This repository is the official Model Context Protocol (MCP) reference implementation, containing seven standalone servers (everything, filesystem, memory, sequentialthinking, fetch, git, time) written in TypeScript or Python. These servers demonstrate the full MCP protocol—tools, prompts, resources, transports (stdio, SSE, Streamable HTTP), subscriptions, sampling, elicitation, tasks, and structured content. They are designed as educational examples for developers building their own MCP servers, not as production-ready solutions. The codebase is well-structured with consistent patterns (server factory, transport abstraction, security-focused path validation, atomic file operations, knowledge graph management) and includes extensive test suites. While actively maintained, some Python servers show drift from the latest MCP SDK (v2 API renames in progress), and the Everything server's demo code is tightly coupled to experimental protocol features. The repository also serves as a central hub for the MCP ecosystem via a curated community resource directory (ADDITIONAL.md).
Odoo is a comprehensive, modular Enterprise Resource Planning (ERP) suite built on a Python backend and a JavaScript/TypeScript frontend. It functions as a full-stack web application framework, providing core business modules (Accounting, Sales, Inventory, HR, CRM) alongside a robust ORM and a component-based UI framework (Owl). The architecture is a modular monolith where the core `odoo/` directory defines the framework and `addons/` contains business logic, localization, and integrations. It relies heavily on PostgreSQL for data persistence and uses a registry pattern for extensibility in both backend and frontend code. The system is designed for high customization through model inheritance (`_inherit`) and frontend patching (`patch`), allowing developers to extend functionality without modifying core code directly. The codebase demonstrates significant craftsmanship in its ORM implementation, which handles complex relationships, computed fields, and access rights rules. The frontend utilizes the Owl framework for reactive components, with a sophisticated service registry for dependency injection. However, the heavy reliance on prototype patching in JavaScript and monkey-patching in Python introduces technical debt and potential fragility during framework upgrades. The repository is actively maintained with frequent commits, a large community, and extensive test coverage including unit tests, integration tests, and UI tours. Localization support is a major feature, with country-specific modules handling tax, invoicing, and compliance requirements.
Qlib is an open-source, AI-oriented quantitative investment platform developed by Microsoft. It covers the full pipeline for quantitative research and trading: data ingestion and feature engineering (Alpha158, Alpha360, high-frequency), model training (traditional ML like LightGBM/XGBoost, deep learning in PyTorch including LSTM, GRU, Transformer, GATs, and reinforcement learning), backtesting with realistic costs and slippage, portfolio optimization, and online serving for production-like deployment. The platform is highly modular and config-driven, with a core library (qlib) and a separate contrib layer for community extensions. It includes a CLI (qrun) for running full workflows from YAML configs, extensive experiment tracking via MLflow, and a rich set of evaluation metrics. While primarily a library/application, it also functions as a research benchmark suite with many example models and data collectors for global markets. The codebase is active and well-maintained, though some components (e.g., TFT model, older RL code) show signs of technical drift due to dependency version locks and deprecated patterns.
AstrBot is a production-grade, multi-platform LLM chatbot framework and development platform. It connects to 10+ instant messaging platforms (QQ, Telegram, Discord, Slack, WeChat, Lark, etc.) via adapter pattern, integrates with 20+ LLM providers (OpenAI, Anthropic, Gemini, DashScope, etc.), and provides a plugin system (Stars) with command/regex/filter decorators. The architecture is a modular monolith: a FastAPI backend serves a Vue 3 dashboard for management, while a pipeline of stages processes incoming messages through waking checks, rate limiting, content safety, LLM interaction, and response delivery. It includes a knowledge base with RAG (FAISS vector store, chunking, hybrid retrieval), agent runners (Dify, Coze, DeerFlow), sandboxed code execution (computer use), TTS/STT, cron jobs, and a CLI. The codebase is well-structured with extensive test coverage, but its broad scope introduces some duplication and deprecated modules.
OI-Wiki is a comprehensive, open-source knowledge base for competitive programming (Olympiad in Informatics, ICPC). It is primarily a static documentation site built with MkDocs, featuring thousands of pages covering algorithms, data structures, mathematics, and programming language tools. The codebase includes thousands of standalone C++/Python/Java code examples, each accompanied by test input/output files, which serve as verified implementations for educational purposes. While not a running application, the repository contains a sophisticated build pipeline (pre-build scripts, post-build HTML processing, custom linting) and extensive CI/CD workflows for testing code correctness and documentation quality. The architecture is that of a content management system with heavy emphasis on reproducible, modular examples. Its primary value lies in the curated collection of reusable algorithm templates and the infrastructure ensuring they remain correct across platforms.
asdf is a command-line application that manages multiple runtime versions (Node.js, Python, Ruby, etc.) per project using a plugin architecture. The Go binary dispatches commands like install, set, current, exec, and reshim; it reads `.tool-versions` files searched from the current directory upward, resolves versions via environment variables, plugin callbacks, and legacy version files, then invokes plugin-provided Bash scripts for listing, downloading, and installing tools. It generates shim executables that proxy to `asdf exec` at runtime, and supports shell completions, hooks, and extension commands. Architecturally, asdf is a modular single-binary Go application with internal packages for plugins, versions, shims, resolution, configuration, Git operations, execution, and plugin index lookups. Key external runtime dependencies are bash (plugin callbacks and hooks), git (plugin repository cloning/updating), and the asdf-plugins index. The codebase reflects a rewrite from Bash to Go (v0.16+), preserving the plugin extension model while introducing typed errors, interfaces, and more maintainable package boundaries. Some legacy BATS integration tests and in-progress cleanup comments remain, but the core implementation is clean and well-organized.
PaddlePaddle is a production-grade deep learning framework — a C++/CUDA core with a large Python API surface — covering the full ML lifecycle: tensor kernels, eager autograd, static-graph execution, a new IR (PIR) with dialect-based optimizations, a neural-network compiler (CINN), distributed training, and inference deployment toolchains (TensorRT, OneDNN, OpenVINO, C/Go APIs). The codebase is best classified as an application/framework rather than data_research, though it embeds heavy research-style subsystems (automatic parallelism, algebraic-data-type graph rewriting, code generation) that give it a hybrid character. Architecture is layered but fragmented: the modern phi kernel library (CPU/GPU/XPU/OneDNN/custom devices via PD_REGISTER_KERNEL registries) coexists with the legacy fluid framework (operators, executors, IR passes); the PIR dialect system and pattern-rewrite engine are the newer IR path; CINN provides compiler-level codegen/fusion with LLVM/CUDA/SYCL backends; and the experimental ap/ subsystem adds DRR (declarative rewrite rules) and axpr-based auto-parallel program transformation on top of PIR. Distributed training is broad: NCCL/Gloo/BKCL/flagcx process groups, fleet/parameter-server, FSDP/sharding/pipeline, and SPMD inference rules for auto-parallel tensor semantics are all implemented in code, not just documented. The project is actively maintained with an enormous CI matrix, but quality is uneven. Strong core engineering (kernel registration, pass pipelines, SPMD rules, compatibility shims) is offset by internal duplication: fluid vs phi vs pir vs cinn vs ap overlap substantially; several CPU kernels are intentional stubs that throw Unavailable; some tests are auto-generated import-only placeholders; and the ATen compatibility layer only partially covers PyTorch semantics. Sub-projects pin stale dependencies (Go 1.15, opt_einsum==3.3.0) and future-dated copyright headers (2026) appear inconsistently. Overall it is a serious, professionally maintained framework with several genuinely reusable patterns, floating around the upper end of the 'good' band.
RealtimeSTT is a production-grade real-time speech-to-text library and server. The core library provides `AudioToTextRecorder`, a facade that orchestrates microphone capture, voice activity detection (VAD), wake-word detection, and multiple ASR backends (faster-whisper, sherpa-onnx, whisper.cpp, etc.) for low-latency realtime and final transcription. It features a dual-lane architecture combining an ultrafast speculative model with a slower accurate model, merged via a sticky alignment algorithm, and a text stabilizer that commits only evidence-backed partials. The server component (`stt-server-production`) is a FastAPI/WebSocket application with a versioned protocol (`realtimestt.remote.v1`) supporting per-session ordered event delivery, fair inference queues, preview snapshots, resume, and HTTP transcription. External dependencies include PyTorch, torchaudio, faster-whisper, sherpa-onnx, and optional engines. The system is designed for voice assistants, dictation, and multi-user ASR services.
This repository is a CLI tool for translating books (EPUB, TXT, PDF, SRT, Markdown) into bilingual versions (original + translation side-by-side) using large language models (OpenAI, Anthropic, Gemini, etc.) and free machine translation engines. It supports multiple translation backends, a provider configuration system, and a PDF-to-EPUB pipeline using docling for PDF extraction and Pandoc for EPUB export. The architecture is modular: loaders parse input formats, translators handle API calls with session context and capability probing, and a pipeline orchestrates PDF-to-EPUB conversion with figure rendering and classification. Key entry points are `make_book.py` and the installed command `bbook_maker`. The tool includes features like plan mode for selective translation, glossary support, resume, progress bars, and Docker support. It has extensive tests covering CLI contract, loaders, translators, pipeline stages, and documentation. External dependencies include LLM APIs, docling, pypdfium2, Pandoc, and various SDKs. The codebase demonstrates careful engineering decisions around capability degradation, session compaction, glossary learning, and structured output ladder. It is a well-maintained application with active development and low technical drift.
PyCaret 4.0 is a full-stack MLOps platform combining a low-code Python AutoML engine, a FastAPI control plane server, and a React web UI into a single deployable system. The engine provides OOP Experiment classes for classification, regression, clustering, anomaly detection, and time series, with native sklearn pipeline implementations and typed result dataclasses. The server adds multi-user workspace management, experiment tracking, model registry, deployment serving, drift monitoring, LLM-powered advisory copilots, scheduling, webhooks, and audit logging. The React frontend offers a rich SPA with real-time event streaming, interactive plots (Plotly), and data-driven forms generated from engine introspection. The architecture is well-structured with protocol-based abstractions for storage (local-fs/S3), data sources (CSV/Postgres), LLM providers (Anthropic/OpenAI/fake), and notebook backends. This is primarily an application (ML platform) but has strong data/research characteristics due to the engine's statistical analyses, dataset profiling, and time-series utilities. The codebase is under active development with a systematic migration from legacy functional APIs to the new OOP architecture, and many components are genuinely reusable.
This repository is Microsoft's Agent Governance Toolkit, a production-grade multi-language framework (Python, TypeScript, Rust, Go, .NET) for enforcing policy, identity, trust, audit, and sandboxing on autonomous AI agents. In production, it intercepts agent tool calls, messages, and delegations before they reach external services, evaluating them against declarative policies (OPA, Cedar, or custom backends) with deterministic outcomes (allow/deny/escalate/transform). The system provides a full governance plane including a Rust-based policy engine (Agent Control Specification), a service mesh (AgentMesh) with API gateway, trust engine, policy server, and audit collector, a hypervisor for execution rings and sandboxing (Docker, Hyperlight, Nono), compliance verification (OWASP, EU AI Act), SLO monitoring, and a plugin marketplace. Integrations exist for LangChain, CrewAI, AutoGen, OpenAI Agents, Semantic Kernel, MCP, and many other frameworks. The toolkit is deployed as CLI tools (`agt`, `agentmesh`, `agentos`), Docker containers with sidecar patterns, Kubernetes charts, and VS Code/Chrome extensions. The architecture is polyglot with a shared policy engine core written in Rust; the Python SDK is the richest, with the .NET and Go SDKs covering governance middleware and lifecycle management. The codebase is heavily tested with 992 conformance tests across 10 formal specs, fuzzing targets, and CI gates enforcing deterministic policy outcomes, fail-closed behavior, and no-stub registration.
Dograh is an open-source voice AI platform for building, deploying, and monitoring conversational voice agents. It provides a visual workflow builder (React/Next.js frontend) where users compose nodes (start, agent, end-call, tools, integrations) into call-handling graphs. The backend (Python/FastAPI) orchestrates real-time voice pipelines using the Pipecat framework, supporting multiple LLM, TTS, and STT providers (OpenAI, Google Gemini, Deepgram, ElevenLabs, etc.) and telephony carriers (Twilio, Vonage, Telnyx, Plivo, Asterisk ARI, WhatsApp, etc.). The system handles inbound/outbound calls, campaign management with traffic splitting and retry logic, text chat sessions, and embeddable widgets. It includes an MCP server that allows AI coding assistants to programmatically create and edit workflows, and auto-generated Python and TypeScript SDKs for programmatic access. The platform is multi-tenant with organization isolation, usage tracking, billing hooks, and extensive observability (Langfuse tracing, PostHog analytics, Prometheus metrics, call event export to BigQuery). Architecturally, the backend follows a modular provider registration pattern: telephony providers, LLM/TTS/STT services, and integration packages (Noveum, Tuner, Paygent) self-register via import side effects, enabling easy extensibility. The workflow engine uses a node-spec system that drives both the UI form renderer and SDK code generation, ensuring consistency. The system uses PostgreSQL (with pgvector for embeddings), Redis (for caching, pub/sub, rate limiting, task queue), and object storage (S3/MinIO). Deployment supports Docker Compose, Helm/Kubernetes, and a devcontainer setup. Key entry points include the FastAPI application (api/app.py), the MCP server (api/mcp_server/server.py), the ARQ background worker (api/tasks/arq.py), and the telephony ARI manager (api/services/telephony/ari_manager.py). The frontend is a Next.js application with a workflow editor, run viewer, settings pages, and billing dashboard. The SDKs provide typed workflow builders and client libraries for both Python and TypeScript.
YouDub WebUI is a full-stack video localization platform that enables users to import videos, transcribe speech via Whisper, translate via OpenAI-compatible APIs, clone voices with VoxCPM2, separate audio with Demucs, align subtitles with Qwen3 Forced Aligner, and export dubbed videos or subtitles. The architecture is plugin-based (Cordis framework) with a Node.js/TypeScript host orchestrating Python subprocesses for ML inference, a Next.js web frontend, and native desktop apps for macOS (Swift) and Windows (C#). The system features a task engine with queuing, cancellation, retry, and partial rerun; a worker protocol using NDJSON over stdin/stdout; and a comprehensive setup service that downloads and verifies model weights. While primarily an application, it includes research-grade model consumption and detailed validation records documenting real-media runs with SHA-256 hashes and human listening feedback. The codebase is actively maintained with recent commits, CI/CD pipelines, and extensive unit tests for contracts, protocols, and permissions.
ServerStatus is a lightweight server monitoring and cloud dashboard system. It consists of a Go-based server that accepts TCP connections from Python clients, collects system metrics (CPU, memory, disk, network, processes, ping latency), and exposes a real-time JSON stats endpoint and a full REST management API. The server also supports service monitoring (HTTP/TCP probes), SSL certificate expiry checks, and a configurable watchdog rule engine that evaluates expressions against live metrics and triggers HTTP callbacks. The web UI is a single-page application with filtering, sorting, detail drawers, and an admin panel for CRUD operations on configuration. The architecture is a classic client-server model: multiple Python agents (client-linux.py or client-psutil.py) connect to a single Go server over a custom TCP protocol. The server authenticates agents, receives periodic metric updates, and serves a web dashboard and API. The Go server is a monolith with separate modules for HTTP handling, TCP agent handling, configuration management, SSL checking, and watchdog evaluation. It uses the Gin web framework for HTTP and the expr-lang library for rule evaluation. Key entry points are the TCP agent listener (port 35601), the HTTP server (port 80/8080), and the CLI flags for configuration. External dependencies include Go modules (gin, expr-lang), Python libraries (psutil for the psutil client), and Docker for containerized deployment. The system is designed for easy deployment via Docker Compose or shell scripts, with environment variable overrides for all client and server settings.
Twikit is an asynchronous Python library that provides a comprehensive, unofficial client for the Twitter (X) API. It allows users to perform a wide range of Twitter operations—such as posting tweets, searching for tweets and users, managing bookmarks and lists, sending direct messages, uploading media, and streaming real-time events—without requiring an official API key. The library achieves this by reverse-engineering Twitter's internal GraphQL and REST v1.1 endpoints, handling authentication via login flows or guest tokens, and implementing sophisticated anti-bot evasion techniques like client-side transaction ID generation (X-Client-Transaction-Id) and UI metrics obfuscation. The architecture separates concerns into GraphQL (gql) and REST (v11) client modules, with data models for tweets, users, communities, and more. It includes optional CAPTCHA solving and cookie persistence for session reuse. The codebase is well-structured, actively maintained, and demonstrates deep reverse-engineering skill, particularly in the `x_client_transaction` module that mimics Twitter's client-side telemetry.
PMXT is a unified prediction market SDK that aggregates data and trading across 15+ venues (Polymarket, Kalshi, Limitless, etc.) into a single, consistent interface. The system provides a core TypeScript library with a local sidecar server (Express), plus TypeScript, Python, and CLI SDKs that support both self-hosted and hosted (trade.pmxt.dev) modes. It offers market data (events, order books, trades, OHLCV), WebSocket streaming, order management (create, cancel, fetch), account balance and positions, cross-venue router for event matching and arbitrage, and data feeds (Binance, Chainlink). The architecture is a monorepo with workspaces core, sdks/typescript, sdks/python, sdks/cli, and tools. Each exchange follows a clean fetcher → normalizer → error mapper pattern, and the SDK surfaces are partially generated from the core's method signatures. While primarily an application SDK, the project includes significant data normalization, cross-venue data aggregation, and a router for analytical queries, giving it a hybrid character.
This is a full-stack cultivation world simulator game (xianxia RPG) with a Python backend (FastAPI + asyncio) and a Vue 3 + TypeScript + PixiJS frontend, supported by an optional Electron desktop shell for Epic Games Store distribution. The simulation engine runs a month-by-month tick system orchestrating ~29 phases (lifecycle, actions, social, war, world events, etc.) producing emergent narratives driven by LLM calls (OpenAI/Anthropic compatible) for character decisions, story generation, world lore rewriting, and roleplay interactions. The codebase is heavily data-driven with static game configurations (sects, techniques, items, regions) loaded from CSV files and multi-language localization via gettext PO files. It exposes a public REST API (query/command) and WebSocket for real-time state updates, supports save/load with JSON snapshots and SQLite event storage, and includes comprehensive test coverage (pytest, vitest, Playwright) and CI/CD workflows. While the architecture shows strong engineering patterns (effect system, action registry, single-choice decision framework, phased simulation pipeline), it carries risks from tight coupling of global singleton registries, LLM dependency, and use of `eval` in effect conditions.
LedFx is a networked LED light effect controller that synchronizes multiple addressable LED devices (e.g., WLED, LIFX, Nanoleaf, Art-Net, DDP) to real-time audio analysis. It runs as a Python asyncio application with a built-in aiohttp REST API and a prebuilt React frontend served on port 8888. The system captures audio from system loopback, microphone, or network streams (Sendspin), processes it through FFT/melbank/beat detection, and drives audio-reactive effects on virtual LED strips and matrices. It also integrates with now-playing services (MPRIS, SMTC, Sendspin) to extract album art gradients and apply them to effects. The architecture is plugin-based: effects, devices, integrations, and API endpoints are registered via a `BaseRegistry` pattern with voluptuous schema validation. The core runtime (`LedFxCore`) orchestrates device discovery, virtual management, scene/playlist systems, and configuration persistence. The codebase is well-structured with clear separation of concerns, but some modules (e.g., `core.py`, `virtuals.py`) are large and handle multiple responsibilities. The project is actively maintained with comprehensive CI/CD, extensive test coverage (including API integration tests), and detailed documentation for users and developers.
SALib is a Python library for global sensitivity analysis (GSA) of computational models. It implements a comprehensive suite of variance-based and moment-independent methods including Sobol', Morris, FAST, DGSM, PAWN, HDMR, RBD-FAST, and fractional factorial designs. The library follows a decoupled workflow: sample parameter space, evaluate the model, then analyze results. It provides both a programmatic API (import SALib) and a command-line interface (salib sample/analyze). The architecture is modular: sampling modules in SALib.sample, analysis modules in SALib.analyze, with shared utilities in SALib.util. A high-level ProblemSpec class enables fluent method chaining (sample → evaluate → analyze → plot). Results are returned as ResultDict objects with to_df() and plot() methods for integration with pandas and matplotlib. External dependencies are numpy, scipy, matplotlib, pandas, and optionally multiprocess/pathos for parallel execution. The library is used in environmental modeling, energy systems, and uncertainty quantification research, with over 1000 GitHub stars and a JOSS paper.
DeepZero is an automated vulnerability research pipeline engine, primarily targeting Windows kernel driver (BYOVD) analysis. It provides a highly concurrent, resumable orchestration framework where pipelines are defined declaratively in YAML. The engine supports stages: ingest, map (parallel analysis), reduce (aggregation), and bulk_map, with built-in fault tolerance, atomic state persistence, and live progress dashboards. It integrates external tools like Ghidra (headless decompilation), Semgrep (static analysis), LIEF (PE parsing), and LLM backends (LiteLLM, Claude Code) for exploitability assessment. The repository includes a full reference pipeline (loldrivers) and multiple language documentation sites. While primarily an application framework, it has strong data research characteristics due to its focus on binary corpus analysis and heuristic/AI assessment.