Search

More Filters

Show More
Add Listing
Go Back

philoagents course

0
New
Multi-Agent Platforms & Frameworks
Report

Report Abuse

Basic Information

An open-source, hands-on course and codebase that teaches how to build an AI-powered game simulation engine which impersonates historical philosophers. The repository provides lesson material, example code and a two-app project structure consisting of a Python backend (philoagents-api) that contains the agent simulation logic and a Node frontend (philoagents-ui) used to play the game. The course covers architecting and implementing production-ready retrieval-augmented generation (RAG) systems, agent design with LangGraph, LLM integrations, short- and long-term memory with MongoDB, RESTful API and WebSocket deployment, and LLMOps practices. Materials include six modules with written and video lessons, setup and usage instructions, and automated data ingestion from Wikipedia and the Stanford Encyclopedia of Philosophy to populate agent memories.

Links

Stars
1220
App URL
https://github.com/neural-maze/philoagents-course
Github Repository
https://github.com/neural-maze/philoagents-course/blob/main/README.md

Categorization

App Details

Features
Modular six-episode course with code examples and videos. A backend philoagents-api app that implements agent simulation logic in Python and a separate philoagents-ui in Node for playback. Agent development and orchestration built around LangGraph and integrations with LangChain. Production-ready RAG architecture with vector database integration and automated knowledge ingestion from Wikipedia and Stanford Encyclopedia entries. Memory systems implementing short- and long-term memory using MongoDB. Exposed as a RESTful API and real-time WebSocket endpoints via FastAPI. Tooling and deployment guidance including Docker, modern Python tools, uv and ruff. LLMOps features such as automated agent evaluation, prompt monitoring and versioning, and evaluation dataset generation. Examples and INSTALL_AND_USAGE instructions to replicate results.
Use Cases
Teaches practitioners to design, implement and deploy agentic applications from principles to production with runnable code templates. Provides a step-by-step path to build philosopher NPCs that combine RAG, LLMs and memory so learners can reproduce a working simulation engine and ship it as an API. Covers end-to-end system architecture including frontend‚Üíbackend‚Üíagent‚Üímonitoring, real-time interaction via WebSockets, memory management and vector search, and practical LLMOps topics like automated evaluation and prompt versioning. Materials are self-paced and free, with optional low-cost usage of external APIs. Targeted at ML/AI engineers, data and software engineers, and data scientists who learn by building.

Categories

Content Creation (5042)
Monetization & Business (2246)
Development Tools (1407)
Marketing & Social Media (1403)
Education & Career (1380)
Multi-Agent Platforms & Frameworks (1009)
Health & Life (957)
AI Resources (920)
Agents & Automation (778)
Data & Analytics (764)
Productivity Tools (679)
Writing & Editing (666)

Similar Listings

listing image

virtual lab

0 (0 review)
listing image

mnemo

0 (0 review)
listing image

EdgeChains

0 (0 review)
listing image

RAG Agents Accelerator

0 (0 review)
listing image

LLM Zero to Hundred

0 (0 review)

Featured Listings

Tags

Please fill the required fields*