# Python

Open-source feature store for machine learning

Feast is an open-source feature store that manages and serves ML features for both training and online inference. It prevents training-serving skew by providing consistent feature access across offline and real-time environments. Feast supports batch materialization from data warehouses, real-time feature retrieval, on-demand transformations, and integrates with major data platforms including BigQuery, Snowflake, Redshift, and DynamoDB.

Generate SDKs and API documentation from OpenAPI specs

Fern is a platform that generates idiomatic client SDKs and beautiful API documentation from OpenAPI specifications. It produces type-safe SDKs for TypeScript, Python, Java, Go, Ruby, and C# with features like pagination, retries, and streaming built in. The documentation includes API reference, guides, and an AI-powered search assistant. Used by companies like Cohere, ElevenLabs, and Merge.

Multilingual emotional text-to-speech with 80+ language support

Fish Speech is an open-source text-to-speech system supporting 80+ languages with emotional expression, zero-shot voice cloning, and real-time streaming. It generates natural speech with controllable emotions, speaking styles, and prosody. Features a web interface, API server, and integration with AI agent frameworks for voice-enabled applications. Over 29,000 GitHub stars.

Open-source feature flags and remote configuration

Flagsmith is an open-source feature flag and remote config platform with 15+ SDKs, a clean REST API, and simple Docker deployment. It supports boolean, multivariate, and string flags with segment-based targeting, A/B testing via flag variations, and environment-based workflows. Flagsmith provides a straightforward self-hosted alternative to LaunchDarkly with full API-first design under a BSD-3-Clause license.

Fast memory-efficient GPU attention kernels

FlashAttention is a fast and memory-efficient exact attention implementation that reduces GPU memory usage from quadratic to linear in sequence length. Created by Tri Dao, it achieves 3-4x speedups over baseline implementations through IO-aware tiling that minimizes HBM reads and writes. Versions include FlashAttention-2 with improved parallelism, FlashAttention-3 optimized for Hopper H100 GPUs, and FlashAttention-4 targeting Hopper and Blackwell architectures.

Open-source voice cloning and text-to-speech with few-shot learning

GPT-SoVITS is an open-source voice cloning and text-to-speech system that generates natural-sounding speech from just a few seconds of reference audio. It combines GPT-style language modeling with SoVITS voice synthesis for zero-shot and few-shot voice cloning across multiple languages. Supports Chinese, English, Japanese, Korean, and Cantonese with over 56,000 GitHub stars.

Bayesian git bisection for finding commits that caused flaky tests

Git Bayesect applies Bayesian inference to git bisection, solving the problem of finding commits that introduced non-deterministic bugs like flaky tests. Unlike standard git bisect which requires binary pass-fail results, Git Bayesect handles probabilistic outcomes where a test might pass sometimes and fail sometimes, using entropy minimization to efficiently narrow down the culprit commit.

Agent Development Kit by Google

Google's open-source framework for building AI agents with Gemini models. Supports multi-agent orchestration, tool use, and deployment to Vertex AI or Cloud Run. Provides a structured approach to agent development with built-in evaluation, testing, and monitoring capabilities, making it the official path for teams building agent systems within the Google Cloud ecosystem.

MCP server for secure database tooling with AI agents

Google GenAI Toolbox is an open-source MCP server from Google that specializes in easy, fast, and secure database tools for AI agents. It provides structured database access through the Model Context Protocol, enabling agents to query, inspect schemas, and manage data across supported databases with built-in security controls.

Build real-time temporal knowledge graphs for AI agents

Graphiti is an open-source Python framework by Zep for building temporally-aware knowledge graphs for AI agents. It continuously integrates conversations, business data, and external information into queryable graphs with bi-temporal tracking. The hybrid retrieval combines semantic search, BM25 keywords, and graph traversal for sub-300ms queries without LLM calls at retrieval time.

Data quality validation framework for Python

Great Expectations is an open-source Python framework for validating, documenting, and profiling data quality. Teams define expectations as expressive unit tests for their data using an intuitive API, then validate datasets against those rules in CI/CD pipelines or production workflows. It connects to pandas, Spark, and SQL sources, generates data documentation automatically, and integrates with orchestrators like Airflow and Prefect for continuous data quality monitoring.

Synthetic data generation platform for privacy and ML

Gretel is a synthetic data platform that generates realistic, privacy-preserving datasets for ML training, testing, and data sharing. It supports tabular, text, and time-series data with configurable privacy guarantees including differential privacy. Features include data augmentation for imbalanced datasets, PII detection and anonymization, and API/SDK access for pipeline integration with BigQuery, Snowflake, and Databricks.

Modular AI agent framework with off-prompt data

Griptape is an open-source Python framework for building AI agents and workflows with a focus on modularity and enterprise-grade off-prompt data handling. It separates predictable pipeline logic from unpredictable LLM interactions, providing structures for sequential and parallel task execution with built-in memory management and tool integration.

Constrained generation that guarantees valid LLM outputs every time

Guidance is Microsoft's structured generation library that enforces output constraints directly within LLM decoding. It supports JSON schemas, regex patterns, grammars, and interleaved generation-and-control flow to guarantee valid outputs from any compatible model. Works with local models via llama.cpp, Transformers, and remote APIs including OpenAI and Anthropic. Eliminates retry loops and post-processing for structured data extraction.

Human-friendly HTTP client

User-friendly CLI HTTP client for testing and debugging APIs with intuitive syntax, colorized output, and JSON highlighting. Simpler than curl with sensible defaults — auto JSON formatting, persistent sessions, and auth helpers. Also available as HTTPie Desktop (GUI) and HTTPie for Web (browser-based). Supports HTTPS, proxies, file uploads, and plugins. 34K+ GitHub stars. The developer-friendly curl alternative for API work.

Instant GraphQL and REST APIs on any database

Hasura auto-generates real-time GraphQL and REST APIs directly from your database schema—PostgreSQL, MySQL, SQL Server, MongoDB, and more. It provides fine-grained row-level and column-level access control, event triggers on database changes, remote schema stitching, and real-time subscriptions out of the box. Available as a managed cloud service or self-hosted, Hasura eliminates weeks of boilerplate API development while maintaining full control over authorization logic.

NLP and RAG pipeline framework by deepset

Haystack is an open-source AI orchestration framework by deepset for building production-ready LLM applications with explicit control over retrieval, routing, memory, and generation pipelines. Its component-based architecture lets developers chain specialized pieces into branching, looping pipelines for semantic search, RAG, QA, and autonomous agents. Integrates with OpenAI, Anthropic, Mistral, Cohere, Hugging Face, Azure, AWS Bedrock, and major vector stores.

ACP skill definitions giving coding agents HuggingFace ML superpowers

Hugging Face Skills is the official collection of ACP skill definitions that give AI coding agents access to HuggingFace ML capabilities. The 13 skills cover LLM fine-tuning with TRL, vision model training, dataset management, model evaluation, and cloud job submission on HF infrastructure. Compatible with Claude Code, Codex, Gemini CLI, and Cursor via a single npx command.

Structured LLM outputs with validation

Instructor is the most popular Python library for extracting structured, validated data from large language models, with over 3 million monthly downloads and ports across Python, TypeScript, Go, Ruby, Elixir, and Rust. It uses Pydantic models to define output schemas and automatically handles validation, retries, and error correction when the LLM output does not match. Instructor patches existing client libraries instead of replacing them, preserving full access to the underlying API.

Interactive computing notebooks for data science

Jupyter is the open-source interactive computing platform providing notebook interfaces for data science, ML, scientific computing, and education. Notebooks combine live code, equations, visualizations, and narrative text. Supports 40+ languages via kernels including Python, R, Julia, and Scala. JupyterLab provides a modern IDE-like interface. JupyterHub enables multi-user deployments. The standard tool for computational research and data exploration worldwide.

Kubernetes-native model inference platform

KServe is an open-source Kubernetes-native platform for deploying and managing ML model inference at scale. It provides standardized inference protocols, autoscaling including scale-to-zero, canary rollouts, A/B testing, and multi-model serving. KServe supports all major ML frameworks including TensorFlow, PyTorch, scikit-learn, XGBoost, and LLM runtimes like vLLM and Triton through pluggable serving runtimes.

Heterogeneous CPU-GPU inference and SFT for large MoE models

Open-source framework for running and fine-tuning large Mixture-of-Experts models with heterogeneous CPU-GPU execution, optimized kernels, limited VRAM and SGLang or LLaMA-Factory integrations.

Open-source AIOps alert management platform

Keep is an open-source AIOps platform that provides a single pane of glass for all alerts from monitoring tools like Datadog, PagerDuty, Grafana, and 50+ integrations. It uses AI to correlate, deduplicate, and enrich alerts, reducing noise and helping on-call teams focus on real incidents. Keep includes workflow automation, bidirectional sync with ticketing systems, and a modern web dashboard.

Open-source AI second brain with deep research and RAG

Khoj is an open-source personal AI app that serves as a self-hostable second brain. It connects to your documents — PDFs, Markdown, Notion, Word — and uses RAG to answer questions grounded in your knowledge base. Supports any local or cloud LLM including Llama, Claude, GPT, and Gemini. Features custom agents, scheduled automations, deep research mode, semantic search, and Obsidian, Emacs, and WhatsApp integrations. Over 33,000 GitHub stars, YC-backed.

AI documentation for legacy codebases

Kodesage is an AI platform designed for navigating and documenting legacy systems, consolidating knowledge from code, issue tickets, and wikis to generate function-level documentation. It creates AST-based code maps that help teams understand complex 20-year-old codebases in plain English, with on-premises and air-gapped deployment options for high-security enterprise environments.

RAG-based document QA with multi-user support and agent reasoning

Kotaemon is an open-source RAG-powered document question-answering interface backed by Cinnamon AI. It supports multi-user workspaces with access controls, advanced retrieval pipelines including hybrid search and knowledge graph extraction, and agentic reasoning for complex multi-step queries. The web UI handles PDFs, Office documents, and images with citations pointing to exact source passages, making it suitable for both individual research and team knowledge management.

Polyglot document intelligence framework with Rust core

Kreuzberg is a polyglot document intelligence framework with a high-performance Rust core that extracts text, metadata, images, and structured data from 91+ file formats. Available for Python, Ruby, Java, Go, PHP, C#, TypeScript, plus CLI, REST API, and MCP server. Features multiple OCR backends (Tesseract, EasyOCR, PaddleOCR), table extraction with structure preservation, and native async support.

Input and output security scanners for LLM applications

LLM Guard is an open-source security toolkit by Protect AI that provides 15 input scanners and 20 output scanners to protect LLM applications from prompt injection, PII leakage, toxic content, secrets exposure, and data exfiltration. Each scanner is modular and independent — pick the ones you need, configure thresholds, and chain them into a pipeline. The library works with any LLM and has been downloaded over 2.5 million times. MIT licensed, Python 3.9+.

Open-source toolkit for quantizing, deploying, and serving LLMs and vision-language models

LMDeploy is an Apache-2.0 toolkit for self-hosting LLM and vision-language model inference with TurboMind and PyTorch engines. It combines continuous batching, blocked KV cache, tensor parallelism, AWQ and KV-cache quantization with OpenAI-compatible APIs, multi-GPU distribution, offline pipelines, and production metrics.

Open-source multi-type data labeling platform

Label Studio is an open-source data labeling tool by HumanSignal supporting images, text, audio, video, and time series. It offers ML-assisted pre-labeling, customizable XML-based annotation interfaces, multi-user review workflows, and REST API access. Used for computer vision, NLP, speech, and LLM fine-tuning including RLHF annotation pipelines.

Visual framework for building multi-agent AI apps

LangFlow is an open-source visual framework for building multi-agent AI apps with drag-and-drop. Built on LangChain, it lets developers compose chains, agents, and RAG pipelines by connecting modular components visually. Features real-time interaction, Python customization, one-click deployment, and export to LangChain code. Supports all major LLM providers, vector stores, and tools. With 146K+ GitHub stars, it bridges visual prototyping and production deployment.

Multi-agent programming framework inspired by the Actor model

Langroid is a lightweight Python framework from CMU and UW-Madison researchers for building LLM applications using a multi-agent programming paradigm inspired by the Actor Framework. Agents are first-class citizens that encapsulate LLM state, vector stores, and tools, then collaborate via message passing through hierarchical task delegation. With 3,900+ GitHub stars, Langroid works with any LLM provider and does not depend on LangChain or other frameworks.

Twelve-lesson curriculum for building AI coding agents from scratch

Learn Claude Code is a comprehensive educational framework with 12 structured lessons teaching AI coding agent construction from first principles. With over 46,000 GitHub stars and 7,000 forks, it provides complete runnable Python implementations progressing from a 50-line bash agent to a 550-line skills agent with modular extensibility and subagent orchestration.

Memory-first coding agent that learns over time

Letta Code is a memory-first CLI coding agent that persists across sessions and improves over time. Unlike stateless tools like Claude Code or Codex, it works with long-lived agents remembering your codebase, preferences, and past interactions. Model-agnostic supporting Claude, GPT, Gemini, and more. Features git-backed context repositories, skill learning from experience, sleep-time reflection, and subagent orchestration. #1 model-agnostic OSS harness on Terminal-Bench.

Build custom AI inference servers in pure Python

Open-source, FastAPI-based serving engine from Lightning AI for building custom inference APIs — models, agents, RAG, and pipelines — with built-in batching, streaming, and multi-GPU autoscaling.

Open-source real-time voice, video, and AI agent infrastructure

LiveKit is an open-source WebRTC infrastructure platform for building real-time voice, video, and data applications. It powers ChatGPT Advanced Voice Mode and serves as the foundation for AI agent voice interactions. LiveKit provides server-side SDKs for Go, Python, Node.js, and Rust alongside client SDKs for every major platform. The Agents framework lets developers build voice-enabled AI assistants with speech-to-text, LLM processing, and text-to-speech pipelines in Python or Node.js.

Multi-LoRA inference server for serving hundreds of fine-tuned models

LoRAX is an inference server that serves hundreds of fine-tuned LoRA models from a single base model deployment. It dynamically loads and unloads LoRA adapters on demand, sharing the base model's GPU memory across all adapters. Built on text-generation-inference with OpenAI-compatible API. Enables multi-tenant model serving without per-model GPU allocation. Over 3,700 GitHub stars.

Community self-hosted MCP server for Jira and Confluence (Python)

MCP Atlassian is a community-built, self-hosted Python MCP server (sooperset/mcp-atlassian) that connects AI coding agents to Jira and Confluence using API tokens or personal access tokens. It runs on your own infrastructure and supports both Cloud and Server/Data Center deployments — a flexible alternative to Atlassian's official remote MCP server when you need on-prem control, custom auth, or self-managed configuration.

Anthropic's open standard for connecting AI models to tools and data

Model Context Protocol (MCP) is Anthropic's open standard that defines how AI models communicate with external tools, resources, and data sources. Provides a universal client-server architecture for connecting LLMs to any API or service through standardized tool definitions, resource access, and prompt templates. Rapidly adopted across the AI industry as the interoperability standard for AI tool integration.

MCP server manager for installing and running Model Context Protocol servers

MCPorter is a management tool for discovering, installing, and running MCP servers. It provides a registry of available servers, handles dependency installation, manages configuration, and starts servers with proper environment setup. Simplifies the process of connecting AI agents to external tools through MCP by abstracting server lifecycle management. Over 5,700 GitHub stars.

AI-first security scanner for LLM, agent, MCP, and RAG codebases

MEDUSA is an AGPL-3.0 AI-first security scanner from Pantheon Security that checks AI and machine-learning applications, LLM agents, MCP workflows, RAG pipelines, repository-poisoning risks, secrets, and agent-specific compromise patterns.

Run LLMs natively on any device with ML compilation

MLC LLM is an open-source engine for deploying large language models natively across diverse platforms using machine learning compilation. It runs models on NVIDIA/AMD GPUs, Apple Silicon, mobile devices, and browsers via WebGPU without cloud dependencies. Features include OpenAI-compatible API, quantization support, and optimized backends for CUDA, Metal, Vulkan, and WebAssembly.

Run and fine-tune Vision Language Models locally on Mac

Open-source Python package for running and fine-tuning Vision Language Models locally on Mac using Apple's MLX framework. Supports multimodal inference with images, audio, and video across Qwen, DeepSeek, Phi, and Gemma architectures. Features OpenAI-compatible API server, Gradio chat UI, and KV cache optimization. 3.8K+ GitHub stars.

Modern data pipeline orchestration with built-in AI

Mage AI is an open-source data pipeline orchestration tool positioned as a modern alternative to Apache Airflow. It provides a visual pipeline editor, native AI integrations for generating pipeline code, real-time streaming support, and built-in data quality checks. Mage handles batch and streaming workloads with a developer-friendly notebook-style interface and deploys to any cloud provider.

Human-in-the-loop web agent you can co-pilot in real time

Magentic-UI is a Microsoft Research web agent with a human-in-the-loop interface for browsing, coding, and file tasks. It plans multi-step actions, asks for approval before executing, and lets users co-pilot by taking over the browser mid-task. Built on AutoGen, it runs a team of specialized agents for web browsing, file handling, and code execution with full action transparency and safety guardrails.

AI-powered file-type detection at Google scale

Open-source AI-powered file-type detection tool from Google that uses a custom deep-learning model under a few megabytes to identify more than 200 binary and textual content types in milliseconds, even on a single CPU. Magika ships as a CLI, Python package, JavaScript/TypeScript library, and an ONNX model, achieves around 99% accuracy on its test set, and is already used at Google scale across Gmail, Drive, and Safe Browsing as well as by VirusTotal and abuse.ch.

Reactive Python notebooks that version with git and deploy as apps

Marimo is a reactive Python notebook environment with 20,000+ GitHub stars and $4M seed funding. Unlike Jupyter, marimo notebooks automatically update dependent cells when values change, version cleanly with git as pure Python files, and deploy directly as interactive web applications without conversion steps.

Convert any file to Markdown for LLM pipelines

MarkItDown is a lightweight Python utility by Microsoft that converts files into clean Markdown optimized for LLM pipelines and text analysis. It supports PDF, Word, Excel, PowerPoint, HTML, images with OCR, audio with transcription, and text formats like CSV, JSON, and XML. The tool preserves document structure including headings, tables, lists, and links while keeping output token-efficient. It offers a CLI, a four-line Python API, Docker support, and a plugin architecture for extensions.