A personal AI assistant that remembers what it learns and reaches you wherever you are — OpenClaw is an open-source agent gateway built by the OpenClaw Foundation with 247,000+ GitHub stars. It connects to 200+ LLM models through providers like Anthropic, OpenRouter, and OpenAI, and meets you on 21+ messaging channels: Telegram, Slack, Discord, WhatsApp, Signal, iMessage, Matrix, and more. Persistent memory with full-text search lets the agent recall context across sessions, and a self-improving skills system means it gets more capable the longer it runs. Voice wake words and talk mode enable hands-free interaction on macOS, iOS, and Android. A live canvas provides an agent-driven visual workspace. Built-in browser automation, cron scheduling for unattended tasks, and subagent spawning for parallel workstreams round out the toolset. The gateway architecture keeps all sessions, credentials, and conversation history on your own server — nothing transits a third-party cloud unless you choose to connect one. The API key you provide for your chosen LLM provider powers the underlying calls; billing goes through your own account. Running on a dedicated VPS with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

OpenRouter's most-used application by token volume — over 17 trillion tokens processed — Hermes Agent is an open-source autonomous agent built by Nous Research that lives on your server and gets more capable every day. Define a goal in natural language and Hermes plans sub-tasks, executes them through tool integrations, observes results, handles errors, and refines until the job is done or it genuinely needs your input. Persistent memory with full-text search and LLM summarization lets it recall context across sessions, and an agent-created skills system self-improves after complex tasks. A messaging gateway connects Telegram, Discord, Slack, WhatsApp, Signal, and 16 more platforms with cross-channel conversation continuity. A built-in cron scheduler runs daily reports, nightly backups, and weekly audits unattended. Subagent spawning parallelizes workstreams, and six terminal backends — local, Docker, SSH, Singularity, Modal, and Daytona — fit any infrastructure. Works with any LLM provider: Nous Portal, OpenRouter for 400+ models from 70+ providers, OpenAI, Anthropic, or your own endpoint. The API key you supply powers all LLM calls; billing goes through your own account. Running on a dedicated VPS with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

DeepSeek Harness gained over 60,000 GitHub stars within hours of its August 2026 launch, establishing itself as the first fully modular open-source agent runtime where literally every component is a swappable plugin. Built on the Cordis framework—a programming paradigm for spatiotemporal composability—dsh decomposes the entire agent stack into independently replaceable pieces: model adapters for DeepSeek, Anthropic, OpenAI, AWS Bedrock, Azure, and Google Gemini; tool registries covering bash execution, file system operations, web search, subagent delegation, and todo management; plus session stores, sandboxes, approval policies, orchestration loops, and the user interface itself. Four operating modes serve different workflows: Standard provides the full toolset, Code mode uses model-generated code to compose multi-round tool calls, Minimal strips down to a shell and editor for benchmarking, and Creator mode lets developers inspect the running runtime and test Cordis plugins in memory. The kernel handles plugin mounting, unmounting, and dependency resolution while typed events and services coordinate between components. Profiles and bundles allow the same codebase to produce entirely different products—a terminal coding agent, a browser-based workspace, a headless automation service, or an ACP/JSON-RPC endpoint—by swapping YAML configuration layers. Session history is stored as an append-only event stream for full trajectory replay, and project-level hooks on agent lifecycle events enable fine-grained behavioral customization. MCP client integration connects to external tool servers, while Agent Client Protocol enables programmatic orchestration. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Webhooks, cron schedules, and app events trigger chains of nodes that fetch, transform, and route data: n8n is a workflow automation platform built around a visual, node-based editor. It ships with 400+ built-in integrations covering databases like Postgres, SaaS tools like Slack and HubSpot, and every major AI provider. When a pre-built node does not exist, the HTTP Request node calls any REST API, and the Code node runs JavaScript or Python inline, so you are never blocked by a missing connector. Workflows execute as directed graphs with branching, loops, error handling, and sub-workflows, and every run is logged for inspection and replay during debugging. It also includes LangChain-based nodes for building AI agents with tool calling and memory. Self-hosting on RepoCloud gives you unlimited workflow executions with no per-task pricing, and all data stays on your instance. Runs on Node.js with SQLite by default; add Postgres and Redis queue mode when you need to scale workers horizontally.

With over 164,000 GitHub stars and one of the fastest-growing open-source projects in the AI tooling ecosystem, Firecrawl is the web context API that turns any website into clean markdown, structured JSON, or screenshots optimized for large language models. The Scrape endpoint converts a single URL into LLM-ready output with approximately 67% fewer tokens than raw HTML, handling JavaScript rendering, rotating proxies, anti-bot bypasses, and dynamic content extraction with zero configuration. The Crawl endpoint recursively scrapes entire websites from a single request with configurable depth, URL filters, and concurrent page limits. The Map endpoint discovers all URLs on a domain instantly for sitemap generation. The Search endpoint performs web searches and returns full page content from results. The Interact endpoint scrapes a page then continues working with it — clicking buttons, filling forms, and extracting dynamic content using AI prompts or code. The Agent endpoint provides autonomous web data gathering where users describe what they need in plain English. SDKs are available for Python, Node.js, Go, Rust, Ruby, PHP, Java, C#/.NET, and Elixir, with an MCP server for connecting to any AI agent or MCP client. Self-hosting deploys via Docker Compose and requires Redis and a Playwright-based browser service for JavaScript rendering. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. AGPL-3.0 licensed.

Langflow turns LLM application development into a visual canvas where every node maps to a real LangChain primitive (chains, agents, retrievers, memory, vector stores, and tools) that teams wire together without writing integration boilerplate. The platform supports 15+ LLM provider components including OpenAI, Anthropic, Google Gemini, Mistral, Groq, Cohere, Azure OpenAI, HuggingFace, and Ollama for fully local inference, with LiteLLM proxying to over 100 additional providers through a single OpenAI-compatible endpoint. Vector database integrations cover Pinecone, Weaviate, Chroma, Qdrant, Astra DB, OpenSearch, FAISS, and Milvus, while built-in Knowledge Bases introduced in version 1.8 allow RAG pipelines without any external vector service. Multi-agent orchestration enables agent-to-agent communication with conversation management, persistent Memory Bases for cross-session context retrieval, and step-by-step reasoning visibility in the interactive Playground. Every flow automatically becomes a callable REST API endpoint via the /run route and an MCP server exposable to Claude Desktop, Cursor, or any MCP-compatible client. Every component is a real Python class that developers can customize, extend, or replace, while Extension Bundles package third-party integrations as independent pip packages for modular installation. Tool integrations include web search, Slack, Gmail, Google Drive, GitHub, and custom REST API calls. Docker deployment with PostgreSQL persistence runs on port 7860. Backed by 153,000+ stars and DataStax. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Dify turns the notoriously complex process of building production-grade AI applications into a visual drag-and-drop experience that teams can actually ship and maintain. With over 87,000 GitHub stars and backing from prominent investors, the platform has become the go-to open-source LLMOps solution for organizations that refuse to be locked into proprietary AI stacks. The visual workflow canvas lets developers wire together LLM calls, conditional logic, iteration loops, tool invocations, and human-in-the-loop checkpoints without writing boilerplate integration code. Its RAG pipeline engine handles the full document lifecycle from ingestion of PDFs, Word documents, and HTML through configurable chunking strategies, embedding with models from OpenAI or open-source alternatives, vector storage in Weaviate, Qdrant, Pinecone, or pgvector, and hybrid semantic-plus-keyword retrieval with citation tracking. Dify integrates with hundreds of model providers including OpenAI GPT-4o, Anthropic Claude, Google Gemini, Mistral, Llama, and any OpenAI-compatible endpoint like Ollama for fully local inference. The agent framework supports both ReAct and function-calling strategies with 50-plus built-in tools spanning Google Search, DALL-E, Stable Diffusion, WolframAlpha, and custom API definitions. Published apps can be deployed as hosted web interfaces, embedded chat widgets, REST API endpoints, or MCP-compatible tools. Enterprise features include role-based access control, SSO integration, and audit logging. A built-in marketplace enables teams to share and reuse model providers, tools, and workflow templates across projects. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. Apache 2.0 licensed with an open-source community edition.

Large language models get a polished front end that can run fully offline: Open WebUI is the self-hosted front end of choice. It talks to local model runners, primarily Ollama, and to any OpenAI-compatible API, so LM Studio, vLLM, Groq, Mistral, OpenRouter, and cloud providers all plug into the same chat interface and can be mixed per conversation. RAG is built in: upload files to knowledge bases or reference them in chat with the # command, backed by a choice of nine vector databases (ChromaDB and PGVector officially maintained) and multiple extraction engines including Tika and Docling, with hybrid BM25-plus-vector search and cross-encoder reranking. Web search results from providers like SearXNG, Brave, and Tavily inject directly into conversations. Extensibility comes from Python tools and functions that run inside the chat, a Pipelines plugin framework, and native MCP support. Multi-user features include RBAC, SSO, and group permissions, and the instance itself exposes an OpenAI-compatible API your own apps can call.

Half the architecture sketches on the internet trace back to Excalidraw - the MIT-licensed virtual whiteboard whose hand-drawn aesthetic made technical diagramming feel approachable, at roughly 85,000 GitHub stars. The infinite canvas offers rectangles, ellipses, diamonds, arrows with smart binding and labels, free-draw, text, images, and an eraser, with full undo/redo, zoom, dark mode, and keyboard-first ergonomics. Community shape libraries add thousands of pre-built elements - AWS architecture icons, flowchart stencils, UI wireframe kits - and everything exports to PNG, SVG, the clipboard, or the open .excalidraw JSON format that keeps drawings diffable and portable. Live collaboration works on a share-a-link model with live cursors and a laser pointer for presenting, and it is end-to-end encrypted by design: the room key travels in the URL hash, which never reaches the server, so the WebSocket relay only ever sees ciphertext. The architecture is remarkably light - the app is a static bundle served by Nginx, drawings persist locally in the browser, and the stateless excalidraw-room relay handles multiplayer - so a self-hosted deployment gives unlimited boards and collaborators with near-zero resource cost, replacing per-editor whiteboard subscriptions.

Real-time collaborative Markdown behind your own firewall: HedgeDoc (formerly CodiMD, descended from HackMD's open-source edition) keeps team notes on team infrastructure. Share a note's URL and collaborators are editing together instantly - live cursors, changes appearing keystroke by keystroke - in a three-mode interface that toggles between raw Markdown, rendered preview, and side-by-side split. The Markdown dialect is extended where engineers need it: Mermaid, Graphviz, and Vega-Lite diagrams, MathJax for equations, syntax-highlighted code blocks, embedded content, and a presentation mode that turns a note into reveal.js slides with a single YAML header. A dropdown permission system controls each note - freely editable, limited to signed-in users, or locked read-only - and published notes become clean read-only pages for wider distribution. Revisions track every change with the ability to revert to any earlier version. The AGPL-3.0 codebase is light enough to run on a Raspberry Pi and deploys via Docker with PostgreSQL, MySQL, or SQLite. Authentication covers LDAP, SAML, OAuth2, and email. It deliberately stays a focused document editor - no page trees or kanban - and does that one job with excellent keyboard-first ergonomics for meeting notes, RFCs, runbooks, and shared scratchpads.

With over 126,000 GitHub stars and adoption across professional studios, research labs, and independent creators, ComfyUI has become the most widely used node-based interface for generative AI workflows — supporting image, video, audio, and 3D content creation through a single visual canvas. The graph editor natively supports Stable Diffusion 1.5, SDXL, SD3.5, Flux.1, Flux.2, HunyuanDiT, Lumina Image 2.0, HiDream, Qwen Image, and Pixart for image generation, plus Wan 2.1 and 2.2, LTX-Video, HunyuanVideo 1.5, CogVideoX, and Mochi for video, ACE-Step and Stable Audio for audio, and Hunyuan3D 2.0 for 3D models. Built-in tools handle inpainting, outpainting, ControlNet conditioning, LoRA and Hypernetwork loading, ESRGAN upscaling, area composition, model merging, and GLIGEN spatial control without writing code. The execution engine implements asynchronous queue processing with partial graph re-execution, running only changed nodes between iterations, and smart VRAM management that offloads models on GPUs with as little as 1 GB of memory. API nodes optionally connect to closed-source models through Comfy API while the core runs fully offline. Reusable subgraphs and App Mode expose complex workflows as simplified interfaces for non-technical users. The V3 custom node schema enables stateless execution with async support and process isolation. The TypeScript and Vue frontend ships as a PyPI package with stable releases every two weeks. Workflows save as JSON and embed in generated PNG, WebP, and FLAC files for reproducibility. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. GPL v3.0 licensed.

With over 110,000 GitHub stars and one of the fastest-growing open-source communities in the self-hosted space, Immich delivers a Google Photos-grade experience entirely on your own hardware. The platform handles automatic background backup from Android and iOS devices, deduplication, and support for RAW formats, LivePhotos, and MotionPhotos. Its machine learning pipeline runs facial recognition and clustering locally on your server, enabling you to group photos by person without sending a single image to the cloud. CLIP-based semantic search lets you find images by describing their content in natural language, while metadata-driven search covers EXIF data, dates, and locations. The web interface built with SvelteKit provides a responsive timeline view, albums, shared albums with configurable permissions, public sharing links with optional passwords and expiry dates, partner sharing for family libraries, and a global map plotting photos by GPS coordinates. Administrative features include multi-user support with per-user storage quotas, OAuth integration, API key management, and a user-defined storage structure for organizing files on disk. The architecture uses PostgreSQL for metadata, Redis with BullMQ for background job queues handling thumbnail generation, video transcoding, and smart search indexing, and exposes over 400 REST API endpoints documented via OpenAPI with auto-generated SDKs for web, mobile, and CLI clients. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. AGPL-3.0 licensed.

With over 107,000 GitHub stars and adoption by teams at Mozilla, 1Password, Peerlist, and thousands of startups, Supabase has become the most widely deployed open-source Firebase alternative — built entirely on PostgreSQL rather than a proprietary NoSQL store. Every project provisions a dedicated Postgres database with 40+ preinstalled extensions, auto-generating REST APIs via PostgREST, GraphQL via pg_graphql, and real-time change streams via an Elixir-based WebSocket engine that supports database change listeners, user presence tracking, and arbitrary broadcast messaging. Authentication covers email and password, phone OTP, magic links, and 20+ social providers including Google, GitHub, Apple, Azure, and SAML SSO, all enforced through Postgres Row Level Security policies that run inside the database itself. S3-compatible object storage delivers files through a CDN spanning 285+ cities with on-the-fly image transformations powered by imgproxy. Edge Functions run globally distributed TypeScript on the Deno runtime with Node.js compatibility and access to over two million NPM packages. The pgvector extension stores, indexes, and queries vector embeddings for AI-powered semantic search and retrieval-augmented generation workflows. Supabase Studio provides a browser-based dashboard with a table editor, SQL editor, schema visualizer, and log explorer. Official client SDKs ship for JavaScript, Python, Flutter, Swift, Kotlin, C#, Go, and Ruby. The self-hosted Docker Compose stack runs fourteen coordinated services including Kong API gateway, Supavisor connection pooler, and Logflare analytics. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. Apache 2.0 licensed.

With over 84,000 GitHub stars since its April 2026 launch, Open Design has emerged as the definitive open-source alternative to Anthropic's Claude Design. Rather than shipping its own language model, Open Design acts as an agent-agnostic design orchestration layer that auto-detects 25+ coding CLI executables on your PATH — including Claude Code, Codex, Cursor, Gemini CLI, OpenCode, Qwen, GitHub Copilot CLI, Hermes, and Kimi — or connects to any OpenAI-compatible endpoint via its built-in BYOK proxy at /api/proxy/stream. The platform introduces a file-based protocol where SKILL.md files define composable design workflows and DESIGN.md files establish version-controlled brand systems, currently shipping 31 first-party skills and 72 brand-grade design systems. Output spans web and mobile prototypes, live dashboards, presentation decks, raster images, video, and HyperFrames motion graphics, with export pipelines for HTML, PDF, PPTX, MP4, and ZIP. The daemon architecture uses SQLite for project state and serves a sandboxed iframe preview renderer with vendored React and Babel for JSX artifacts. Deployment options include the native desktop app for macOS, Windows, and Linux, local daemon mode via pnpm tools-dev, a single-container Docker Compose path serving both API and Next.js frontend on port 7456, and Vercel deployment for the web layer. On RepoCloud, deploy Open Design on a dedicated VPS with full root SSH access, persistent storage for your design systems and generated artifacts, and complete control over which AI providers and agent CLIs your instance connects to, all under the Apache-2.0 license.

Adobe Acrobat and Smallpdf, answered by a self-hosted Java web application: Stirling PDF processes every file with its 60+ tools on your own server and deletes it after the task completes. Nothing is uploaded to a third party, which is the whole point for contracts, invoices, and medical records. The toolbox covers page operations (merge, split at page numbers or scanned dividers, rotate, reorder, crop, extract), conversion in both directions between PDF and Word, Excel, PowerPoint, images, HTML, and Markdown, OCR that turns scans into searchable PDFs via Tesseract/OCRmyPDF (including PDF/A archival conversion), and security tools for passwords, permissions, watermarks, signatures, and true UI-driven text redaction. A built-in viewer handles annotation, drawing, and text or image insertion, and V2 added stateful processing - upload once, chain multiple tools - plus undo/redo history. For automation, nearly every tool has a REST API endpoint, no-code pipelines combine operations into custom logic chains, and watched folders process files automatically. Enterprise deployments get SSO, user management, and audit logging; the interface ships in 40+ languages. With 84K+ GitHub stars it is the most popular PDF tool in self-hosting, replacing $20/month Acrobat subscriptions with flat infrastructure cost.

Sixty-thousand-plus GitHub stars make Uptime Kuma the most popular self-hosted monitoring tool - MIT-licensed, Node.js, and the standard replacement for UptimeRobot, Pingdom, and Freshping. It watches a dozen monitor types: HTTP(S) endpoints with keyword and JSON-query content validation, TCP ports, ICMP ping, DNS records, WebSockets, Docker containers via the socket, Steam game servers, MQTT brokers, gRPC services, and push-based heartbeats for cron jobs and internal workers. Checks run at intervals as tight as 20 seconds - versus UptimeRobot's 5-minute free tier - with unlimited monitors and unlimited data retention. When something fails, alerts fan out through 90+ notification channels: Slack, Discord, Telegram, email with LiquidJS templating, PagerDuty, OpsGenie, ntfy, Gotify, Matrix, and dozens more via native providers plus the Apprise library. Unlimited public or password-protected status pages - mappable to specific domains and organized into monitor groups - communicate health to customers, with maintenance windows that suppress alerts during planned work. The reactive dashboard graphs response times, tracks SSL certificate expiry with advance warnings, supports proxies and 2FA, and ships in dozens of languages. One Docker container with a SQLite volume covers an entire infrastructure.

RAGFlow has established itself as one of the most widely adopted open-source RAG engines available, powering production AI systems that demand traceable, hallucination-free answers from complex enterprise data. The platform processes PDF, DOCX, Excel, and PPT files through vision-based deep document understanding with layout analysis and OCR, extracting structured knowledge from tables, charts, and images that simpler parsers miss entirely. RAGFlow's hybrid retrieval pipeline combines vector search with BM25 keyword matching and multi-stage reranking across configurable document stores including Elasticsearch, InfiniFlow's Infinity engine, OpenSearch, and OceanBase. Developers connect any combination of LLM providers — OpenAI, DeepSeek, Anthropic Claude, Google Gemini, and locally-hosted models via Ollama — through a unified configuration layer. The visual agent workflow system enables multi-step reasoning chains with persistent memory, tool calling, and pre-built templates for common enterprise scenarios. RAGFlow synchronizes data from Confluence, S3, Notion, and Google Drive, and delivers answers through chat integrations with Feishu, Discord, Telegram, and Line. The Python SDK and RESTful API on port 9380 provide programmatic access to knowledge base management, document parsing, and conversational retrieval. The full stack deploys via Docker Compose with MySQL for metadata, Redis for task orchestration, and MinIO for object storage. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. Apache 2.0 licensed.

Thirteen-plus LLM providers, one unified client: NextChat (formerly ChatGPT-Next-Web) is an open-source AI chat interface built on Next.js that spans OpenAI GPT-4, Anthropic Claude, Google Gemini, DeepSeek, Groq, Azure endpoints, and self-hosted backends like Ollama, LocalAI, and RWKV-Runner. Its defining trait is minimalism - the first screen loads in about 100 KB, the desktop client is roughly 5 MB, and there is no database or user system to operate; chat history lives locally in the browser with optional WebDAV or UpStash Redis sync. The Mask system saves reusable prompt-template personas you can share and debug, long conversations auto-compress to fit context windows, and Markdown rendering covers LaTeX, Mermaid diagrams, and code highlighting with streaming responses. Plugins add web search and calculators, MCP support enables external tool calling, and Artifacts previews generated content in a separate pane. Ships as a web app, Docker image, and Tauri desktop builds for Windows, macOS, and Linux, translated into 20+ languages. MIT-licensed.