This repository is a Python library and framework for building and deploying multi-agent AI systems. It provides a structured way to define agents with specific roles, instructions, tools, and communication flows, orchestrated by an Agency. The framework extends the OpenAI Agents SDK with production-grade features: FastAPI web serving with streaming SSE endpoints, realtime voice support via WebSocket and Twilio, MCP (Model Context Protocol) server integration with OAuth authentication, persistent conversation state with load/save callbacks, system reminders for prompt engineering, input/output guardrails, and observability hooks for Langfuse/AgentOps. It also includes CLI tools for scaffolding agents and migrating from OpenAI Assistant configurations. Architecturally, the system is a library that can be used programmatically (create Agent and Agency instances, call get_response) or deployed as a FastAPI application via run_fastapi(). The core data flow involves user messages flowing through an agent's execution pipeline, which may invoke tools (built-in, MCP, OpenAPI, LangChain), hand off to other agents via SendMessage/Handoff, and stream responses back. The ThreadManager provides flat message storage with agent/caller metadata, supporting thread isolation and persistence. The tool system uses Pydantic models for schema generation and supports concurrency control. Key entry points include the Agent and Agency classes for programmatic use, run_fastapi() for web deployment, run_realtime() for voice, run_mcp() for MCP server, and CLI commands (create-agent-template, migrate-agent, import-tool). External dependencies include the OpenAI Agents SDK (pinned), FastAPI, Pydantic, and optional integrations like LiteLLM, LangChain, and MCP SDK. The codebase demonstrates strong engineering practices with extensive test coverage (unit, integration, live API), modular design, and reusable patterns such as the BaseTool class, ToolFactory adapter, ThreadManager message store, and OAuth flow for MCP. However, it has tight coupling to the OpenAI Agents SDK internals, requiring careful maintenance as the SDK evolves.
Tokimeki is a full-featured, open-source Bluesky client built with SvelteKit and TypeScript. It provides a multi-column deck layout (similar to TweetDeck) with support for multiple accounts, real-time timeline updates, chat (direct and group), rich media embeds, custom moderation (keyword mutes, labelers), and extensive customization (themes, keyboard shortcuts, layout options). The application uses the AT Protocol (XRPC) for all Bluesky interactions, implements OAuth and password-based authentication, and includes a service worker for push notifications and offline caching. Architecturally, Tokimeki is a single-page application (SPA) with server-side routes for OAuth flows, AI features (alt text generation, column icon suggestions), and proxy endpoints. State management is handled via Svelte 5 runes ($state, $derived) and custom reactive classes (ColumnState, AppState, PostState). Data persistence uses IndexedDB (via Dexie) for accounts, bookmarks, and drafts, and localStorage for settings. The codebase is modular with clear separation of concerns: UI components in src/lib/components/, state classes in src/lib/classes/, utilities in src/lib/, and routes in src/routes/. It includes a comprehensive test suite using Vitest and Playwright. Key features include a custom feed merge engine for combining multiple timelines, a virtual scrolling system with Fenwick tree for efficient rendering, an image compression pipeline with WebAssembly and fallback, a full chat system with group management, and an atmosphere service registry for third-party integrations. The application is internationalized with 10+ locales and supports on-device translation via the browser's Translator API.
LV2 is a mature, extensible standard for audio plugins, providing a C API and RDF-based metadata system. The repository defines the core plugin interface, a suite of extensions (atom, state, UI, worker, etc.), and tooling for documentation generation and validation. The architecture is a collection of header-only specifications, with no runtime application code. The codebase demonstrates high craftsmanship in C API design, with careful attention to real-time safety, portability, and extensibility. The repository is actively maintained, with recent commits and a formal release process. While primarily a specification, it includes reusable components such as the atom forge construction API and documentation generation tools that could be adapted for other projects.
Meteor is an ultra-simple full-stack JavaScript framework for building modern web and mobile applications. This monorepo contains the Meteor CLI tool (`meteor`), the build system (isobuild, Rspack integration), core runtime packages (reactive data via DDP, MongoDB integration, accounts, Blaze templating, modules, bundling), and a rich ecosystem of OAuth providers, testing infrastructure, and developer tools (ESLint plugin, Babel preset, installer). The codebase is organized as a monorepo with `tools/` for the CLI and build system, `packages/` for framework packages, and `npm-packages/` for standalone npm packages. It demonstrates a real-time data synchronization pattern using DDP (Distributed Data Protocol), a custom constraint solver for package dependency resolution, and a compiler plugin system for transpilation. Despite being a well-established framework with extensive testing, the codebase shows signs of technical drift: deprecated packages remain in-tree, there is a dual sync/async API surface due to ongoing migration from Fibers to async/await, and the build system is transitioning from a legacy compiler to Rspack.
This Rust codebase is an LLM inference proxy and tool-routing gateway. It exposes an OpenAI-compatible HTTP API (`/v1/chat/completions`, `/v1/models`) and forwards requests to multiple upstream LLM providers (OpenAI, Anthropic via direct/Bedrock, Vertex AI, vLLM DeepSeek, TokenHub) through a unified Provider trait. A QUIC server (s2n-quic, TLS 1.3) accepts connections from serverless tools written in Go or Node.js; the agent loop performs multi-round tool calling, invokes registered tools, and streams results back in SSE format. A separate model API proxy layer handles non-chat endpoint shapes (messages, responses, generateContent) with usage extraction and injection. Architecturally, the system is a Rust CLI binary (`yomo`) with three subcommands: `serve` starts the HTTP API and QUIC zipper, `init` scaffolds serverless tool projects, and `run` launches a tool subprocess and connects it to the zipper. Tool registration is done at runtime over QUIC and stored in-memory, so state is lost on restart. The HTTP layer is Axum, auth is bearer-token, and observability uses OpenTelemetry. The serverless execution model is subprocess-based: it creates temporary directories, runs `npm install`/`go mod tidy`, and exchanges metadata over stdout. Reusable engineering exists in the framing protocol (`io`), streaming SSE mappers, usage aggregation logic, TLS configuration, and provider error separation. However, the provider implementations are duplicated and brittle to upstream API drift; hard-coded model limits, ephemeral tool state, and near-empty serverless stubs reduce long-term maintainability. No integration tests against real upstream APIs were found in the reviewed surface.
This repository is the official JavaScript/TypeScript client SDK for Centrifugo, a scalable real-time messaging server. It provides a robust, event-driven client (Centrifuge class) that manages persistent connections via multiple transports (WebSocket, SSE, HTTP stream, SockJS, WebTransport), handles token-based authentication and subscription authorization, and supports three subscription models: stream (standard channel), map (keyed data), and shared poll (polling with version tracking). The SDK also implements advanced features like automatic reconnection with exponential backoff, recovery from connection drops using offset/epoch, command batching for HTTP transports, and delta compression for efficient updates. The architecture is library-oriented with a clear separation of concerns: transport implementations are abstracted behind a common interface, the main client class manages connection state and dispatch ordering via a serial promise chain, and each subscription type extends a base class with its own state machine (stream, map three-phase, shared poll). The codebase is extensively tested with both unit tests (using a fake server) and integration tests against a real Centrifugo instance in Docker. The SDK is published on npm, supports CJS and ESM builds, and includes protobuf codec support. Notable patterns include a transport abstraction with dependency injection that allows easy addition of new transports, a serial dispatch chain ensuring ordered response processing, and a per-key publish debounce mechanism. The library is actively maintained with ongoing work on refactoring subscription types as documented in NEXT_MAJOR_SUBSCRIPTION_TYPES.md. The repository also demonstrates high craftsmanship in its comprehensive test coverage, graceful error handling, and careful handling of edge cases like stale tokens, network interruptions, and concurrent operations.
Plow is a high-performance HTTP(S) benchmarking CLI tool written in Go. It uses fasthttp for efficient HTTP client operations and provides real-time metrics including latency statistics, percentiles, histograms, and throughput. The tool supports configurable concurrency, request rate limiting, ramp-up, duration-based or request-count-based runs, and custom headers, body, TLS, and proxy settings. It outputs results to the terminal with live updating tables and also serves a web UI with interactive charts (latency, RPS, status codes, concurrency) using go-echarts. The architecture is a single binary with three main components: a requester that spawns concurrent workers, a stream-based report aggregator that computes streaming quantiles and histograms, and a printer/chart server for output. The code is well-structured, thoroughly tested, and follows Go best practices. It is not a library but a standalone application, though some internal components (e.g., the streaming stats engine and throughput interceptor) are cleanly isolated and could be reused in other projects.
PocketPages is a server-side page rendering framework for PocketBase, enabling developers to build multi-page applications (MPAs) using file-based routing, EJS templating, and a plugin system. The core framework handles route resolution, middleware execution, layout rendering, and asset fingerprinting. It includes a rich plugin ecosystem for authentication (password, OTP, OAuth2, anonymous), realtime SSE updates, Markdown processing, and Datastar integration. The monorepo also provides starter kits (minimal, auth, daisyui, htmx, datastar) and a documentation site built with the framework itself. In production, it runs as a PocketBase hook, intercepting HTTP requests and rendering pages from the `pb_hooks/pages/` directory with full access to the PocketBase JSVM API.
This repository is the official W3C WebSub specification (formerly PubSubHubbub), a decentralized publish/subscribe protocol over HTTP. It is not a software application or data pipeline; it contains the normative ReSpec specification documents, implementation reports, and W3C governance metadata. The core deliverable is source.html, with staged snapshots for FPWD, Working Draft, and the 2018 Recommendation. The spec defines three roles — publisher, subscriber, and hub — and specifies discovery via link rel=hub/self, hub subscription/unsubscription with lease management, content distribution via POST, and optional authenticated distribution using HMAC signatures. It also includes conformance classes and implementation report templates that multiple independent projects (Google, Mastodon, Twitch, Superfeedr, etc.) have used to self-certify interoperability.
This is a Python application and library for singing voice conversion and real-time voice changing, forked from so-vits-svc and rebuilt around PyTorch, PyTorch Lightning, and a Click-based CLI. The actual code provides two user-facing entry points: the `svc` CLI with commands for inference, realtime microphone conversion, dataset preprocessing, training, clustering, and cleanup, and the `svcg` PySimpleGUI desktop application for interactive and realtime inference. Inference loads a HuBERT content encoder from Hugging Face, extracts pitch using CREPE, DIO, Harvest, or Parselmouth, then runs a VITS-style SynthesizerTrn with either HiFi-GAN or MS/MB-iSTFT decoders conditioned on speaker embeddings. Despite fastapi being listed as a dependency, no HTTP API server exists in the source; the project is a desktop/CLI tool, not a web service.
This repository is a collection of standalone example applications demonstrating features of the Gin web framework for Go. It includes over 30 examples covering routing, middleware, authentication, file uploads, WebSocket, server-sent events, gRPC integration, OpenTelemetry, and more. Each example is a self-contained Go program with its own main.go and dependencies. The codebase serves as a learning resource and reference for Gin patterns, but is not a cohesive production system. Many examples are simple and straightforward, though some demonstrate non-trivial patterns like rate limiting, struct-level validation, and concurrent room management.
This repository contains a cross-platform mobile application (iOS and Android) that functions as an AI assistant for Ray-Ban Meta smart glasses. The app connects to the glasses via the Meta Wearables DAT SDK to access camera and microphone streams, then provides various AI-powered features including real-time conversations (Live AI), image recognition (Quick Vision), food nutrition analysis (LeanEat), real-time translation, and experimental RTMP streaming. The architecture follows MVVM patterns on both platforms, with SwiftUI/Jetpack Compose for UI, ViewModels for state management, and service layers handling API communications with multiple AI providers (Alibaba Cloud, Google Gemini, OpenRouter). Key features include secure API key storage, Bluetooth audio routing for glasses microphones, and integration with external systems like OpenClaw. The application is actively maintained with recent commits and demonstrates solid engineering practices, though the multi-platform nature and reliance on external AI services introduce some complexity.
LiveTalking is a real-time interactive streaming digital human engine that synchronizes lip movements with audio generated from text or speech input. It functions as a production-grade web server (Flask + aiohttp) supporting WebRTC, RTMP, and virtual camera output, enabling applications like live streaming, virtual assistants, and conversational avatars. The system integrates a pluggable pipeline: user input → optional LLM (OpenAI-compatible) → TTS (8+ providers including EdgeTTS, CosyVoice, GPT-SoVITS) → lip-sync model inference (Wav2Lip, MuseTalk, Ultralight Digital Human) → video frame compositing → streaming output. It also includes ASR via a local FunASR/SenseVoice WebSocket server and a web admin UI for session management and avatar generation. Architecturally, it follows a plugin-based design using a decorator registry (registry.py) that allows extending TTS, Avatar, and Output modules via registration. The core rendering loop in BaseAvatar manages three concurrent threads (TTS, inference, frame processing) with queue-based data flow. WebRTC integration uses aiortc for peer connections, and the system supports multi-session concurrency with session limits. While primarily an application, it embeds research-derived model code (Whisper, face detection, face parsing) and includes a benchmark script for ASR latency comparison. The codebase has some technical debt: duplicated face detection utilities, stale Dockerfile (Python 3.10/torch 1.12 vs README's newer requirements), and commented-out legacy code. However, the core architecture is solid, and the plugin system and audio utilities are well-crafted and reusable.