karpathy

LLM Wiki

A pattern for building personal knowledge bases using LLMs.

This is an idea file, it is designed to be copy pasted to your own LLM Agent (e.g. OpenAI Codex, Claude Code, OpenCode / Pi, or etc.). Its goal is to communicate the high level idea, but your agent will build out the specifics in collaboration with you.

The core idea

Most people's experience with LLMs and documents looks like RAG: you upload a collection of files, the LLM retrieves relevant chunks at query time, and generates an answer. This works, but the LLM is rediscovering knowledge from scratch on every question. There's no accumulation. Ask a subtle question that requires synthesizing five documents, and the LLM has to find and piece together the relevant fragments every time. Nothing is built up. NotebookLM, ChatGPT file uploads, and most RAG systems work this way.

emschwartz

This is an OPML version of the HN Popularity Contest results for 2025, for importing into RSS feed readers.

Plug: if you want to find content related to your interests from thousands of obscure blogs and noisy sources like HN Newest, check out Scour. It's a free, personalized content feed I work on where you define your interests in your own words and it ranks content based on how closely related it is to those topics.

AndrewAltimit

ComfyUI MCP Server (local image/video generation)

Warning: Requires a powerful GPU!

A containerized ComfyUI setup with MCP (Model Context Protocol) integration for AI-driven image generation workflows. Includes both standard MCP (stdio) access and HTTP API access.

Usage

See the template repository for a complete example. Also includes the model training mcp used for creating checkpoints / loras.

AndrewAltimit

MCP Server Manim Integration

A complete implementation guide for integrating Manim (Mathematical Animation Engine) with MCP (Model Context Protocol) servers, enabling AI assistants to create programmatic animations and visualizations.

Example Output

AndrewAltimit

Gemini AI Integration MCP Server

A Model Context Protocol (MCP) server that integrates Google's Gemini AI for code review, technical consultation, and AI-assisted development workflows. This server provides seamless integration with Claude Code and other MCP-compatible clients.

Usage

lemassykoi

import os
import json
import aiohttp
import datetime
from contextlib import asynccontextmanager
from typing import AsyncIterator
from mcp.server.fastmcp import FastMCP, Context
from mcp.server import Server
from swarm import Swarm, Agent
from duckduckgo_search import DDGS

jlia0

You are Manus, an AI agent created by the Manus team.

You excel at the following tasks:
1. Information gathering, fact-checking, and documentation
2. Data processing, analysis, and visualization
3. Writing multi-chapter articles and in-depth research reports
4. Creating websites, applications, and tools
5. Using programming to solve various problems beyond development
6. Various tasks that can be accomplished using computers and the internet

sarath-menon

Code Bash command prefix detection

This defines risk levels for actions that the ${K4} agent may take. This classification system is part of a broader safety framework and is used to determine when additional user confirmation or oversight may be needed.

Command prefix extraction examples

Examples:

• cat foo.txt => cat
• cd src => cd

willccbb

# train_grpo.py
#
# See https://github.com/willccbb/verifiers for ongoing developments
#
"""
citation:

@misc{brown2025grpodemo,
  title={Granular Format Rewards for Eliciting Mathematical Reasoning Capabilities in Small Language Models},
  author={Brown, William},

sayakpaul

from diffusers import FluxPipeline, AutoencoderKL
from diffusers.image_processor import VaeImageProcessor
from transformers import T5EncoderModel, T5TokenizerFast, CLIPTokenizer, CLIPTextModel
import torch
import gc


def flush():
    gc.collect()
    torch.cuda.empty_cache()