| Name | agentscript JSON |
| Version |
0.1.3
JSON |
| download |
| home_page | None |
| Summary | A programming language for AI agents |
| upload_time | 2024-03-29 21:40:07 |
| maintainer | None |
| docs_url | None |
| author | Patrick Barker |
| requires_python | <4.0,>=3.10 |
| license | Apache 2.0 |
| keywords |
|
| VCS |
|
| bugtrack_url |
|
| requirements |
No requirements were recorded.
|
| Travis-CI |
No Travis.
|
| coveralls test coverage |
No coveralls.
|
<!-- PROJECT LOGO -->
<br />
<p align="center">
<!-- <a href="https://github.com/agentsea/skillpacks">
<img src="https://project-logo.png" alt="Logo" width="80">
</a> -->
<h1 align="center">Agentscript</h1>
<p align="center">
A programming language for AI agents
<br />
<a href="https://github.com/agentsea/agentscript"><strong>Explore the docs »</strong></a>
<br />
<br />
<a href="https://github.com/agentsea/agentscript">View Demo</a>
·
<a href="https://github.com/agentsea/agentscript/issues">Report Bug</a>
·
<a href="https://github.com/agentsea/agentscript/issues">Request Feature</a>
</p>
<br>
</p>
Agentscript is an isomorphic programming language for AI agents, it includes both a server-side interpreter and browser-based renderer.
▶ On the server, agenscript directly interprets LMM outputs and executes actions in a streaming manner.
▶ In the browser, agentscript renders LLM outputs in a rich manner and provides live updates.
## Server-side Interpreter
The server-side interpreter is capable of executing actions in a streaming manner, and supplying updates on their results to the UI.
### Install
```bash
pip install agentscript
```
## Usage
Execute the translator tool from Python
```python
from agentscript import Interpreter, Use
from toolfuse import Tool, action
# Create a fake translator tool
class Translator(Tool):
"""A fake translator tool"""
@action
def translate(self, text: str) -> str:
return "Hola"
# Add the tool to the Use command
cmd = Use(tools=[Translator()])
# Create the interpreter supplying our Use command
interpreter = Interpreter(commands=[cmd])
# Parse the script, find the tool, and execute it
interpreter.execute("""
We need to do translation <{"type": "use", "tool": "Translator", "action": "translate", "parameters": {"text": "Hello", "options": {"from": "en", "to": "es"}}}>
""")
# Show the past invocations with the results
print(interpreter.invocations())
```
## Browser-based Renderer
### Install
```
npm i @agentsea/agentscript
```
### Usage
```javascript
import Agentscript from "@agentsea/agentscript";
(
<Agentscript text="I created this image for you <Image url='https://any.url' />" url="...">
)
```
### Components
#### Boolean
```js
(
<Agentscript text="Does this work for you? <Boolean />" >
)
```
#### Image
```js
(
<Agentscript text="I created this image for you <Image src='https://any.url' />"">
)
```
#### Invoke
```js
(
<Agentscript text='Lets check the weather <Invoke tool="Weather" action="get" parameters={"location": "Madrid"} />'>
)
```
## Dialects
The above components are known as the `common` dialect, but you can create your own dialects as well
## Roadmap
### Programable LLMs
Give agentscript the ability to program an LLM. Here we load a LoRA into a PEFT compatible LLM
```python
interpreter.execute("I need to load the weather LoRA <Load lora='weather' />")
```
### Browser components
- [ ] Select One
- [ ] Select Any
- [ ] Video
- [ ] Plan
- [ ] References
- [ ] Image with bounding box
- [ ] Task
- [ ] Markdown
- [ ] Code blocks
## Develop
To test
```sh
make test
```
To publish
```sh
make publish
```
Raw data
{
"_id": null,
"home_page": null,
"name": "agentscript",
"maintainer": null,
"docs_url": null,
"requires_python": "<4.0,>=3.10",
"maintainer_email": null,
"keywords": null,
"author": "Patrick Barker",
"author_email": "patrickbarkerco@gmail.com",
"download_url": "https://files.pythonhosted.org/packages/ab/c7/7c2a6de7a9609df90f11a2bd73549c6a528a5fa96c18cf480cd6d9f88ec4/agentscript-0.1.3.tar.gz",
"platform": null,
"description": "<!-- PROJECT LOGO -->\n<br />\n<p align=\"center\">\n <!-- <a href=\"https://github.com/agentsea/skillpacks\">\n <img src=\"https://project-logo.png\" alt=\"Logo\" width=\"80\">\n </a> -->\n\n <h1 align=\"center\">Agentscript</h1>\n\n <p align=\"center\">\n A programming language for AI agents\n <br />\n <a href=\"https://github.com/agentsea/agentscript\"><strong>Explore the docs \u00bb</strong></a>\n <br />\n <br />\n <a href=\"https://github.com/agentsea/agentscript\">View Demo</a>\n \u00b7\n <a href=\"https://github.com/agentsea/agentscript/issues\">Report Bug</a>\n \u00b7\n <a href=\"https://github.com/agentsea/agentscript/issues\">Request Feature</a>\n </p>\n <br>\n</p>\n\nAgentscript is an isomorphic programming language for AI agents, it includes both a server-side interpreter and browser-based renderer.\n\n\u25b6 On the server, agenscript directly interprets LMM outputs and executes actions in a streaming manner.\n\n\u25b6 In the browser, agentscript renders LLM outputs in a rich manner and provides live updates.\n\n## Server-side Interpreter\n\nThe server-side interpreter is capable of executing actions in a streaming manner, and supplying updates on their results to the UI.\n\n### Install\n\n```bash\npip install agentscript\n```\n\n## Usage\n\nExecute the translator tool from Python\n\n```python\nfrom agentscript import Interpreter, Use\nfrom toolfuse import Tool, action\n\n# Create a fake translator tool\nclass Translator(Tool):\n \"\"\"A fake translator tool\"\"\"\n\n @action\n def translate(self, text: str) -> str:\n return \"Hola\"\n\n\n# Add the tool to the Use command\ncmd = Use(tools=[Translator()])\n\n# Create the interpreter supplying our Use command\ninterpreter = Interpreter(commands=[cmd])\n\n# Parse the script, find the tool, and execute it\ninterpreter.execute(\"\"\"\nWe need to do translation <{\"type\": \"use\", \"tool\": \"Translator\", \"action\": \"translate\", \"parameters\": {\"text\": \"Hello\", \"options\": {\"from\": \"en\", \"to\": \"es\"}}}>\n\"\"\")\n\n# Show the past invocations with the results\nprint(interpreter.invocations())\n```\n\n## Browser-based Renderer\n\n### Install\n\n```\nnpm i @agentsea/agentscript\n```\n\n### Usage\n\n```javascript\nimport Agentscript from \"@agentsea/agentscript\";\n\n(\n <Agentscript text=\"I created this image for you <Image url='https://any.url' />\" url=\"...\">\n)\n```\n\n### Components\n\n#### Boolean\n\n```js\n(\n <Agentscript text=\"Does this work for you? <Boolean />\" >\n)\n```\n\n#### Image\n\n```js\n(\n <Agentscript text=\"I created this image for you <Image src='https://any.url' />\"\">\n)\n```\n\n#### Invoke\n\n```js\n(\n <Agentscript text='Lets check the weather <Invoke tool=\"Weather\" action=\"get\" parameters={\"location\": \"Madrid\"} />'>\n)\n```\n\n## Dialects\n\nThe above components are known as the `common` dialect, but you can create your own dialects as well\n\n## Roadmap\n\n### Programable LLMs\n\nGive agentscript the ability to program an LLM. Here we load a LoRA into a PEFT compatible LLM\n\n```python\ninterpreter.execute(\"I need to load the weather LoRA <Load lora='weather' />\")\n```\n\n### Browser components\n\n- [ ] Select One\n- [ ] Select Any\n- [ ] Video\n- [ ] Plan\n- [ ] References\n- [ ] Image with bounding box\n- [ ] Task\n- [ ] Markdown\n- [ ] Code blocks\n\n## Develop\n\nTo test\n\n```sh\nmake test\n```\n\nTo publish\n\n```sh\nmake publish\n```\n",
"bugtrack_url": null,
"license": "Apache 2.0",
"summary": "A programming language for AI agents",
"version": "0.1.3",
"project_urls": null,
"split_keywords": [],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "eb8f61e9752db8c62f275c9f1feac30d64a80eea615878eed661e4ca0c4fbfc2",
"md5": "ab3368761ebaf94c67c5f74b99bd1d06",
"sha256": "478ce080be41b3055571ac5273d24d018c5be8011c4b4416897b7524cc203def"
},
"downloads": -1,
"filename": "agentscript-0.1.3-py3-none-any.whl",
"has_sig": false,
"md5_digest": "ab3368761ebaf94c67c5f74b99bd1d06",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": "<4.0,>=3.10",
"size": 14121,
"upload_time": "2024-03-29T21:40:05",
"upload_time_iso_8601": "2024-03-29T21:40:05.992607Z",
"url": "https://files.pythonhosted.org/packages/eb/8f/61e9752db8c62f275c9f1feac30d64a80eea615878eed661e4ca0c4fbfc2/agentscript-0.1.3-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "abc77c2a6de7a9609df90f11a2bd73549c6a528a5fa96c18cf480cd6d9f88ec4",
"md5": "e674f79edf7575755571c8db71c9e7b0",
"sha256": "c5c6cc6e67629b0819338acc9dd70e02839a0ddb5ed021b79493e0c803307ae3"
},
"downloads": -1,
"filename": "agentscript-0.1.3.tar.gz",
"has_sig": false,
"md5_digest": "e674f79edf7575755571c8db71c9e7b0",
"packagetype": "sdist",
"python_version": "source",
"requires_python": "<4.0,>=3.10",
"size": 10303,
"upload_time": "2024-03-29T21:40:07",
"upload_time_iso_8601": "2024-03-29T21:40:07.690878Z",
"url": "https://files.pythonhosted.org/packages/ab/c7/7c2a6de7a9609df90f11a2bd73549c6a528a5fa96c18cf480cd6d9f88ec4/agentscript-0.1.3.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2024-03-29 21:40:07",
"github": false,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"lcname": "agentscript"
}
