# Python

Microsoft's AI orchestration SDK for .NET, Python, and Java

Microsoft's open-source AI SDK that lets you combine AI models with conventional programming. Supports plugins, planners, memory, and function calling with availability for .NET, Python, and Java. Designed for enterprise developers building AI-powered applications within the Microsoft ecosystem, offering deep integration with Azure AI services and existing business logic.

AI-powered command-line productivity tool

ShellGPT (sgpt) is a command-line productivity tool powered by OpenAI models that generates shell commands, code snippets, and documentation directly in the terminal. Integrates with Bash, Zsh, PowerShell, and CMD; places AI-suggested commands into the terminal input via hotkeys. Supports persistent chat sessions, a REPL mode, and custom Python functions for extending capabilities. Accepts stdin and arguments for pipe-based workflows where command output can be piped to the AI.

Hunt down social media accounts by username across 400+ platforms

Sherlock is a Python CLI tool that searches for a given username across 400+ social networks and websites simultaneously. It is widely used in OSINT investigations, security audits, red teaming exercises, and digital footprint analysis. Sherlock is included in Kali Linux and Parrot Security distributions and has over 76,000 GitHub stars, making it one of the most popular open-source security tools.

YC-backed cloud deployment platform for Rust and Python applications

Shuttle is a YC-backed cloud deployment platform that simplifies deploying Rust and Python backend applications. Developers annotate their code with Shuttle macros to declare infrastructure needs like databases, caches, and secrets, and Shuttle provisions the resources automatically on deployment. Features instant deployment, automatic HTTPS, and infrastructure-from-code. Over 6,100 GitHub stars.

Run AI workloads on any cloud with automatic cost optimization

SkyPilot is an open-source framework for running LLMs, AI, and batch jobs on any cloud with automatic cost optimization. It supports AWS, GCP, Azure, Lambda Cloud, and more, automatically selecting the cheapest available GPUs and managing spot instance preemption. Features include multi-cloud job scheduling, managed spot jobs with automatic recovery, and cluster autoscaling with 6,000+ GitHub stars.

Hugging Face's lightweight agent framework

smolagents is Hugging Face's lightweight agent framework for building AI agents that can use tools, write and execute code, and collaborate in multi-agent setups. Designed for simplicity with minimal abstractions — agents are just LLMs that write Python code to orchestrate tool calls rather than using JSON-based function calling. Supports any LLM provider, integrates with Hugging Face Hub for sharing tools and agents, and runs with as few as 1,000 lines of core library code.

Data-centric AI platform for programmatic data labeling

Snorkel AI is a data-centric AI platform that enables programmatic labeling of training data through labeling functions rather than manual annotation. Spun out of Stanford AI Lab, it lets teams write Python functions that encode domain heuristics to label data at scale, with the platform combining weak labels into high-quality training sets. Used by Fortune 500 companies for text, image, and structured data labeling.

Supply chain security for npm and Python packages

Socket.dev detects and prevents supply chain attacks in open-source dependencies before they compromise your applications. Unlike traditional SCA tools that match known CVEs, Socket analyzes package behavior — detecting install scripts, network access, filesystem operations, and obfuscated code that indicate malicious intent. Monitors npm, Python (PyPI), and Go packages in real-time. Provides GitHub PR comments with risk assessments for new dependencies added to your projects.

Auto-generate SDKs and docs from backend routes

Speakeasy uses AI to parse backend API routes and auto-generate production-ready SDKs in multiple languages alongside OpenAPI documentation. It ensures that client libraries and documentation always match the current backend implementation, eliminating the drift between API code, SDK behavior, and documentation that plagues most API-first teams as their services evolve.

Generate production-ready SDKs from API specifications

Stainless generates idiomatic, production-ready client SDKs from OpenAPI specifications with features like automatic pagination, retries, streaming, and proper error handling baked in. Used by Anthropic, OpenAI, Cloudflare, and Lithic to maintain their official SDKs. Produces TypeScript, Python, Go, Java, and Kotlin SDKs that match hand-written quality with automated maintenance and versioning.

AWS open-source SDK for building model-driven AI agents

Strands Agents is an open-source SDK from AWS that takes a model-driven approach to building AI agents. Developers define a prompt, model, and tools, and the LLM handles planning and orchestration autonomously. Supports Amazon Bedrock, Anthropic, OpenAI, Gemini, Ollama, and more. Powers Amazon Q Developer and AWS Glue in production. Available in Python and TypeScript with native MCP support.

Open-source Firecracker sandboxes for long-running AI agents

Superserve is an open-source sandbox infrastructure layer for AI agents that need durable computers instead of short-lived shells. It runs isolated Firecracker microVMs, supports pause, resume, snapshot, fork, preview URLs, MCP connectivity, SDK/API control, Docker workloads, and self-hosting, while the hosted service adds pay-as-you-go agent sandboxes for teams.

Reusable computer vision tools for developers

Supervision is an open-source Python toolkit by Roboflow providing reusable CV utilities for detection, tracking, annotation, and dataset management. It works with any model including YOLO and Hugging Face via a standardized Detections class. Features include 20+ annotators, ByteTrack object tracking, zone counting, speed estimation, and dataset conversion between COCO, YOLO, and Pascal VOC formats.

Multi-agent orchestration with 10+ swarm patterns

Swarms is an enterprise-grade multi-agent orchestration framework with 6,100+ GitHub stars that provides 10+ swarm patterns including sequential, concurrent, hierarchical, mixture-of-agents, and graph-based workflows. The SwarmRouter lets teams switch between orchestration strategies by changing a single parameter. It supports MCP for tool integration, multi-model providers via Anthropic, OpenAI, and local models, and includes an AutoSwarmBuilder that generates agents from task descriptions.

Code-first agent framework for data analytics tasks

TaskWeaver is Microsoft's open-source code-first agent framework that converts natural language requests into executable Python code for data analytics and workflow automation. Unlike text-based agent frameworks, it preserves rich in-memory data structures like DataFrames across conversation turns, supports custom algorithm plugins as callable functions, and verifies generated code before execution. It includes a Planner for task decomposition and a Code Interpreter for generation and execution.

AI framework for distributed vulnerability research

Taskflow Agent is an open-source MIT-licensed AI framework by GitHub Security Lab that automates vulnerability discovery through a three-stage pipeline: threat modeling, issue suggestion, and audit validation. It has discovered 91 confirmed vulnerabilities in major open-source projects including Outline and WooCommerce, using distributed community-powered security research coordinated by AI agents.

Build smaller, faster desktop apps with Rust and web tech

Tauri is a Rust-based framework for building desktop applications using web technologies like HTML, CSS, and JavaScript—without bundling Chromium. By leveraging the system's native WebView, Tauri apps ship as tiny installers under 10MB and use 30-50MB RAM at idle, a fraction of Electron's footprint. It supports Windows, macOS, and Linux with any frontend framework (React, Vue, Svelte, etc.) and provides a secure Rust backend for system-level operations with fine-grained permission controls.

Self-hosted AI accounting for freelancers and small teams

TaxHacker is an open-source, self-hosted AI accounting app that automatically extracts financial data from receipts, invoices, and bank statements using LLMs. It supports 170+ currencies and 14 cryptocurrencies with historical exchange rate conversion, multi-project accounting, and custom AI extraction fields. Works with OpenAI, Gemini, Mistral, or local models via Ollama—deploy with Docker and keep all financial data under your control.

Enterprise feature platform for real-time ML

Tecton is an enterprise feature platform for building and serving ML features at scale. Created by the team behind Feast, it provides managed feature engineering, real-time feature computation from streaming data, feature monitoring, and a unified feature store with offline/online consistency. Used by production ML teams to eliminate training-serving skew and accelerate model deployment cycles.

Durable execution for fault-tolerant workflows

Temporal is an open-source durable execution platform that ensures application code runs to completion regardless of failures or outages. It captures workflow state at every step, enabling seamless recovery without custom retry logic. With SDKs for Go, Java, Python, TypeScript, and .NET, Temporal powers mission-critical orchestration at Netflix, Nvidia, and other enterprises. Valued at $5B, it replaces fragile cron jobs, state machines, and saga patterns with resilient workflow-as-code.

NVIDIA's LLM inference optimization and acceleration library

TensorRT-LLM is NVIDIA's open-source library for optimizing LLM inference on NVIDIA GPUs. It provides kernel fusion, quantization (FP8, INT4, INT8), KV cache optimization, and in-flight batching to maximize throughput. Supports multi-GPU and multi-node setups with tensor and pipeline parallelism, and integrates with Triton Inference Server for production deployment of models like LLaMA, GPT, Mistral, and Qwen.

Hugging Face's production LLM serving framework

Text Generation Inference (TGI) is Hugging Face's production-ready serving framework for large language models. It features flash attention, continuous batching, tensor parallelism, quantization via GPTQ/AWQ/EETQ, and Safetensors support. Powers Hugging Face's Inference API and Inference Endpoints, with an OpenAI-compatible API and Docker deployment. Supports LLaMA, Mistral, Falcon, and other popular model architectures.

AI-powered Stripe-style API documentation

Theneo is a Y Combinator-backed tool that generates high-quality, Stripe-style API documentation in seconds using AI. It transforms OpenAPI specs, Postman collections, or raw code into interactive developer portals with code playgrounds, multi-language SDK examples, and beautiful visual design, helping API-first teams create professional documentation without spending weeks on manual writing.

Google's pretrained foundation model for zero-shot time-series forecasting

TimesFM is a pretrained time-series foundation model from Google Research that performs zero-shot forecasting on diverse datasets without task-specific training. It handles univariate and multivariate time series across domains including finance, logistics, energy, and infrastructure monitoring with accuracy competitive against traditional statistical methods like ARIMA and Prophet.

Tool infrastructure for AI agents

Cloud platform providing optimized tools for AI agents with a universal SDK for Python and TypeScript. Works with any LLM provider and enables one-line tool integration. Handles authentication, rate limiting, and caching for external APIs so agent developers can focus on logic rather than plumbing, dramatically reducing the boilerplate needed for production agents.

Open-source observability and self-healing layer for AI agents

TraceRoot is a YC S25-backed open-source observability platform purpose-built for AI agents and LLM apps. It combines OpenTelemetry-compatible tracing with an agentic debugging runtime that reads your source code, correlates failures with recent commits, and proposes fix PRs automatically. BYOK support spans seven LLM providers; the entire stack runs self-hosted via Docker Compose, with TraceRoot Cloud available for managed deployments.

Incremental parsing system powering code intelligence in AI editors

Tree-sitter is an incremental parsing library with 19,000+ GitHub stars used by Cursor, Neovim, GitHub, and Helix for real-time syntax analysis. It generates concrete syntax trees that update incrementally as code changes, enabling AI code editors to understand program structure for intelligent completions, refactoring, and code navigation.

Context-aware AI review with business logic validation

Umaku is a context-aware AI code review agent that understands full codebase and business logic context, detecting inconsistencies and assessing quality and risk beyond syntax-level analysis. It auto-generates and validates QA test cases from reviewed code, making it particularly effective for reviewing AI-generated code where product-intent validation matters more than style checking.

ETL for LLMs — preprocess any document format

Unstructured is an open-source ETL library that preprocesses and transforms documents from diverse formats into clean, structured data ready for LLM ingestion and RAG pipelines. It handles PDF, HTML, Word, PowerPoint, and many other file types through partitioning, cleaning, and chunking operations. The library offers connector-based architecture for integrating with various data sources and destinations, making it a key component in document processing workflows for AI applications.

Agent framework with native MCP server support

Upsonic is an agent framework designed for building reliable AI agents with native Model Context Protocol (MCP) server support. It provides structured task execution, tool calling orchestration, and built-in reliability patterns for production agent deployments. Features include automatic error recovery, structured output validation, and seamless integration with MCP-compatible tools and data sources for enterprise agentic workflows.

OpenAI's open-source speech recognition model for any language

Whisper is OpenAI's open-source automatic speech recognition model trained on 680,000 hours of multilingual audio data. It supports transcription and translation across 99 languages with robust handling of accents, background noise, and technical vocabulary. Available in multiple model sizes from tiny (39M) to large (1.5B parameters) for balancing accuracy and speed.

Local model inference engine with OpenAI-compatible API and web UI

Xinference is a local inference engine that runs LLMs, embedding models, image generation, and audio models with an OpenAI-compatible API. It provides a web dashboard for model management, supports vLLM, llama.cpp, and transformers backends, and handles multi-GPU deployment automatically. Supports 100+ models including Qwen, Llama, Mistral, and DeepSeek with over 9,200 GitHub stars.

Multi-agent AI coding platform with orchestrated specialist agents

Zencoder is an AI coding platform that uses multi-agent orchestration to handle complex development tasks. Specialist agents collaborate on different aspects of implementation including code generation, testing, documentation, and review. Integrates with VS Code and JetBrains IDEs. Features repository-aware context that understands project architecture and coding standards.

AI chatbot framework for WeChat with multi-model and plugin support

chatgpt-on-wechat is an open-source framework for deploying AI chatbots on WeChat, the dominant messaging platform in China. It supports OpenAI, Claude, Gemini, Qwen, and local models through a plugin architecture. Features group chat management, image generation, voice messages, and knowledge base integration. Over 42,700 GitHub stars reflecting massive adoption in the Chinese developer community.

SQL-based data transformation framework

dbt (data build tool) is an open-source SQL transformation framework with 10K+ GitHub stars that lets analytics engineers transform data in their warehouse using select statements. Brings software engineering practices to data — version control, testing, documentation, and CI/CD for SQL. Supports Snowflake, BigQuery, Redshift, Databricks, PostgreSQL, and more. Features Jinja templating, incremental models, snapshots, and a package hub of reusable transformations.

Python library for declarative data loading that LLMs can generate

dlt (data load tool) is a Python library for building data pipelines with declarative, schema-aware loading that is simple enough for LLMs to generate correctly. It extracts data from APIs, databases, and files, normalizes nested structures, handles schema evolution, and loads into warehouses and lakes. Supports 30+ destinations including BigQuery, Snowflake, DuckDB, and PostgreSQL. Over 5,200 GitHub stars.

One-command local coding agent that auto-detects your hardware and picks the best model

hf-agents is a Hugging Face CLI extension that detects your hardware, recommends the best GGUF model using llmfit, and launches a local coding agent in a single command. It collapses the multi-step local LLM setup into hf agents run pi, automatically handling hardware profiling, model download, inference server startup, and coding agent activation.

Open-source diagnostic for AI operational misalignment

iFixAi is an Apache-2.0 diagnostic tool for scoring AI agents and models against operational-misalignment risks such as hallucination, manipulation, sabotage, sandbagging, and oversight evasion.

The fast, feature-rich terminal

GPU-accelerated terminal emulator written in C and Python, focused on performance and features. Supports ligatures, true color, graphics protocol for displaying images/plots inline, tabs, splits, and remote control via IPC. Highly configurable via a plain text config file. Cross-platform on macOS and Linux. Features a kitten framework for writing terminal programs in Python. Known for innovation in terminal graphics. 26K+ GitHub stars and a dedicated power-user community.

Composable agent orchestration via MCP servers

mcp-agent is an open-source framework with 8K+ GitHub stars for building AI agents that leverage MCP (Model Context Protocol) servers as composable tool providers. Agents connect to multiple MCP servers simultaneously, gaining access to diverse capabilities without custom integrations. Supports multi-agent workflows, parallel tool execution, and automatic server discovery. Designed to make MCP the universal interface between AI agents and external tools, databases, and services.

Fullstack MCP framework connecting any LLM to MCP servers

mcp-use is an open-source framework that enables any LLM to interact with MCP servers through a unified client interface. It bridges the gap between models that lack native MCP support and the growing ecosystem of MCP tools by providing automatic tool discovery, execution management, and multi-server orchestration. Supports both direct LLM connections and agent-based workflows. Over 9,000 GitHub stars.

The 100-line SWE agent that solves GitHub issues from your terminal

Radically minimal open-source SWE agent (~100 lines of Python) that uses nothing but bash to fix GitHub issues and assist in the command line, while scoring >74% on SWE-bench Verified.

ModelScope's fine-tuning framework supporting 600+ models

ms-swift is ModelScope's open-source framework for fine-tuning over 600 large language and multimodal models. It supports SFT, DPO, RLHF, LoRA, QLoRA, and full fine-tuning with a web UI and CLI interface. Optimized for the Chinese AI ecosystem with native ModelScope Hub integration alongside Hugging Face support. Over 13,500 GitHub stars.

PostgreSQL administration tool

The most popular open-source administration and management tool for PostgreSQL, used by millions of DBAs and developers worldwide. Features a powerful SQL query editor with auto-completion, visual query builder (graphical EXPLAIN), server dashboard with real-time monitoring, backup/restore wizards, ERD generator for schema visualization, and user/role management. Runs as a web application accessible via browser. Supports PostgreSQL 12+ and is available on Windows, macOS, Linux, and Docker.

AI-powered test generation agent for automated code coverage improvement

qodo-cover (formerly Cover Agent) is an open-source AI agent that automatically generates meaningful unit tests to improve code coverage. It analyzes existing code and test patterns to produce tests that follow project conventions and target uncovered branches. Uses an iterative approach where generated tests are verified by running them, discarding those that fail. MIT licensed with over 5,300 GitHub stars.

Meta's official PyTorch library for LLM fine-tuning

torchtune is Meta's official PyTorch-native library for fine-tuning large language models. It provides composable building blocks for training recipes covering LoRA, QLoRA, full fine-tuning, DPO, and knowledge distillation. Supports Llama, Mistral, Gemma, Qwen, and Phi model families with distributed training across multiple GPUs. Designed as a hackable, dependency-minimal alternative to higher-level frameworks.

All-in-one embeddings database with RAG, search, and agent capabilities

txtai is a self-contained AI search and RAG platform that combines vector embeddings, semantic search, LLM pipelines, and agent workflows in a single Python library. It handles embedding generation, similarity search, extractive QA, summarization, translation, and custom pipelines without external dependencies. Runs locally with over 12,400 GitHub stars and Apache 2.0 license.

Extremely fast Python type checker written in Rust

ty is an extremely fast Python type checker built in Rust by Astral, the team behind Ruff and uv. It performs full type inference, supports PEP 695 type parameter syntax, and checks Python code orders of magnitude faster than mypy or pyright. ty completes the Astral Python toolchain alongside Ruff for linting and uv for package management, giving developers a unified Rust-powered development experience.