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

Ai Models Python Packages

Python packages with the GitHub topic ai-models. Sorted by monthly downloads, with stars and forks.
mnfst
modelparams

Open-source AI model parameters database.

6K 16 6
TeamKillerX
akenoai

AkenoAI-Lib is a high-performance library for making raw HTTP requests, powered by aiohttp. It provides a simple yet powerful syntax for handling API requests efficiently, ensuring speed and flexibility.

3K 6 1
alialtunar
model-price-radar-mcp

MCP server: LLM prices on OpenRouter now and since 2023 (price history, drops, cheapest model for a job). No API keys.

2K 0 0
Sigwarth-Software
crypto-trader-analysis

A Spring Boot web app that buys and sells cryptocurrencies from API data sources. Its quick trading and other features allow users to leverage computer power to outperform the market.

928 1 0
audkus
ai-utilities

Contract-first Python utilities for building and testing AI-powered applications across providers

453 1 0
IBM
ai-privacy-toolkit

A toolkit for tools and techniques related to the privacy and compliance of AI models.

359 113 46
timoncool
civitai-mcp-ultimate

Ultimate MCP server for Civitai API — search models, browse top images with prompts, download LoRAs/Checkpoints, analyze trends. Bilingual (EN/RU). Python + FastMCP.

326 22 6
ReneNyffenegger
aimodelsdb

Load AI models from models.dev into an SQLite database

324 0 0
Plale-Lab
patra-toolkit

Toolkit for semi-automated modelcard creation for AI/ML models.

282 4 5
ajentsor
llm-radar-mcp

[RETIRED 2026-05] Daily-updated MCP server for AI model intel from OpenAI, Anthropic, Google. No longer maintained.

278 0 0
blueraai
universal-intelligence

◉ Universal Intelligence: AI made simple.

248 64 8
ecmwf-lab
ai-models-gencast

An ai-models plugin to run Deepmind's gencast model

225 23 4
varejad
behavioralflow

Reinforcement learning library inspired by Behavioral Psychology, focused on simplicity. It uses Python dictionaries instead of complex tables, making implementation intuitive. Agents learn through reinforcement and punishment, considering context and consequences. They can also combine actions to create new behaviors.

131 3 0
    • Original data from PyPI, GitHub, and OSV; downloads served through ClickHouse
    • Sources & methodology