Compile and return

    Language REPL-->>-Unit Runtime: Output result

    Unit Runtime-->>-LLM/ChatGPT: Display processing result

    LLM/ChatGPT-->>-Human: Verify/modify code

```

For examples:

1. generate a "Hello, world" and send to Kotlin Repl

```kotlin

@RestController

object Pages {

   @GetMapping("/")

   fun main() = "Hello World!"

}

```

2. will start a server like: [http://localhost:10043](http://localhost:10043) , you can test and verify it.

## Websocket API

server: `ws://localhost:8080/repl`

input:

```kotlin

@Serializable

data class InterpreterRequest(

    var id: Int = -1,

    val code: String,

    val language: String = "kotlin",

    val framework: String = "spring",

    val history: Boolean = false

)

```

output:

```kotlin

@Serializable

data class Message(

    var id: Int = -1,

    var resultValue: String,

    var className: String = "",

    var msgType: MessageType = MessageType.NONE,

    var content: MessageContent? = null,

)

```

## Todos

- Backend

    - [x] Kotlin

        - [x] basic REPL

        - [ ] Spring Boot framework based on [https://github.com/JetBrains/kotless](https://github.com/JetBrains/kotless)

        - [x] Ktor framework based on [https://github.com/JetBrains/kotless](https://github.com/JetBrains/kotless)

    - [x] TypeScript

        - [x] basic REPL

        - [x] Deno with Hono

    - [ ] Java

    - [ ] Python

- [x] Frontend

    - [x] React with TypeScript and Babel

    - [ ] Vue

    - [ ]Angular

## Development

1. git clone `https://github.com/prompt-engineering/unit-runtime`

2. `./gradlew bootRun`

API:

## LICENSE

This code is distributed under the MIT license. See [LICENSE](./LICENSE) in this directory.