contributors

Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

State-of-the-art diffusion in PyTorch and JAX.

OpenMMLab Detection Toolbox and Benchmark

CLI harness for AnyGen OpenAPI - Generate docs, slides, websites and more via AnyGen cloud API. Requires: ANYGEN_API_KEY

Lean enterprise content management powered by Django.

Opinionated lightweight ETL pipeline framework

Django email backends and webhooks for Amazon SES, Brevo, MailerSend, Mailgun, Mailjet, Mailtrap, Mandrill, Postal, Postmark, Resend, Scaleway TEM, SendGrid, SparkPost, and Unisender Go (EmailBackend, transactional email tracking and inbound email signals)

MLX-powered LLM fine-tuning for Apple Silicon - Unsloth-compatible API for Mac

The Context Optimization Layer for LLM Applications - Cut costs by 50-90%

Backend.AI Storage Proxy

Transition's persistence for django-fsm

Transform Claude Code transcript JSONL files to terminal and HTML views

The next-generation Python library engineered for modern archive management, leveraging cutting-edge Zstandard compression to deliver superior performance, security, and reliability

A Python tool that uses Google's Gemini API to generate animated GIFs from text prompts

Django AI Core provides developer-focused AI features for implementing AI tooling in to Django sites.

Enhanced ManifestStaticFilesStorage for Django

Langchain provider for Spyder

Python bindings for Quillmark - template-first Markdown rendering

从 YAML 配置生成标准化的 AI 协作规则文档 (llm.txt)

Abstraction layer for cloud blobstores.

OneDL Model Pretraining Toolbox and Benchmark

Toolkit for managing huggingface models and datasets

Intelligent routing and management for multiple LangChain ChatModel instances with rate limiting, fallback, and structured output support

AI-native code indexing tool for large codebases

AI-powered knowledge management with YAKE keyword extraction for Claude Code development

Claude environment manager - switch between Claude Code configurations

A flexible library for testing LLM responses against predefined rubrics using OpenAI's API for automated scoring

macOS-style three-finger drag gestures for Linux trackpads

Lightweight cross-platform tool to scan for local AI model files

API governance and breaking change detection for OpenAPI specs

Safely converge Alembic migration graphs by generating minimal merge migrations

DAZZLE - Domain-Aware, Token-Efficient DSL for LLM-Enabled Apps

LangChain extension for accessing Drasi continuous queries via MCP

Better OpenID Connect authentication support for Django

LLM CLI plugin for fal.ai generative AI models and services

Privacy-first text redaction using local LLM models with rule generation capabilities

OpenSearch AI Observability SDK — OTEL-native tracing and scoring for LLM applications

Reliable, structured, production-safe LLM outputs with schema validation and auto-repair

Generate browsable HTML logs from OpenCode local storage

Python wrapper for Audio Workbench Player (HTML/Streamlit embedding)

Catch AI-generated code mistakes before they cause problems

Developer-first AI regression & failure detection for production LLM applications

Universal optimization system for AI coding assistants

A comprehensive Django notification extension with email (via Anymail) and SMS (via Twilio) support

Production-grade API performance analysis platform for Django and FastAPI

OpenID Connect authentication support for Django

Capsule sandbox integration for LangChain — run code in isolated WebAssembly sandboxes

Production-quality CLI for training, evaluating, and predicting with CatBoost models from tabular data

Advanced rate limiting and queue management for Celery workers using Redis-based token bucket algorithms

A powerful CLI for Claude AI using AWS Bedrock - no Anthropic subscription needed

Export Claude Code conversations to self-contained HTML with interactive selection.

A lightweight Python SDK for Claude Code CLI using subprocess

Session management for Claude CLI - preserve context across projects

An introspective interface for Django's ORM.

Django database backend powered by Apache Iceberg and Polars - bringing time travel, cloud-native storage, and blazing-fast analytics to Django

Site-wide Two-Factor Authentication enforcement middleware for Django applications using django-allauth

LangChain VectorStore integration for Envector

A Python tool that uses Google's Gemini API to generate animated GIFs from text prompts

LangChain-integrated compliance audit handler for GenAI (EU AI Act etc.). Captures prompts, outputs, and model usage with provenance hashing.

LangChain document loaders for HWP/HWPX using hwp-hwpx-parser

A code snippet manager, originally written to power djangosnippets.org

Auto-redirect LLM API requests (OpenAI, Anthropic, Gemini, Mistral, Cohere, OpenRouter) to xAI APIs - Just Grok It!

Reusable Flask server for LLM backends (Ollama, LM Studio) with tool calling

Composable building blocks for LLM context engineering

Lightweight LLM tracing SDK with remote tool invocation

DigitalOcean AI embeddings integration for LlamaIndex.

A Django app for managing ads and internal promotions.

Build and maintain Obsidian knowledge bases with LLM assistance

GPU and TPU compatibility toolkit for AI frameworks

data-service-sdk python sdk

Safety-Aware LLM Routing Framework — Bias Detection + Mental Health Risk Detection + Human Escalation. Classifies locally at zero API cost, routes to the best specialized model, and escalates to crisis services when needed.

Local-only RAG benchmarking CLI — measures recall, MRR, chunk overlap, latency, and BEIR IR metrics

HydRAG — Multi-Headed Retrieval-Augmented Generation with CRAG supervision

A tool for finding cryptocurrency wallet seeds using parallel processing

Professional Web Automation and Testing Framework with 60+ MCP Tools, Cloud Platform Support, and Performance Optimization

Cross-tool usage analytics for Claude Code and Codex CLI

Automatically respond 'yes' to interactive CLI prompts via PTY proxy

CLI coding assistant with local LLM support via Ollama

Extract per-field confidence scores from LLM structured JSON outputs using token-level log-probabilities.

Compare LLM architectures without downloading weights — structural fingerprint & proxy-test advisor

Adaptive rate-limit-aware LLM routing. Bring your own clients.

AI-powered code intelligence tool for analyzing and documenting codebases

pymemcache-based Django cache backend for Amazon ElastiCache with auto discovery

Power Grid Model Input/Output

支持多 LLM 提供方的项目 Wiki 自动生成工具（Claude / OpenAI / Ollama）

Know exactly what your AI project will cost. Local-first LLM cost forecasting that learns from your usage.

A beginner-friendly Python SDK that wraps OpenAI APIs behind simple AI actions.

A high-performance array storage and manipulation library

llama-index readers opendal_reader integration

Model-agnostic LLM evaluation that feels like pytest.

Production-grade workflow orchestration system with LLM cost tracking, performance analytics, and dependency management.

SpeechJailbreaker: Framework for testing SpeechLLM robustness against jailbreak attacks

Universal AI CLI Proxy, Firewall, and Token Intelligence Gateway

Cartograph hallucination risk across an LLM's knowledge space

Compare LLM model outputs side-by-side with rich diff visualization

Self-learning prompt injection detection engine for LLM applications

Deterministic LLM workflows you can replay — explicit states, strict schemas, local logs.

No description available