treyorr/pocket-agents
Self-contained agent backend with tools, RAG, and durable runs. One binary, no external services.
PocketAgents helps software developers quickly set up a complete backend for AI applications without complex infrastructure. It takes various documents like PDFs and Word files as input to build knowledge bases, enabling conversational AI agents. The output is a functional AI agent backend that can be integrated into web or desktop applications. This tool is for developers building AI-powered features or products.
Use this if you are a software developer needing a self-contained, production-ready backend for AI agents, including RAG and tool execution, that can be deployed with a single file.
Not ideal if you are a non-technical end-user looking for a no-code solution to build AI applications, as this tool requires programming knowledge.
Stars
11
Forks
1
Language
TypeScript
License
MIT
Category
Last pushed
Mar 08, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/rag/treyorr/pocket-agents"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
deepsense-ai/ragbits
Building blocks for rapid development of GenAI applications
infiniflow/ragflow
RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses...
GiovanniPasq/agentic-rag-for-dummies
A modular Agentic RAG built with LangGraph — learn Retrieval-Augmented Generation Agents in minutes.
truefoundry/cognita
RAG (Retrieval Augmented Generation) Framework for building modular, open source applications...
vectara/py-vectara-agentic
A python library for creating AI assistants with Vectara, using Agentic RAG