Search

More Filters

Show More
Add Listing
Go Back

js-agent

0
Multi-Agent Platforms & Frameworks
Report

Report Abuse

Basic Information

JS Agent is a composable and extensible framework for creating AI agents and apps using JavaScript and TypeScript. It was built to help developers move beyond quick prototypes by providing reusable building blocks, tooling and patterns that make agent behavior more reliable and robust. The repository contains an agent runtime, example agents, prompt templates, text utilities and an HTTP server to host and control agents. It targets developers who need typed, modular primitives for defining agents, actions and run properties and who want to experiment with planner and loop patterns such as generate-next-step and BabyAGI-style loops. The README notes the project is an early experiment and not actively developed, pointing to a successor project, but the code and documentation remain useful for learning and constructing production-oriented agent workflows.

Links

Stars
266
Language
App URL
https://github.com/lgrammel/js-agent
Github Repository
https://github.com/lgrammel/js-agent/blob/main/README.md

Categorization

App Details

Features
The project exposes agent definition and execution with configurable run properties and observers. It records all LLM calls, calculates LLM cost, supports stopping criteria and can use multiple models in a single agent. An Agent HTTP Server allows starting, stopping and observing runs and hosting multiple agents. Supported models include OpenAI text and chat completions and embeddings. Built-in actions and tools include read/write file, run CLI commands, programmable search, webpage extraction, ask-user prompts, sub-agent calls and optional executor sandboxing (for example Docker). It supplies loop patterns (BabyAGI-style, generate-next-step), prompt templates, text extraction and splitting utilities (character and token splitters), data converters (HTML and PDF to text) and retry/backoff for LLM calls.
Use Cases
JS Agent helps developers build, test and operate AI agents faster by providing a structured, typed framework and ready-made utilities. It reduces boilerplate for common tasks such as prompting, chunking and embedding text, executing tools and managing multi-step agent loops. Observability features record LLM calls and compute costs, which aids debugging and production monitoring. The HTTP server and optional executor separation let teams integrate agents into services or sandbox execution environments like Docker. Comprehensive examples and tutorials demonstrate use cases such as a Wikipedia QA agent, an automated JavaScript/TypeScript developer agent, BabyAGI and PDF-to-thread workflows, enabling developers to adapt patterns to their own projects.

Categories

Content Creation (5042)
Monetization & Business (2246)
Development Tools (1407)
Marketing & Social Media (1403)
Education & Career (1380)
Multi-Agent Platforms & Frameworks (1230)
Health & Life (957)
AI Resources (920)
Agents & Automation (778)
Data & Analytics (766)
Productivity Tools (679)
Writing & Editing (666)

Similar Listings

listing image

yutu

0 (0 review)
listing image

cyber-doctor

0 (0 review)
listing image

LLM-Powered-RAG-System

0 (0 review)
listing image

vibevideo-mcp

0 (0 review)
listing image

xpert

0 (0 review)

Featured Listings

Tags

Please fill the required fields*