Notte is a full-stack web AI agent framework and browser automation SDK. The implementation is a multi-package Python monorepo: notte-core provides shared domain models, actions, error hierarchies, telemetry, and configuration; notte-browser implements Playwright/Patchright browser control, DOM snapshotting, scraping pipelines, and form-filling heuristics; notte-agent contains the LLM-driven agent loop, deterministic fallback, and workflow execution; notte-llm wraps LiteLLM with structured completions, retries, and a file-based prompt library; notte-sdk is the client for the hosted Notte cloud API with remote sessions, agents, vaults, personas, and serverless functions; notte-integrations adds notifiers and third-party CDP session providers. Primary entry points are `NotteClient` for cloud usage, `NotteSession` for local browser automation, and `Agent`/`AgentFallback` for autonomous and hybrid scripted-agent workflows.
PiDeck is an open-source Electron desktop application that serves as a comprehensive workbench for AI coding agents, primarily wrapping the `pi` coding agent and the DeepSeek Harness (DSH) backend. It provides a rich session-centric chat workspace with features including multi-project management, Git integration, a built-in terminal, voice transcription, image generation, scheduled automation tasks, a desktop pet companion, and extensive configuration options. The application supports importing sessions from other tools like Claude, Codex, Cursor, and OpenCode, and offers a web service variant for remote access. Architecturally, PiDeck follows the standard Electron pattern with a main process (Node.js services, IPC handlers, filesystem operations), a preload script for secure IPC bridging, and a renderer process built with React 19, TypeScript, Jotai for state management, and Tailwind CSS v4 with shadcn/ui-style components. The codebase is organized into `src/main/` for backend services, `src/renderer/` for the UI, and `src/shared/` for cross-process types and utilities. Key entry points include the main process index, renderer bootstrap, and numerous IPC modules that validate inputs and delegate to domain services. Data flows center on session files stored in JSONL format (for pi) or compressed JSONL (for DSH), with model catalogs, usage statistics, and configuration persisted in user data directories. The application manages multiple backends through a unified session catalog, with runtime state synchronized via IPC events and Jotai atoms. External dependencies include the pi-coding-agent CLI, DSH runtime packages, node-pty for terminal emulation, whisper.cpp for local speech-to-text, and electron-updater for cross-platform updates. The codebase demonstrates strong engineering practices with extensive unit tests (node:test), Playwright E2E tests, pure-function modules extracted for testability, and consistent IPC boundary validation patterns.
Taste-skill is not a software application in the traditional sense; it is a portable library of AI-agent 'skills' - extremely detailed Markdown instruction files (SKILL.md) distributed via the `npx skills add` CLI (Vercel agent-skills spec) and a .claude-plugin marketplace. The repo's product is the prompt content itself: 13 frontend design-direction skills that agents like Claude Code, Codex, and ChatGPT load to avoid generic 'AI slop' output. The flagship is `taste-skill` v2 (`design-taste-frontend`), a ~5000-line instruction document that codifies anti-pattern bans (zero em-dashes, no section-number eyebrows, no three-equal-card rows), a brief-inference protocol, design-system mapping to official packages (Fluent, Carbon, Polaris, GOV.UK), canonical GSAP/scroll-reactive code skeletons, and a hard pre-flight checklist with mechanical pass/fail criteria. It is complemented by image-generation-only skills (brandkit, imagegen-frontend-web/mobile) that produce reference comps for downstream coding agents, plus variant skills (brutalist, minimalist, soft, stitch, output-enforcement). The repository also contains a `research/laziness/` folder documenting LLM output-truncation causes and remediation, and a small set of Node/Sharp image-processing scripts used to build the README assets. Those scripts contain one genuinely valuable, extractable algorithm: a flood-fill outer-background removal with auto-cropping to content bounds. The scripts are one-off (hardcoded `C:/Users/User/Downloads` source paths, tightly coupled to specific sponsor assets), so they are not drop-in reusable without adaptation, but the background-removal technique itself is portable. This is a content/instruction repository rather than a codebase; software-engineering quality bars (tests, CI) do not apply. Its craftsmanship lives in the rigor, specificity, and mechanical enforcement of the prompt files, which is exceptional for the prompt-engineering domain. The active development cadence, current dependency references (Tailwind v4, Motion/react, React Server Components), and 92k-star traction confirm it is the leading project in its niche.
OpenHands/OpenHands is the frontend application for the OpenHands AI agent platform, known as Agent Canvas. It is a React single-page application (SPA) built with Vite, TypeScript, Tailwind CSS, and React Router. The application provides a comprehensive user interface for interacting with AI coding agents (OpenHands, Claude Code, Codex, Gemini, or any ACP-compatible agent) via an agent server. It supports multiple backends (local self-hosted, cloud at app.all-hands.dev) with a backend registry that routes API calls accordingly. The UI includes a chat interface with real-time WebSocket event streaming, a conversation panel for managing multiple sessions, a file explorer with Monaco editor, terminal emulator, browser snapshot view, git integration (commits, diff viewer, push/pull), settings for LLM profiles, MCP servers, secrets, skills/plugins, and an automation dashboard for scheduled or event-driven agent runs. The application is also published as an npm package (@openhands/agent-canvas) for embedding in other applications, and supports Electron desktop builds. The architecture follows a modern React pattern with Zustand for client-side state management (conversations, events, UI preferences), TanStack React Query for server-state caching and synchronization, and react-i18next for internationalization. The backend abstraction layer is a key architectural feature: every service (settings, profiles, git, secrets, automations, etc.) branches on the active backend kind (local vs cloud) and delegates to either a direct SDK client (@openhands/typescript-client) or a cloud proxy (callCloudProxy). This dual-transport pattern is enforced by guard tests that prevent ad-hoc HTTP calls outside vetted files. The application also includes a manifest system for declarative automation setup, a tool visualizer registry for rendering agent tool calls (bash, file editor, search, task), and extensive mock infrastructure (MSW) for development and testing. Key entry points include the root layout (src/routes/root-layout.tsx) which provides the main shell with sidebar, command menu, and onboarding; the conversation main view (src/components/features/conversation/conversation-main/conversation-main.tsx) with resizable panels for chat and tabs; the settings pages (src/routes/settings.tsx) with schema-driven forms; and the automation dashboard (src/routes/automations-list.tsx). External dependencies include the agent server REST API, cloud proxy endpoints, @openhands/typescript-client SDK, @openhands/extensions for automation catalogs, and various UI libraries (HeroUI, framer-motion, xterm.js, Monaco editor). The codebase is actively maintained with over 84k stars, frequent commits, and a large test suite (Vitest unit tests, Playwright E2E tests, Stryker mutation testing).
DeerFlow is an open-source, full-stack AI agent harness built on LangGraph/LangChain, providing a production-ready platform for building, deploying, and managing conversational AI agents. The system features a Python/FastAPI backend with a modular architecture that includes agent orchestration, long-term memory (DeerMem), sandboxed code execution, a skill system with static analysis (SkillScan), MCP (Model Context Protocol) tool integration, multi-channel IM support (Telegram, Slack, Discord, Lark, etc.), scheduled tasks, subagent batches, and a comprehensive authorization framework. The frontend is a Next.js/React workspace with real-time streaming, artifact management, and a terminal UI (TUI) for headless operation. The architecture follows a gateway pattern: the FastAPI gateway handles authentication (JWT, OAuth, PATs), routing, and SSE streaming, while the core harness package (`deerflow`) implements agent logic, middleware chains, and runtime components. Persistence uses SQLAlchemy with Alembic migrations, supporting both SQLite and PostgreSQL. The system is highly extensible via a Python extension API (`deerflow-extension-api`) and a plugin system for frontend surfaces. Deployment supports Docker Compose and Kubernetes (Helm chart). While primarily an application, DeerFlow includes research-oriented components such as memory eviction benchmarks, context snapshot evaluations, and tracing integrations (LangSmith, Langfuse, OpenTelemetry). The codebase demonstrates strong engineering practices with extensive unit tests, blocking IO regression tests, and contract tests, though its large feature surface and many configuration options introduce complexity and potential for drift between environments.
Huginn is a self-hosted, hackable automation platform built as a Ruby on Rails application. It allows users to create and chain 'agents' that monitor, scrape, transform, and act on data from hundreds of sources (web, RSS, email, Twitter, Telegram, Slack, OpenAI, etc.) via an event-driven architecture. Agents are polymorphic Ruby classes with a consistent lifecycle: scheduled checks, event reception, and event emission. The system supports Liquid templating for dynamic configuration, OAuth services, file pointers, and background job processing via DelayedJob. The codebase is extensive with 80+ agent types, reusable concerns (WebRequestConcern, LiquidInterpolatable, FormConfigurable), and a comprehensive test suite. While primarily an application, it includes a small research dataset (ANEW sentiment norms) used by a sentiment analysis agent, but the dominant character is clearly a production automation service.
GPT Researcher is an autonomous research agent that produces comprehensive, cited reports from web and local sources. In production, it operates as a full-stack web application: a FastAPI backend (main.py, backend/server/app.py) exposes REST and WebSocket endpoints for initiating research, streaming progress, and retrieving reports. A Next.js frontend (frontend/nextjs/) provides the user interface, and a lightweight vanilla JS frontend (frontend/scripts.js) is also available. The core Python package (gpt_researcher/) can be used programmatically via the GPTResearcher class or as a CLI tool (cli.py). Architecture follows a planner-executor pattern: given a research task, the system generates sub-queries, executes them in parallel across 20+ search engine wrappers (Tavily, Google, Bing, Brave, DuckDuckGo, ArXiv, PubMed, etc.), scrapes the resulting URLs using multiple backends (BeautifulSoup, browser automation, PyMuPDF, FireCrawl), filters and compresses the context using embedding or keyword-based methods, and finally generates a structured report with citations. The system supports multiple report types (summary, detailed, deep research) and multi-agent orchestrations (LangGraph, AG2) for more complex workflows. Key data flows: user query to sub-query generation (LLM) to parallel search across configured retrievers to URL scraping to context compression to source curation to report generation (LLM) to output as markdown/PDF/DOCX. Real-time progress is streamed via WebSocket. External dependencies include LLM providers (OpenAI, Anthropic, Google, Ollama, etc.), search APIs (Tavily, SerpAPI, etc.), and optional services (MCP servers, vector stores, image generation APIs). The codebase demonstrates strong engineering practices: extensive test suite (200+ tests), plugin architecture for retrievers, configurable context filters, cost tracking, and evaluation frameworks for quality and hallucination. However, it carries maintenance risks from its large dependency surface, multiple parallel agent implementations, and reliance on rapidly-changing external APIs.
FastGPT is a production-grade AI Agent building platform that enables users to create, deploy, and manage AI applications through a visual workflow editor. The system provides a full-stack solution including a Next.js frontend with Chakra UI, a comprehensive REST API layer, and a modular backend architecture. Core capabilities include a workflow engine with agent loops, tool calling, dataset (knowledge base) management with vector search, sandboxed code execution (JS/Python), multi-tenant team management with fine-grained permissions, billing and usage tracking, and integration with external platforms (WeChat, Feishu, Dingtalk, MCP). The platform is designed for both open-source community and commercial deployments, with feature gating via license activation. The codebase is organized as a monorepo with clear separation of concerns: shared types and constants in `packages/global`, business logic in `packages/service`, UI components in `packages/web`, data access layer in `packages/dal`, and separate services for sandbox execution and volume management. It relies on MongoDB, Redis, BullMQ, S3-compatible storage, and multiple vector database backends (PG, Milvus, OceanBase, SeekDB, OpenGauss). The architecture is predominantly monolithic with the main application as a Next.js app, but sandbox and volume manager run as independent services, indicating a hybrid monolith/microservices pattern.
Hermes Studio is a self-hosted AI agent orchestration platform providing a unified interface for multiple AI agents (Hermes, Ekko, Claude Code, Codex, Pi) with chat, workflow automation, agent management, and skill-based extensibility. The architecture features a Vue 3 frontend, Node.js/Koa backend, Electron desktop client, and hybrid TypeScript/Python agent runtime. Key capabilities include real-time collaboration via Socket.IO, voice processing with multiple STT/TTS providers, file management with preview capabilities, usage analytics, and Model Context Protocol (MCP) integration for extending agent tools. The platform supports social messaging integrations (Feishu, Telegram, Weixin) and MCU device support for embedded voice processing.
AutoRAG is a production-grade, privacy-focused personal AI assistant and retrieval-augmented generation (RAG) agent. It provides a local-first search and answer engine that indexes federated datasources (Slack, Discord, KakaoTalk, GitHub, email, Obsidian, RSS, cloud drives, and more) via external CLI connectors, without migrating data. The system exposes a CLI, MCP server, TypeScript API, and a TUI (Pi interactive host), and powers a separate desktop Electron app. Its architecture is modular: a configurable agent (`AutoRAGAgent`) orchestrates multiple retrieval methods (BM25, semantic vectors, hybrid RRF, file-name search, web search), document parsing (PDF, DOCX, HWP, images via OCR), embedding (local Qwen3 model or external APIs), reranking (OpenRouter/Dazzi), and evidence judgment. A peer-to-peer layer (SimpleX) enables policy-controlled file sharing with injection and PII gates. The repository also contains a legacy Python codebase (`legacy/`) focused on automated RAG pipeline evaluation and QA dataset generation, which is in maintenance mode but still provides reusable metrics and pipeline components. This is a hybrid project where the dominant character is a modern TypeScript application, with significant data/research heritage in the legacy Python portion.
PPTAgent is an agentic PowerPoint generation system designed for integration with AI coding agents (Claude Code, Codex, OpenCode). It creates editable PowerPoint presentations from text briefs through a workflow involving HTML slide authoring, rendering, visual review (either multimodal or via external visual models), and PPTX export. The system features a dual-codepath architecture: 'deeppresenter/' as the current runtime with CLI, multi-agent orchestration, and MCP tool integration, and 'pptagent/' as the legacy core generation library still used for the MCP server entrypoint. Key capabilities include template-driven slide generation, visual quality validation, context management to prevent overflow, and support for optional document processing (MinerU) and search APIs. The skill-based architecture allows coding agents to invoke presentation generation as a tool while maintaining editable source artifacts.
Swarm is a production-grade Swift-native agent runtime framework for building multi-agent conversational systems with type-safe tools, on-device Apple Foundation Models, composable workflows, memory, guardrails, and observability. The architecture is modular: core agent execution (Agent, Workflow, Job) with pluggable inference providers (Foundation Models, OpenAI-compatible, mock), memory backends (conversation, sliding window, summary, vector, persistent via SwiftData or Wax SQLite), and tool integration (built-in tools, MCP protocol, web search). Key entry points include Agent.run()/stream(), Workflow.execute(), and the SwarmMCPServerService for exposing tools via MCP. Data flows involve agent turns with tool calls, memory retrieval/consolidation, and durable workflow checkpointing via the HiveCore deterministic runtime. External dependencies include Apple FoundationModels (macOS 26+), swift-log, swift-syntax (for macros), and optional Wax (SQLite vector store) and OpenTelemetry SDK. The framework emphasizes compile-time safety via @Tool and @Agent macros, and provides resilience patterns (retry, fallback, circuit breaker, rate limiting) and observability (tracing, metrics, OpenTelemetry).
JeecgBoot is an enterprise-grade low-code development platform that accelerates application delivery through AI-powered code generation, online form/report builders, and workflow integration. The backend is built on Spring Boot 3 with MyBatis-Plus, Shiro, and JWT, supporting both monolithic and microservice architectures (Spring Cloud, Nacos, Sentinel, XXL-Job). The frontend uses Vue 3 + TypeScript + Ant Design Vue with a rich component library including JVxeTable for editable grids and schema-driven forms. The platform provides comprehensive RBAC, multi-tenancy, dynamic data sources, data dictionaries, and third-party integrations (DingTalk, WeChat, Feishu). A dedicated AI module (airag) offers RAG knowledge bases, LLM chat, voice/image generation, and MCP plugin support. The codebase is actively maintained with frequent commits and a large community, though it contains some commented-out legacy code and hardcoded security values that represent minor technical debt.
WorldMonitor is a full-stack, open-source global intelligence platform providing real-time monitoring of geopolitical, economic, military, supply chain, and natural events. The codebase is overwhelmingly an application (single-page web dashboard, Vercel Edge API, Convex backend, Tauri desktop app, CLI, and SDKs) with a secondary data pipeline character (consumer price scraping, external API seeding). It powers a commercial SaaS with free and Pro tiers, featuring a map-based dashboard with 100+ configurable panels, an MCP (Model Context Protocol) server for AI agents, and extensive multi-language support (28 locales). The architecture follows a seed-cache pattern where Railway cron jobs fetch external data into Redis, and serverless Edge functions read cached JSON for low-latency responses. The frontend uses vanilla TypeScript with Vite, deck.gl/MapLibre for mapping, and a panel system for modular UI composition. The system is actively maintained, with daily commits, comprehensive test coverage (unit, integration, E2E with Playwright), and a well-documented API surface with 298 protobuf definitions across 36 domain services. While the codebase is large and occasionally duplicates shared constants across modules, it demonstrates strong software engineering practices including circuit breakers, idempotency keys, rate limiting, and a consistent handler pattern.
OpenMontage is an open-source, agentic video production platform where an AI coding assistant (Claude Code, Cursor) orchestrates the entire pipeline. It provides a library of 100+ tools (video generation, audio, graphics, enhancement, analysis, avatar, subtitles) behind a scored provider selection layer, and 10+ production pipeline manifests (animated explainer, cinematic, documentary montage, talking head, etc.) that define stage order, approval gates, and tool assignments. The core architecture is a Python framework with a BaseTool class, ToolRegistry for auto-discovery, pipeline loader, checkpoint system, and a Remotion-based video composer. It also includes a Backlot living storyboard server for live production monitoring and an Ink Theater procedural puppetry engine. While primarily an application, it contains data/research elements such as ManimGL/ManimCE educational animation examples covering transformer internals, quantum mechanics, and ML concepts, as well as a CLIP-based corpus builder for documentary montage pipelines.
AgentScope is a full-stack, production-grade multi-agent orchestration platform. The core library (`src/agentscope/`) provides a FastAPI-based agent service with CRUD endpoints for agents, sessions, credentials, channels, knowledge bases, schedules, and SOPs. It features a modular middleware onion pattern for agent lifecycle hooks (reply, reasoning, acting, tool execution), a pluggable storage abstraction (Redis, SQL with Alembic migrations, S3 blob store), and a message bus (in-memory or Redis) for inter-session communication and distributed coordination. The system supports real-time voice (WebRTC, DashScope/OpenAI/Gemini/xAI), RAG pipelines with document parsing and vector stores (Qdrant, Milvus, MongoDB, Elasticsearch), channel integrations (Feishu, DingTalk, Discord), and sandboxed workspace backends (Docker, Kubernetes, E2B, Daytona, Apple Containers, Bubblewrap, OpenSandbox). A full React/TypeScript web UI (`examples/web_ui/frontend`) provides chat, channel management, schedule calendar, knowledge base browsing, and MCP hub browsing. Additionally, a terminal console and a goal-oriented pipeline are provided for developer workflows. The framework emphasizes transparency, controllability, and separation between agent logic and infrastructure, supporting multi-agent collaboration, human-in-the-loop permissions, and long-term memory via ReMe and mem0 middleware.
MiroThinker is a deep research agent framework designed for complex, multi-step tasks requiring external tool use. The system orchestrates LLM reasoning with a modular suite of MCP (Model Context Protocol) tools including web search, code execution, vision, audio, and reasoning capabilities. It features sophisticated context management through failure experience summarization and sliding window truncation to handle long conversations. The agent iteratively generates tool calls, executes them via MCP servers, and integrates results until producing a final answer. The repository includes benchmark evaluation scripts for GAIA, BrowseComp, HLE, and other research benchmarks, trace collection utilities for model improvement, and a Gradio demo for interactive use. Architecture centers on an orchestrator managing the agent loop, a pipeline for step execution, tool executors handling MCP server interactions, and LLM abstractions supporting Anthropic and OpenAI APIs with prompt caching.
ByteRover CLI is an AI-powered development assistant that provides persistent, structured memory for AI coding agents through a context tree. It features a multi-layered architecture with CLI (OCLIF), TUI (React Ink), and WebUI (React/Vite) interfaces, backed by a daemon service handling core agent logic. The system enables knowledge curation, synthesis, version control for context trees, swarm-based querying across multiple LLM providers, and integration with external AI agents via MCP. Key capabilities include tool execution (file operations, code execution), review workflows for AI-generated changes, and telemetry tracking.
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.
Nacos is a production-grade dynamic service discovery, configuration management, and service management platform, originally built by Alibaba. The codebase is a large Java/Spring Boot monolith with a React frontend, organized into modules for core infrastructure (cluster, gRPC, Raft consensus, Distro sync), configuration management (CRUD, long-polling, gray rules, history), naming/service discovery (instance registration, health checks, push v2), and an extensive plugin system (auth, datasource, encryption, control, visibility). In recent versions, Nacos has expanded into AI resource management, adding modules for MCP server registry, agent specs, skills, prompts, A2A agent discovery, vector search indexing, and pipeline execution. The repository includes two frontend codebases (legacy console-ui and modern console-ui-next with Radix UI/Tailwind), a Java client SDK, and comprehensive unit/integration tests. The architecture is modular with SPI-based plugin loading, event-driven internal communication, and support for multiple databases (Derby, MySQL, PostgreSQL, Oracle). Despite its size and rapid AI feature growth, the codebase maintains solid engineering practices with clear separation of concerns, extensive test coverage, and a well-defined plugin contract.