idosal/AgentLLM
AgentLLM is a PoC for browser-native autonomous agents
This project provides a way to define complex goals and have an AI agent autonomously break them down into steps and execute them, all within your web browser. You provide a high-level objective, and the agent generates a plan and attempts to complete it, returning the outcome of its efforts. It's designed for individuals exploring the capabilities of AI in automating multi-step tasks without needing powerful external servers.
457 stars. No commits in the last 6 months.
Use this if you want to experiment with autonomous AI agents for various goal-oriented tasks directly in your web browser, leveraging your device's GPU for processing.
Not ideal if you need a production-ready system for critical tasks, or if your device lacks a powerful GPU and modern browser for optimal performance.
Stars
457
Forks
88
Language
JavaScript
License
GPL-3.0
Category
Last pushed
Jul 31, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/idosal/AgentLLM"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
fractalic-ai/fractalic
Fractalic: Build and version-control AI systems using Markdown & YAML. Combine LLM calls, shell...
qntx/x402-openai-python
Drop-in OpenAI Python client with transparent x402 payment support.
Haohao-end/LMForge-End-to-End-LLMOps-Platform-for-Multi-Model-Agents
AI Agent Development Platform - Supports multiple models (OpenAI/DeepSeek/Wenxin/Tongyi),...
PrefectHQ/marvin
an ambient intelligence library
ArcadeAI/arcade-py
Official Arcade Python Client