Django backend agent skills for Django, DRF, Celery, and Django-specific code review.
AI and Agents in Python
39 projects in AI & ML. Most starred: hermes-agent, transformers and langchain.
Python's AI tooling splits into layers. Orchestration frameworks such as LangChain, LangGraph, Pydantic AI and CrewAI handle prompts, tool calls and multi-step agent loops. LangGraph is the lower-level option when you want explicit state and control flow, while CrewAI models a team of agents with roles. The vendor SDKs from OpenAI, Anthropic (Claude Agent SDK) and Google (ADK) are the shortest path when you are committed to one model provider. To expose your own functions to AI clients, the official MCP SDK and FastMCP implement the Model Context Protocol.
Agent Skills5
Agent skills for scientific research and analysis with Python libraries like scikit-learn, polars, and biopython.
Agent skills the Sentry team uses for code review, pull requests, and Django reviews.
Security skills for vulnerability detection, auditing, and testing.
Plugins, agents, and skills for AI coding tools, including Python skills for testing, async, packaging, and uv.
Orchestration4
A framework for building agents and LLM-powered applications.
Low-level orchestration framework for building stateful, long-running LLM agents.
A Python agent framework for building generative AI applications with structured schemas.
A framework for orchestrating role-playing autonomous AI agents for collaborative task solving.
Vendor Agent SDKs3
Anthropic's Python SDK for building AI agents on Claude Code's harness — custom tools, in-process MCP servers, hooks.
Google's code-first toolkit for building, evaluating, and deploying AI agents.
Model Context Protocol2
Personal Assistants2
A multi-platform AI assistant that connects LLMs to chat apps like Telegram, Slack, and QQ, extensible with Python plugins.
Prompt Optimization1
Data Layer5
A library for extracting structured data from LLMs, powered by Pydantic.
A toolkit for building RAG pipelines and agents over your data.
An intelligent memory layer for AI agents enabling personalized interactions.
A context database for AI agents that unifies memory, resources, and skills.
A graph-native context and knowledge layer for AI agents with reasoning, provenance, and governance.
Pre-trained Models2
The model-definition framework for pretrained models in text, computer vision, audio, video, and multimodal tasks, for inference and training.
Compute embeddings, run retrieval, and rerank results with pretrained and fine-tuned models.
Local LLM Inference3
Python client for Ollama, which downloads and runs open-weight LLMs locally.
Python bindings for llama.cpp, for running GGUF models locally.
LLM Serving3
A high-throughput and memory-efficient inference and serving engine for LLMs.
A high-performance serving framework for large language models and multimodal models.
DeepSeek's production inference engine for DeepSeek models, with MoE expert parallelism.
Image and Video Generation1
Pre-trained diffusion models for generating and editing images, audio, and video.
Fine-tuning4
A library for parameter-efficient fine-tuning of large pretrained models.
A library for post-training transformer language models with SFT, DPO, GRPO, and other trainers.
Faster, lower-memory LLM fine-tuning, as a Python library or a desktop app.
Speech4
A Whisper reimplementation on CTranslate2, up to 4 times faster than openai-whisper with less memory.
A general-purpose automatic speech recognition model trained on 680k hours of multilingual and multitask supervised data.
Python library and CLI tool for converting text to speech using Google Translate TTS.
Industrial-grade speech recognition toolkit with speaker diarization and emotion detection.