PyRank
  • Search
  • PyPI
  • GitHub
  • Insights
  • Compare
  • Advisories
  • Ecosystem
  • About

Karpathy Python Packages

Python packages with the GitHub topic karpathy. Sorted by monthly downloads, with stars and forks.
Ar9av
obsidian-wiki

Framework for AI agents to build and maintain a digital brain through Obsidian wiki | Memory System for Agents

5K 4K 359
Pratiyush
llm-notebook

LLM-powered knowledge base from your Claude Code, Codex CLI, Copilot, Cursor & Gemini sessions. Karpathy's LLM Wiki pattern — implemented and shipped.

2K 397 56
kytmanov
synto

More than just Karpathy’s LLM Wiki, 100% local with Ollama. Drop Markdown notes → AI extracts concepts → your Obsidian wiki auto-links and grows. Zero sharing. Your notes stay yours.

1K 261 26
kytmanov
obsidian-llm-wiki

Karpathy’s LLM Wiki, 100% local with Ollama. Drop Markdown notes → AI extracts concepts → your Obsidian wiki auto-links and grows. Zero sharing. Your notes stay yours.

636 834 126
dean0x
autoevolve

Companion tools for Karpathy's autoresearch - smarter evaluation, guided steering, and multi-agent competitions for GPT pretraining

168 6 1
vinothhacks
kairos-agent

kairos picks the right LLM technique for any task by querying a curated wiki of agent patterns - RAG, ReAct, Reflexion, and 17 more. Karpathy LLM Wiki + rule-based selector + 3 working runners. Zero API keys (routes through llm-mcp).

139 0 0
dean0x
autojudge

Companion tools for Karpathy's autoresearch - smarter evaluation, guided steering, and multi-agent competitions for GPT pretraining

125 6 1
dean0x
autosteer

Companion tools for Karpathy's autoresearch - smarter evaluation, guided steering, and multi-agent competitions for GPT pretraining

119 6 1
vbarsoum1
klore

Compile documents into a living Obsidian wiki. Any AI agent. Based on Karpathy's LLM Wiki pattern.

93 26 1
kbtransfer
kbtransfer

Open-protocol federated knowledge base for AI agents. Karpathy-style wiki + signed pack distillation + MCP-native sharing.

87 0 0
johanity
theorist

Prediction-error optimization. The agent guesses before each experiment. Wrong predictions are the learning signal. One file, zero dependencies. pip install theorist

57 1 0
    • Original data from PyPI, GitHub, and OSV; downloads served through ClickHouse
    • Sources & methodology