🎉 The Instagram Growth Blueprint: How to Gain 1,000 Real Followers in 30 Days Without Paid Ads

gittech. site

for different kinds of informations and explorations.

Agents are a directed nested graph

Published at
3 days ago
Main Article
https://github.com/helenaeverleyz/pocket

License: MIT Docs

🚀 Pocket

Build enterprise-ready AI systems—fast, modular, and vendor-agnostic.

Why Pocket?

Enterprises need automation. The typescript LLM framework capture what we see as the core abstraction of most LLM frameworks: A Nested Directed Graph that breaks down tasks into multiple (LLM) steps, with branching and recursion for agent-like decision-making.

From there, it's easy to layer on more complex features like Multi-Agents, Agents, Prompt Chaining, RAG, etc.

✨ Features

  • 🔄 Nested Directed Graph - Each "node" is a simple, reusable unit
  • 🔓 No Vendor Lock-In - Integrate any LLM or API without specialized wrappers
  • 🔍 Built for Debuggability - Visualize workflows, add logs, and handle state persistence
Framework Computation Models Communication Models App-Specific Models Vendor-Specific Models Lines Of Codes Package + Dependency Size
LangChain Agent, Chain Message Many Many 405K +166MB
CrewAI Agent, Chain Message, Shared Many Many 18K +173MB
SmolAgent Agent Message Some Some 8K +198MB
LangGraph Agent, Graph Message, Shared Some Some 37K +51MB
AutoGen Agent Message Some Many 7K +26MB
PocketFlow Graph Shared None None 179 +56KB

Get Started

  1. Clone the Repo 

    git clone https://github.com/helenaeverleyz/pocket.git
cd pocket

  2. Check out documentation: https://helenaeverleyz.github.io/pocket/