agentscript

Build AI agents that think in code. A Typescript framework for building reliable AI agents that express their plans as code and execute it in our custom built AST runtime: enabling stop/start workflows to keep humans in loop, tool-level state management, and enhanced observability.

Stars: 123

Visit

AgentScript is an open-source framework for building AI agents that think in code. It prompts a language model to generate JavaScript code, which is then executed in a dedicated runtime with resumability, state persistence, and interactivity. The framework allows for abstract task execution without needing to know all the data beforehand, making it flexible and efficient. AgentScript supports tools, deterministic functions, and LLM-enabled functions, enabling dynamic data processing and decision-making. It also provides state management and human-in-the-loop capabilities, allowing for pausing, serialization, and resumption of execution.

README:

AgentScript: Build AI agents that think in code

AgentScript is a unique open-source framework for building re-act AI agents.

npm install agentscript-ai

Check out a short demo video:

What is it?

Typical Re-act agent work like this:

Send to LLM a prompt with available tools
LLM sends back a tool call
Execute the tool and send back the result
LLM responds with another tool call
...

Wouldn't be better if LLM just told you upfront what tools to use, in which order and what to do with the results?
LLMs are great at code generation, so maybe it could just write a code to express its plan!

AgentScript does exactly that: prompts an LLM to generate code (a subset of JS) and executes it in a dedicated runtime with resumability, state persistence and interactivity (human in the loop) baked in.

How it works?

Define a runtime with tools and optionally input and output variables
Define a task to be executed (aka prompt)
AgentScript prompts LLM to genarate JS code
Code it not executed directly but parsed into an AST
AST is executed in a dedicated, safe runtime (interpreter).
No sandbox is needed - the generated code is not running directly in Node.
Execution can be paused, serialized into a database and resumed later.
(like when a tool call requires human interaction or approval).

Show me the code

Let's build an agent doing stuff with Linear.
You can see full example here.

// Configure the language model
const llm = AnthropicModel({
    model: 'claude-3-5-sonnet-latest',
    apiKey: process.env.ANTHROPIC_API_KEY,
});

// Configure the Linear client
const linear = LinearClient({
    apiKey: process.env.LINEAR_API_KEY,
});

// Define available tools.
const tools = {
    // Needed for date calculation
    addToDate,
    // Turns data into text
    summarizeData: summarizeData({ llm }),
    // The real deal
    linear: {
        searchIssues: searchIssues({ llm, linear }),
    },
};

// Define a task for the agent
const prompt = 'Give me a progress update of tasks created in the last week';

// Define the expected output
const output = s.string();

// Let the LLM generate the AgentScript code
const agent = await inferAgent({
    tools,
    output,
    llm,
    prompt,
});

LLM responds with a plan:

I'll help create a progress update for recent tasks. Here's the plan:

First, we'll search for all issues created in the last week

Then we'll take those issues and generate a summary that includes:

How many tasks were created

Their current status distribution

Key highlights or patterns

Format it in a clear, concise way

...and generates AgentScript code:

// NOTE: this is real code generated by LLM.
// it's not executed but parsed into AST and runs in a specialized runtime.

// Calculate the date from 7 days ago
const lastWeek = addToDate(new Date(), { days: -7 });

// Search for all issues created in the last week
const issues = linear.searchIssues({
    createdAfter: lastWeek,
    orderBy: 'createdAt',
});

// Create a summary of the issues found
result = summarizeData({
    data: issues,
    prompt: 'Create a progress update focusing on number of tasks created, their current status distribution, and any notable patterns. Format as a clear business update.',
});

Now execute the agent:

await executeAgent({ agent });

// See the output
console.log(agent.output);

// Check variables in the execution state
console.log(agent.root.variables);

How is it different from other frameworks?

Many products define agent as a fixed workflow (for example Glide).
They work very nice for well defined tasks, but fall short when the task is ambiguous or not known beforehand.

Then we have a bunch of orchestration frameworks (LangGraph, CrewAI, Inferable among others).
They provide architecture and make it easier to build classic re-act agents, where each tool call or decision point requires another LLM query. But this makes the LLM context grow quickly, is costly, slow and not flexible enough (try to implement a loop this way).

AgentScript takes a completely different approach. By making LLM express execution plan as code, agent can think more abstractly about the task and does not even need to know all the data to perform operations on it or make decisions. Just like a developer writing an app does not need to know all the data it would use - they can write code working on dynamic data by using if statements and loops.

Data is expressed as local variables and can be passed to tools, which can be normal deterministic functions, or LLM enabled ones, built using LangChain or any other library.

What about state management and human in the loop?

Because AgentScript works on AST, not really running the generated code, execution can be paused on each statement or a tool call. It can be serialized and put into a database, then retrieved and resumed from where it stopped.

Each tool would be able to store its state, wait for a user interaction, an event, or some time to pass. They will have built in interactivity and approval mechanism, so it will be easy to add human in the loop.

State of development

Right now we have a working code generation and runtime supporting tools and most common JS statements.

Feel free to play with it by forking our examples repo.

How to Join the Community

AgentScript is an open-source project, and we welcome contributions from everyone.

Join our Discord server - talk to us!
See Github Issues - check out what we're working on, post your ideas!

Current roadmap

Execution serialization and deserialization
More JS features:
- if statements,
- for loops,
- template literals
- arrow functions
- unary and binary operators
Input variables
Tool state
Tool interactivity
Observability and debugging

For Tasks:

Click tags to check more tools for each tasks

generate code execute tasks manage state handle interactivity serialize execution

For Jobs:

ai engineer software developer machine learning engineer data scientist research scientist

Alternative AI tools for agentscript

Similar Open Source Tools

agentscript

github

: 123

aici

The Artificial Intelligence Controller Interface (AICI) lets you build Controllers that constrain and direct output of a Large Language Model (LLM) in real time. Controllers are flexible programs capable of implementing constrained decoding, dynamic editing of prompts and generated text, and coordinating execution across multiple, parallel generations. Controllers incorporate custom logic during the token-by-token decoding and maintain state during an LLM request. This allows diverse Controller strategies, from programmatic or query-based decoding to multi-agent conversations to execute efficiently in tight integration with the LLM itself.

github

: 1.8k

llama-on-lambda

This project provides a proof of concept for deploying a scalable, serverless LLM Generative AI inference engine on AWS Lambda. It leverages the llama.cpp project to enable the usage of more accessible CPU and RAM configurations instead of limited and expensive GPU capabilities. By deploying a container with the llama.cpp converted models onto AWS Lambda, this project offers the advantages of scale, minimizing cost, and maximizing compute availability. The project includes AWS CDK code to create and deploy a Lambda function leveraging your model of choice, with a FastAPI frontend accessible from a Lambda URL. It is important to note that you will need ggml quantized versions of your model and model sizes under 6GB, as your inference RAM requirements cannot exceed 9GB or your Lambda function will fail.

github

: 150

Pandrator

Pandrator is a GUI tool for generating audiobooks and dubbing using voice cloning and AI. It transforms text, PDF, EPUB, and SRT files into spoken audio in multiple languages. It leverages XTTS, Silero, and VoiceCraft models for text-to-speech conversion and voice cloning, with additional features like LLM-based text preprocessing and NISQA for audio quality evaluation. The tool aims to be user-friendly with a one-click installer and a graphical interface.

github

: 306

chronon

Chronon is a platform that simplifies and improves ML workflows by providing a central place to define features, ensuring point-in-time correctness for backfills, simplifying orchestration for batch and streaming pipelines, offering easy endpoints for feature fetching, and guaranteeing and measuring consistency. It offers benefits over other approaches by enabling the use of a broad set of data for training, handling large aggregations and other computationally intensive transformations, and abstracting away the infrastructure complexity of data plumbing.

github

: 757

llm.c

LLM training in simple, pure C/CUDA. There is no need for 245MB of PyTorch or 107MB of cPython. For example, training GPT-2 (CPU, fp32) is ~1,000 lines of clean code in a single file. It compiles and runs instantly, and exactly matches the PyTorch reference implementation. I chose GPT-2 as the first working example because it is the grand-daddy of LLMs, the first time the modern stack was put together.

github

: 23.4k

openorch

OpenOrch is a daemon that transforms servers into a powerful development environment, running AI models, containers, and microservices. It serves as a blend of Kubernetes and a language-agnostic backend framework for building applications on fixed-resource setups. Users can deploy AI models and build microservices, managing applications while retaining control over infrastructure and data.

github

: 157

burn

Burn is a new comprehensive dynamic Deep Learning Framework built using Rust with extreme flexibility, compute efficiency and portability as its primary goals.

github

: 9.4k

llama3-tokenizer-js

JavaScript tokenizer for LLaMA 3 designed for client-side use in the browser and Node, with TypeScript support. It accurately calculates token count, has 0 dependencies, optimized running time, and somewhat optimized bundle size. Compatible with most LLaMA 3 models. Can encode and decode text, but training is not supported. Pollutes global namespace with `llama3Tokenizer` in the browser. Mostly compatible with LLaMA 3 models released by Facebook in April 2024. Can be adapted for incompatible models by passing custom vocab and merge data. Handles special tokens and fine tunes. Developed by belladore.ai with contributions from xenova, blaze2004, imoneoi, and ConProgramming.

github

: 69

pydantic-ai

PydanticAI is a Python agent framework designed to make it less painful to build production grade applications with Generative AI. It is built by the Pydantic Team and supports various AI models like OpenAI, Anthropic, Gemini, Ollama, Groq, and Mistral. PydanticAI seamlessly integrates with Pydantic Logfire for real-time debugging, performance monitoring, and behavior tracking of LLM-powered applications. It is type-safe, Python-centric, and offers structured responses, dependency injection system, and streamed responses. PydanticAI is in early beta, offering a Python-centric design to apply standard Python best practices in AI-driven projects.

github

: 5.2k

PromptAgent

PromptAgent is a repository for a novel automatic prompt optimization method that crafts expert-level prompts using language models. It provides a principled framework for prompt optimization by unifying prompt sampling and rewarding using MCTS algorithm. The tool supports different models like openai, palm, and huggingface models. Users can run PromptAgent to optimize prompts for specific tasks by strategically sampling model errors, generating error feedbacks, simulating future rewards, and searching for high-reward paths leading to expert prompts.

github

: 150

kork

Kork is an experimental Langchain chain that helps build natural language APIs powered by LLMs. It allows assembling a natural language API from python functions, generating a prompt for correct program writing, executing programs safely, and controlling the kind of programs LLMs can generate. The language is limited to variable declarations, function invocations, and arithmetic operations, ensuring predictability and safety in production settings.

github

: 91

ai-services

AI Services is a WordPress plugin that provides a centralized infrastructure for integrating AI capabilities into WordPress websites. It allows other plugins to utilize AI services via a common API, making it easier for developers to incorporate AI features without the need to implement separate API layers. The plugin supports various AI services such as Anthropic, Google, and OpenAI, enabling users to choose their preferred service. It simplifies the process of configuring AI APIs and unlocks AI capabilities for smaller plugins or features. The plugin is still in early stages, with ongoing enhancements and improvements planned to streamline API usage and enhance user experience.

github

: 51

alignment-handbook

The Alignment Handbook provides robust training recipes for continuing pretraining and aligning language models with human and AI preferences. It includes techniques such as continued pretraining, supervised fine-tuning, reward modeling, rejection sampling, and direct preference optimization (DPO). The handbook aims to fill the gap in public resources on training these models, collecting data, and measuring metrics for optimal downstream performance.

github

: 4.5k

uncheatable_eval

Uncheatable Eval is a tool designed to assess the language modeling capabilities of LLMs on real-time, newly generated data from the internet. It aims to provide a reliable evaluation method that is immune to data leaks and cannot be gamed. The tool supports the evaluation of Hugging Face AutoModelForCausalLM models and RWKV models by calculating the sum of negative log probabilities on new texts from various sources such as recent papers on arXiv, new projects on GitHub, news articles, and more. Uncheatable Eval ensures that the evaluation data is not included in the training sets of publicly released models, thus offering a fair assessment of the models' performance.

github

: 65

ChainForge

ChainForge is a visual programming environment for battle-testing prompts to LLMs. It is geared towards early-stage, quick-and-dirty exploration of prompts, chat responses, and response quality that goes beyond ad-hoc chatting with individual LLMs. With ChainForge, you can: * Query multiple LLMs at once to test prompt ideas and variations quickly and effectively. * Compare response quality across prompt permutations, across models, and across model settings to choose the best prompt and model for your use case. * Setup evaluation metrics (scoring function) and immediately visualize results across prompts, prompt parameters, models, and model settings. * Hold multiple conversations at once across template parameters and chat models. Template not just prompts, but follow-up chat messages, and inspect and evaluate outputs at each turn of a chat conversation. ChainForge comes with a number of example evaluation flows to give you a sense of what's possible, including 188 example flows generated from benchmarks in OpenAI evals. This is an open beta of Chainforge. We support model providers OpenAI, HuggingFace, Anthropic, Google PaLM2, Azure OpenAI endpoints, and Dalai-hosted models Alpaca and Llama. You can change the exact model and individual model settings. Visualization nodes support numeric and boolean evaluation metrics. ChainForge is built on ReactFlow and Flask.

github

: 2.0k

For similar tasks

AGiXT

AGiXT is a dynamic Artificial Intelligence Automation Platform engineered to orchestrate efficient AI instruction management and task execution across a multitude of providers. Our solution infuses adaptive memory handling with a broad spectrum of commands to enhance AI's understanding and responsiveness, leading to improved task completion. The platform's smart features, like Smart Instruct and Smart Chat, seamlessly integrate web search, planning strategies, and conversation continuity, transforming the interaction between users and AI. By leveraging a powerful plugin system that includes web browsing and command execution, AGiXT stands as a versatile bridge between AI models and users. With an expanding roster of AI providers, code evaluation capabilities, comprehensive chain management, and platform interoperability, AGiXT is consistently evolving to drive a multitude of applications, affirming its place at the forefront of AI technology.

github

: 2.7k

aiexe

aiexe is a cutting-edge command-line interface (CLI) and graphical user interface (GUI) tool that integrates powerful AI capabilities directly into your terminal or desktop. It is designed for developers, tech enthusiasts, and anyone interested in AI-powered automation. aiexe provides an easy-to-use yet robust platform for executing complex tasks with just a few commands. Users can harness the power of various AI models from OpenAI, Anthropic, Ollama, Gemini, and GROQ to boost productivity and enhance decision-making processes.

github

: 58

claude.vim

Claude.vim is a Vim plugin that integrates Claude, an AI pair programmer, into your Vim workflow. It allows you to chat with Claude about what to build or how to debug problems, and Claude offers opinions, proposes modifications, or even writes code. The plugin provides a chat/instruction-centric interface optimized for human collaboration, with killer features like access to chat history and vimdiff interface. It can refactor code, modify or extend selected pieces of code, execute complex tasks by reading documentation, cloning git repositories, and more. Note that it is early alpha software and expected to rapidly evolve.

github

: 247

mistreevous

Mistreevous is a library written in TypeScript for Node and browsers, used to declaratively define, build, and execute behaviour trees for creating complex AI. It allows defining trees with JSON or a minimal DSL, providing in-browser editor and visualizer. The tool offers methods for tree state, stepping, resetting, and getting node details, along with various composite, decorator, leaf nodes, callbacks, guards, and global functions/subtrees. Version history includes updates for node types, callbacks, global functions, and TypeScript conversion.

github

: 63

project_alice

Alice is an agentic workflow framework that integrates task execution and intelligent chat capabilities. It provides a flexible environment for creating, managing, and deploying AI agents for various purposes, leveraging a microservices architecture with MongoDB for data persistence. The framework consists of components like APIs, agents, tasks, and chats that interact to produce outputs through files, messages, task results, and URL references. Users can create, test, and deploy agentic solutions in a human-language framework, making it easy to engage with by both users and agents. The tool offers an open-source option, user management, flexible model deployment, and programmatic access to tasks and chats.

github

: 176

flock

Flock is a workflow-based low-code platform that enables rapid development of chatbots, RAG applications, and coordination of multi-agent teams. It offers a flexible, low-code solution for orchestrating collaborative agents, supporting various node types for specific tasks, such as input processing, text generation, knowledge retrieval, tool execution, intent recognition, answer generation, and more. Flock integrates LangChain and LangGraph to provide offline operation capabilities and supports future nodes like Conditional Branch, File Upload, and Parameter Extraction for creating complex workflows. Inspired by StreetLamb, Lobe-chat, Dify, and fastgpt projects, Flock introduces new features and directions while leveraging open-source models and multi-tenancy support.

github

: 170

RoboMatrix

RoboMatrix is a skill-centric hierarchical framework for scalable robot task planning and execution in an open-world environment. It provides a structured approach to robot task execution using a combination of hardware components, environment configuration, installation procedures, and data collection methods. The framework is developed using the ROS2 framework on Ubuntu and supports robots from DJI's RoboMaster series. Users can follow the provided installation guidance to set up RoboMatrix and utilize it for various tasks such as data collection, task execution, and dataset construction. The framework also includes a supervised fine-tuning dataset and aims to optimize communication and release additional components in the future.

github

: 73

agentscript

github

: 123

For similar jobs

sweep

Sweep is an AI junior developer that turns bugs and feature requests into code changes. It automatically handles developer experience improvements like adding type hints and improving test coverage.

github

: 7.1k

teams-ai

The Teams AI Library is a software development kit (SDK) that helps developers create bots that can interact with Teams and Microsoft 365 applications. It is built on top of the Bot Framework SDK and simplifies the process of developing bots that interact with Teams' artificial intelligence capabilities. The SDK is available for JavaScript/TypeScript, .NET, and Python.

github

: 390

ai-guide

This guide is dedicated to Large Language Models (LLMs) that you can run on your home computer. It assumes your PC is a lower-end, non-gaming setup.

github

: 159

classifai

Supercharge WordPress Content Workflows and Engagement with Artificial Intelligence. Tap into leading cloud-based services like OpenAI, Microsoft Azure AI, Google Gemini and IBM Watson to augment your WordPress-powered websites. Publish content faster while improving SEO performance and increasing audience engagement. ClassifAI integrates Artificial Intelligence and Machine Learning technologies to lighten your workload and eliminate tedious tasks, giving you more time to create original content that matters.

github

: 593

chatbot-ui

Chatbot UI is an open-source AI chat app that allows users to create and deploy their own AI chatbots. It is easy to use and can be customized to fit any need. Chatbot UI is perfect for businesses, developers, and anyone who wants to create a chatbot.

github

: 27.7k

BricksLLM

BricksLLM is a cloud native AI gateway written in Go. Currently, it provides native support for OpenAI, Anthropic, Azure OpenAI and vLLM. BricksLLM aims to provide enterprise level infrastructure that can power any LLM production use cases. Here are some use cases for BricksLLM: * Set LLM usage limits for users on different pricing tiers * Track LLM usage on a per user and per organization basis * Block or redact requests containing PIIs * Improve LLM reliability with failovers, retries and caching * Distribute API keys with rate limits and cost limits for internal development/production use cases * Distribute API keys with rate limits and cost limits for students

github

: 953

uAgents

uAgents is a Python library developed by Fetch.ai that allows for the creation of autonomous AI agents. These agents can perform various tasks on a schedule or take action on various events. uAgents are easy to create and manage, and they are connected to a fast-growing network of other uAgents. They are also secure, with cryptographically secured messages and wallets.

github

: 1.2k

griptape

Griptape is a modular Python framework for building AI-powered applications that securely connect to your enterprise data and APIs. It offers developers the ability to maintain control and flexibility at every step. Griptape's core components include Structures (Agents, Pipelines, and Workflows), Tasks, Tools, Memory (Conversation Memory, Task Memory, and Meta Memory), Drivers (Prompt and Embedding Drivers, Vector Store Drivers, Image Generation Drivers, Image Query Drivers, SQL Drivers, Web Scraper Drivers, and Conversation Memory Drivers), Engines (Query Engines, Extraction Engines, Summary Engines, Image Generation Engines, and Image Query Engines), and additional components (Rulesets, Loaders, Artifacts, Chunkers, and Tokenizers). Griptape enables developers to create AI-powered applications with ease and efficiency.

github

: 2.1k