Authentication that lives inside your application rather than behind a redirect to an external identity provider - SuperTokens takes a fundamentally different architecture from Auth0 and AWS Cognito. Three tiers make that work - frontend SDKs (React, Angular, Vue, vanilla JS, React Native) render overridable login UI and manage tokens; backend SDKs (Node.js, Python, Go) expose auth endpoints on your own API domain; and SuperTokens Core, the piece you host here, is the stateless HTTP service handling core auth logic, password hashing, token signing, and database operations against PostgreSQL. The recipe system keeps features decoupled: use email/password, social login, passwordless (magic links, OTP), phone-password, multi-factor authentication (TOTP, WebAuthn), user roles, and microservice auth - individually or combined; you can even use SuperTokens purely for session management alongside another login provider. Sessions are where it shines: rotating refresh tokens with theft detection, automatic access-token refresh, CSRF protection, and secure cookie handling out of the box - the details that become vulnerabilities when hand-rolled. Verification happens locally in your backend via cached JWT signing keys, so the Core stays off the hot path. Self-hosted means no user limits, free forever, with all user data in your database. Apache-licensed.

Backed by the Linux Foundation with contributions from AWS, Cisco, IBM, Microsoft, Red Hat, and Shell, Agentgateway is the first data plane built from the ground up for AI agent workloads — providing a unified Rust-based proxy that handles conventional HTTP and gRPC traffic alongside MCP tool servers, A2A agent communication, and LLM inference endpoints through a single deployment. The LLM gateway routes requests to OpenAI, Anthropic, Gemini, AWS Bedrock, and other providers through an OpenAI-compatible unified API with per-tenant budget controls, spend tracking, prompt enrichment, load balancing across multiple model endpoints, and automatic failover when providers experience outages. The MCP gateway federates multiple tool servers behind one endpoint, supporting stdio, HTTP/SSE, and Streamable HTTP transports with built-in OAuth authentication compliant with the MCP auth specification, integrating Auth0 and Keycloak out of the box. OpenAPI integration exposes existing REST APIs as MCP-native tools without code changes, enabling legacy services to participate in agent workflows. Policy-based RBAC controls which agents access which tools, while OpenTelemetry integration provides distributed tracing across agent communication chains. Deploy as a standalone binary with flat YAML configuration or on Kubernetes using the built-in controller with Gateway API support for declarative infrastructure-as-code management. 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 nearly 9,000 GitHub stars and adoption by over 60,000 companies across 100 countries, Papermark is the open-source DocSend alternative that turns document sharing into a data-rich conversation between you and your viewers. Every shared document generates page-by-page analytics showing exactly which pages capture attention, how long viewers spend on each section, where they drop off, and whether they return for a second look, with real-time notifications the moment a document is opened. Virtual data rooms support unlimited folders with drag-and-drop organization, bulk uploads, granular per-viewer permissions, dynamic watermarking that stamps each page with the viewer's identity, and NDA gating that requires agreement before access. Custom branding applies your logo, colors, and custom domain to every shared link and download page, while email verification and password protection add authentication layers. The AI Data Room Copilot lets viewers chat with uploaded documents, ask questions, and receive contextual summaries directly within the data room interface. The developer platform exposes 43 REST API operations covering data rooms, documents, folders, links, visitors, and analytics, with an MCP server for AI agent integration and a CLI for automation. Built on Next.js with TypeScript, Prisma ORM, PostgreSQL, NextAuth.js authentication, and shadcn/ui components. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. AGPLv3 licensed.

Created by the developer behind Uptime Kuma and carrying over 23,000 GitHub stars, Dockge brings the same clean, reactive design philosophy to Docker Compose stack management with a web interface that makes Portainer's compose handling feel like editing YAML in a terminal over SSH. The interactive editor provides syntax highlighting, inline validation, and a live preview of your compose.yaml files while keeping every stack stored as a standard file on disk in /opt/stacks by default, meaning you can seamlessly switch between the web UI and the docker compose CLI without lock-in or proprietary database formats. Real-time WebSocket updates stream pull progress, container start/stop transitions, and build output directly to the browser with no polling delays. The built-in web terminal opens a shell session inside any running container for quick debugging, while the docker-run-to-compose converter transforms single-container run commands into proper compose.yaml definitions with one click. Multi-agent support introduced in version 1.4.0 connects multiple Docker hosts to a single Dockge dashboard, enabling centralized management of stacks distributed across different servers. Image update detection shows which stacks have newer versions available, and one-click updates pull the latest images and recreate containers without manual intervention. The stack is a single Docker container running on Node.js with Socket.IO for reactivity and stores no external database. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Personal, minimalist, database-free bookmarking - Shaarli is a philosophy as much as an app. Everything lives in a single compressed datastore file inside data/: no MySQL, no PostgreSQL, backup by copying one directory. That write-once/read-many file is usually served straight from OS disk caches, which is why a decade-old Shaarli instance with tens of thousands of links still responds instantly. Designed deliberately single-user, it saves URL, title, unlimited-length description, and tags (with autocomplete, renaming, and merging), marks entries public or private, and automatically strips utm_source and fb tracking parameters from saved URLs. That description field is why the community uses Shaarli as far more than bookmarks: a microblog, read-it-later queue, code-snippet base, pastebin, and shared clipboard between machines. Sharing is one click via bookmarklet or Android apps; consumption is per-tag RSS/Atom feeds plus a daily digest feed; search is full-text with tag filtering. A REST API opens it to any client, a plugin and theme system extends the PHP core (Markdown rendering, thumbnails), and import/export uses browser-standard Netscape HTML - your data enters and leaves freely. LDAP login is supported, no telemetry is sent anywhere, and the UI degrades gracefully without JavaScript. The anti-cloud Delicious.

Prototype multi-agent AI systems without writing orchestration code: AutoGen Studio is Microsoft's low-code interface over the AutoGen AgentChat framework. You compose teams of LLM-powered agents in a visual Team Builder, either by drag-and-drop from a component library or by editing the declarative JSON specification directly. Each agent gets a model, a prompt, tools (Python functions), and the team gets termination conditions and an orchestration pattern, sequential or LLM-driven. The Playground runs teams interactively with live message streaming between agents, a visual control-transition graph, tool-call and code-execution tracking, and pause/stop controls, which makes it a practical debugger for agent behavior. Finished teams export as JSON for use in any Python application via the TeamManager class, or serve as an API endpoint. Any OpenAI-compatible model endpoint works, including local servers like Ollama or vLLM. Microsoft labels it a research prototype: use it for prototyping and evaluation, and build production systems on the underlying AutoGen framework.

With over 15,900 GitHub stars and 40,000 weekly npm downloads in its first two months, OpenWiki from LangChain has rapidly become the standard for AI-generated codebase documentation. Built on the Deep Agents framework, it deploys a documentation agent that reads your repository's source code, tests, and configuration, then synthesizes a complete linked Markdown wiki with architecture overviews, integration guides, data-flow diagrams, and validated Mermaid visualizations. Two operating modes cover distinct workflows: code mode generates repository documentation in an openwiki/ folder with automatic AGENTS.md and CLAUDE.md integration for Codex, Claude Code, OpenCode, and Cursor, while personal mode builds a local knowledge base from nine connectors including Notion, Slack, Gmail, X/Twitter, Hacker News, LangSmith, Custom MCP, Web Search, and local git repositories. Thirteen model providers are supported out of the box — OpenAI, Anthropic, Gemini, AWS Bedrock, GitHub Copilot, OpenRouter, Nebius, Fireworks, Baseten, NVIDIA NIM, and any OpenAI-compatible endpoint like Ollama or LM Studio. Grounded Claims track every material assertion back to versioned source evidence, flagging stale propositions before they propagate. The interactive visualizer renders wiki pages as an explorable node graph with a side-by-side Markdown reader, exportable as a static site for GitHub Pages or MkDocs. Self-updating CI workflows via GitHub Actions, GitLab CI, or Bitbucket Pipelines open documentation PRs automatically when code changes. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Its author, a student and WakaTime fan, didn't want to pay $9/month for data about his own keystrokes - so Wakapi was born, a self-hosted, WakaTime-compatible backend for coding statistics. The compatibility is the killer design decision: the official WakaTime plugins for VS Code, JetBrains IDEs, Vim, and dozens of other editors work unmodified - just point the plugin's API URL at your Wakapi instance with your personal key, and heartbeats flow to your server instead of a third party's. Duration inference matches WakaTime's own algorithm, with a configurable timeout (10 minutes by default). From that stream Wakapi builds statistics and plots across projects, languages, editors, hosts, and operating systems, plus the fun extras: public leaderboards (optionally login-gated, with configurable aggregation windows), badges for GitHub readmes, and weekly email reports. A REST API serves your data programmatically, Prometheus export feeds your existing Grafana, and a WakaTime relay mode can mirror heartbeats to both services during migration - with one-click import of historical WakaTime data. Written in Go, it is lightning fast and light enough for the smallest instance, storing to SQLite, PostgreSQL, or MySQL, with configurable data retention for GDPR peace of mind. Deliberately smaller than WakaTime, deliberately yours.

Staying on top of hundreds of RSS feeds is impossible when every reader just dumps articles in chronological order. RSSMonster takes a different approach: it evaluates, scores, and prioritizes every article so the signal rises above the noise. The three-pane reading interface automatically marks articles as read when you scroll past them, while the built-in quality scoring engine rates content by freshness, originality, trust, and attention metrics. Compose advanced search expressions using field operators like star:true, quality:>0.6, hot:true, and date filters like @today or @lastweek, then save those expressions as persistent Smart Folders for one-click access to curated views. Semantic event clustering groups related articles across sources so you see one coherent story instead of fifteen duplicates. Connect your favorite mobile client through the Fever API (supporting Reeder for iOS) or the Google Reader API (compatible with News+, FeedMe, Vienna RSS, and ReadKit). The AI chat assistant powered by the Model Context Protocol lets you ask questions about your feed content and get summarized answers. Import your existing subscriptions via OPML, switch between light and dark themes, and install the app as a Progressive Web App for offline reading. On RepoCloud, deploy RSSMonster on a dedicated VPS with root SSH access, full data ownership, and persistent storage under the MIT license.

GPT Load has become the go-to self-hosted AI gateway for teams managing multiple LLM provider credentials behind a single URL. The Go-built proxy transparently preserves native API formats for OpenAI Chat Completions, OpenAI Responses, Anthropic Messages, and Google Gemini — applications swap one base URL and keep their existing SDK integration untouched. Twenty built-in channels cover official APIs (OpenAI, Anthropic, Gemini, xAI), cloud platforms (Azure OpenAI, AWS Bedrock, Google Vertex AI), model services (DeepSeek, Moonshot AI, SiliconFlow, Zhipu AI, Alibaba Cloud, Volcengine, OpenRouter, Groq), and subscription accounts (Codex, Claude, Antigravity, Grok) using the same credential management, scheduling, and health system. The intelligent key pool rotates among valid credentials using atomic counters for fair high-concurrency distribution, automatically blacklists failing keys after configurable thresholds, and recovers them via scheduled health checks — all transparent to clients. Weighted load balancing distributes traffic across multiple upstream endpoints while per-credential proxies route individual keys through different egress paths. The Vue 3 management dashboard provides real-time statistics, group configuration, key testing, request logs with full debugging context, per-model cost estimates, and route inspection. Docker deployment exposes the management interface and proxy on port 3001 with SQLite by default, MySQL or PostgreSQL optional, and Redis for distributed leader-follower cluster scaling. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

BitRouter is a context-aware LLM router that learns which model delivers the cheapest successful outcome per workflow step, cutting agent costs by up to 80% while maintaining 96% quality versus all-frontier baselines. Point any agent runtime at http://localhost:4356 with a one-line OPENAI_BASE_URL change and BitRouter routes to OpenAI, Anthropic, Google, Groq, DeepSeek, Mistral, Moonshot, MiniMax, Nvidia, and any OpenAI-compatible endpoint simultaneously, normalizing authentication, streaming, and cross-protocol translation between wire formats. The act-observe-evaluate-learn loop traces every hop with cost, tokens, and latency attribution, scores each decision against a versioned policy-lock.yaml, then tightens routes automatically with no LLM judge in the path. Native MCP gateway auto-discovers tools from connected servers and makes them routable and governed alongside model calls. Agent Client Protocol integration enables the TUI to manage Claude Code, Codex, OpenCode, OpenClaw, Gemini, and Copilot sessions in real time with inline tool-call approval and live streaming. Built-in guardrails inspect, redact, or block risky content before requests leave your network. Virtual keys scope API access per agent or user without exposing upstream credentials. Per-agent spend caps and loop guards contain runaway cost automatically. Multi-account failover reroutes mid-run so rate limits never re-pay completed work. Ships as a single Rust binary via npm or Cargo. 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.

DataHub maps your entire data ecosystem into a searchable, governed catalog where every table, pipeline, dashboard, and metric is discoverable and traceable from source to consumer. Originally built at LinkedIn to manage metadata at hyperscale and proven to handle 10 million+ assets and billions of relationships in production, the platform is now trusted by 3,000+ organizations including Netflix, Visa, Slack, and Pinterest. The Spring Java backend (GMS) exposes both GraphQL and OpenAPI REST endpoints, while the React frontend delivers an intuitive interface for searching, browsing, and governing data assets. The Python-based ingestion framework provides 80+ production-grade connectors extracting deep metadata from Snowflake, BigQuery, Redshift, Databricks, dbt, Airflow, Spark, Kafka, Looker, Tableau, Power BI, Superset, PostgreSQL, MySQL, Hive, Glue, S3, Iceberg, and Unity Catalog through pull-based scheduled crawls and push-based emission via Python and Java SDKs. Automatic table-level and column-level lineage detection uses SQL parsing with 97-99% accuracy, tracing data flows from ingestion pipelines through warehouses to BI dashboards. Real-time metadata streaming via Kafka keeps the catalog continuously synchronized as schemas evolve and pipelines execute. The governance layer provides business glossary management, tag propagation along lineage graphs, domain-based organization, and fine-grained access control policies. DataHub Actions triggers automated responses to metadata changes, enabling notifications, quality checks, and downstream workflows. Elasticsearch powers full-text search with faceted filtering across entities. 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.

Named from the German "Ich schrei sonst" - roughly "or I'll scream" - Isso is a lightweight Python/JavaScript commenting server, a drop-in Disqus replacement for people who noticed what Disqus does to reader privacy and page load times. The design premise is printed right in the docs: comments are not Big Data. So the backend is a single SQLite file rather than a database cluster, and the entire client is one embeddable JavaScript file - 65 kB, 20 kB gzipped - that you drop into any static site, blog, or CMS. Commenters write in Markdown, need no account, and can edit or delete their own comments within a configurable window (15 minutes by default). Spam control comes from an optional moderation queue: held comments stay invisible until you activate them via an admin interface or email notification links. Migration is a first-class feature, with importers for Disqus and WordPress exports, so years of existing threads move over intact. Because everything is server-rendered from your own instance, no third party tracks your readers, and real-world switchers report smaller pages and faster loads than the Disqus embed. MIT-licensed, running since 2012.

Upload files, get a share link, let it expire: PsiTransfer is a self-hosted WeTransfer with no accounts, no logins, and no third-party cloud with size caps and metadata harvesting. The engineering focus is large files over imperfect networks. Uploads use the tus.io resumable protocol, so a dropped connection on a multi-gigabyte video resumes exactly where it stopped once you're back online; downloads support HTTP range headers for the same resilience, and everything streams, so file size is bounded by your disk rather than memory. Files organize into upload buckets with retention you control: expire after a set time (up to weeks) or after a one-time download, with automatic cleanup when links lapse. Recipients need nothing installed - they open the link, preview files in modal views, and grab everything as a zip or tar.gz archive with one click. Buckets can be password-protected (AES-encrypted download lists), and security-through-obscurity is done properly: bucket URLs use hashed UUID tokens and stored filenames are replaced with UUIDs. An optional admin page (enabled by setting an admin password) lists bucket information and storage. The Vue.js frontend ships under 100 KB gzipped and is fully responsive. Honest caveat from the author: no end-to-end payload encryption yet. BSD-licensed, Docker-ready.

The first open-source substrate for enterprise knowledge engineering that learns passively and governs itself. The Rust-built backend paired with PostgreSQL and pgvector delivers a bitemporal knowledge graph where every fact carries two timelines: when it held in the real world and when the system came to believe it — enabling full audit trail replay of how understanding evolved. Document ingestion handles PDF, DOCX, PPTX, XLSX, CSV, Markdown, HTML, and plain text with legacy encoding detection, while scheduled syncing pulls from web pages, RSS feeds, GitHub, Jira, Notion, WebDAV, and S3-compatible buckets. Search fuses Tantivy full-text indexing with pgvector semantic vectors using Reciprocal Rank Fusion, streaming answers with inline citations that link directly to source passages. The built-in agent harness drives agentic RAG through conversation — searching documents, walking the knowledge graph at any historical date, and querying mounted databases via Ontology2SQL which achieves state-of-the-art results on BIRD Mini-Dev benchmarks. Five ontology packs ship inside the binary (schema.org, W3C Org, PROV-O, FOAF, IOF Core) with forward-chaining reasoning for transitivity, symmetry, inverses, and relation hierarchy. Entity resolution operates in three stages: exact name matching, embedding similarity, then model-based judgment with every merge reversible. Any OpenAI-compatible endpoint works including DeepSeek, Qwen, Ollama, and vLLM for fully air-gapped deployment. 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.

Describe a component in natural language and watch it render: OpenUI, from Weights & Biases, is an open alternative to Vercel's v0. Type a prompt like "a dark-themed dashboard with a sidebar and charts" and the LLM renders working HTML with Tailwind styling live in the browser. You then iterate conversationally, asking for changes until the design is right, and convert the result to React, Svelte, or Web Components for use in a real project. The backend is Python with LiteLLM routing, so it works with OpenAI, Anthropic, Gemini, Groq, and Mistral API keys, or fully offline against local Ollama models, including vision models like LLaVA that can generate UI from screenshot input - feed a screenshot and the model reproduces or riffs on an existing interface. Generated markup is inspectable at any point, with light and dark mode toggles, theme selection, and responsive previews across device sizes. The practical effect is compressing the mockup-review-revise loop from hours to minutes: a described layout renders in seconds and iterates through follow-up prompts, and because output converts to real framework code, prototypes feed directly into production codebases instead of staying trapped in a design tool. Self-hosting keeps unreleased product interfaces and prompts on your own server, and LiteLLM routing lets you pick the model per task - a cheap fast model for rough drafts, a stronger one for final passes, or free local models for unlimited experimentation.

Backed by nearly 30,000 GitHub stars and powering millions of meetings through meet.jit.si, Jitsi Meet is the open-source video conferencing platform that runs entirely in the browser with no plugins or downloads required. The WebRTC-based architecture delivers HD audio and video through the Jitsi Videobridge selective forwarding unit, while Prosody handles XMPP signaling and Jicofo manages conference focus and orechestration. End-to-end encryption uses AES-GCM 128-bit keys exchanged via the Olm protocol, protecting audio, video, and screen sharing through the Insertable Streams API in Chromium-based browsers. Moderators can split participants into breakout rooms with individual password protection, enable lobby waiting rooms for admission control, set meeting passwords, and track speaker statistics with per-participant talk time metrics. Virtual backgrounds leverage TensorFlow.js body segmentation with WebGPU and WebGL acceleration, automatically adapting quality through device tier detection. Server-side recording and YouTube live streaming run through Jibri, while Jigasi provides a SIP gateway for PSTN dial-in and speech-to-text transcription. The platform includes in-meeting chat with private conversations, polls, raise-hand functionality, emoji reactions, and tile and speaker view layouts. Mobile applications for iOS and Android complement the web client, and both web and native SDKs enable embedding video conferences into custom applications. 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.

MateClaw delivers a multi-agent AI platform where digital employees run as persistent team members with roles, goals, and accumulated skills rather than stateless chat completions. The Spring Boot backend on Spring AI Alibaba provides ReAct iterative reasoning and Plan-and-Execute decomposition on a StateGraph runtime, with parallel delegation between employees and dynamic context pruning for multi-step tasks. Five career templates ship ready (Product Researcher, Customer Support, Knowledge Curator, Data Analyst, Executive Assistant) while custom employees inherit configurable backstories, pixel-art avatars, and dedicated tool bindings. The MCP integration supports stdio, SSE, and Streamable HTTP transports with per-employee tool isolation preventing capability bleed between agents. ACP bridges bring Claude Code, Codex, and other coding agents in as first-class employees. Workflow orchestration composes multiple employees and system actions into publishable linear DSL processes with seven step modes: sequential, fan_out, collect, conditional, await_approval, dispatch_channel, and write_memory. The trigger system wires cron schedules, webhooks, channel messages, employee lifecycle events, content matches, and workflow completions to automated flows. The Admin Runtime Console provides real-time visibility into running employees with token usage tracking and one-click force-recycle. Spring Boot Actuator monitoring, full audit trail, and per-channel error isolation deliver production-grade reliability. 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.