Backed by Y Combinator and trusted by over 2,300 companies processing billions of observations monthly, Langfuse is the most widely adopted open-source platform for building, monitoring, evaluating, and debugging LLM applications. The hierarchical tracing engine captures every LLM call, tool invocation, retrieval step, and agent action as nested spans based on OpenTelemetry, with automatic cost calculation, latency tracking, and token usage attribution across sessions and users. Prompt Management separates prompts from code with versioned artifacts, label-based deployments, one-click rollbacks, and runtime SDK fetching with server-side caching, while linking every generation back to its exact prompt version for attribution analytics. The evaluation system supports LLM-as-a-judge scoring, heuristic code evaluators, user feedback collection, and manual annotation workflows that run automatically on production traces or against curated datasets. The Playground enables interactive prompt testing on real production inputs with side-by-side model comparison across providers. Datasets and Experiments define test cases for systematic benchmarking with comparative result visualization. Native SDKs for Python and TypeScript provide decorator-based instrumentation, while 100+ integrations cover LangChain, LlamaIndex, OpenAI SDK, LiteLLM, Vercel AI SDK, and any OpenTelemetry-instrumented framework. The analytics dashboard surfaces cost breakdowns, quality scores, latency percentiles, and usage trends across models and prompt versions. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Designed as a unified personal AI workstation, QwenPaw operates as an autonomous digital copilot that coordinates scheduled automations, interactive coding sessions, and multi-channel team communication across everyday messaging apps. Users can dispatch long-running research tasks, process office documents including PDF, Excel, and Word files, and execute browser-based data collection without manual intervention. The built-in web console and terminal interface provide full visibility into agent reasoning, allowing operators to inspect intermediate thinking steps, review proposed file edits, and approve sensitive tool calls. Through direct connectors for Discord, Telegram, DingTalk, Lark, and WeChat, teams can trigger specialized skills or query shared workspaces directly from their existing group channels. A self-evolving personal memory system continuously indexes chat interactions and local resources into editable Markdown files, ensuring knowledge persists across restarts and task delegations. Built-in guardrails including a sandboxed execution runtime, tool access policies, and automated skill scanners protect underlying host files from unauthorized modifications during autonomous scripting runs. 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 15,500 GitHub stars and over 1,100 forks, Plandex delivers a terminal-based AI coding agent purpose-built for the complex, multi-file tasks that overwhelm single-file AI assistants. The Go-powered server maintains a cumulative diff review sandbox that quarantines all AI-generated changes from your project files until you explicitly approve them — enabling 20-file refactors where you cherry-pick good changes and reject bad ones without touching git. A 2M token effective context window loads only what each step requires, while tree-sitter project maps index repositories exceeding 20M tokens across 30+ programming languages, providing structural awareness of class hierarchies, function signatures, and import graphs without burning tokens on full file content. The configurable model pack system assigns different models to different roles — Claude for planning, GPT for coding, Gemini for summarization — supporting Anthropic, OpenAI, Google, OpenRouter, Azure OpenAI, AWS Bedrock, DeepSeek, Perplexity, and Ollama for local models. Full auto mode handles end-to-end autonomous workflows including high-level planning, context loading, implementation, terminal command execution, and automated debugging of both terminal and browser applications. The interactive REPL provides fuzzy auto-complete, version-controlled sandbox branching, rewind to any previous point, and Git integration for commit message generation. The Plandex Server exposes 60+ REST API endpoints for programmatic orchestration across organizations, projects, plans, and branches. Deploy via Docker Compose for self-hosted operation with your own API keys. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Machine translation with no Google, no Azure, no per-character billing, and no text leaving your infrastructure: LibreTranslate is a free, open-source translation API that runs entirely on your own server. The engine underneath is Argos Translate, which runs OpenNMT neural models with SentencePiece tokenization and Stanza sentence-boundary detection, all offline. Models install as portable .argosmodel packages covering dozens of languages - English, Spanish, French, German, Chinese, Japanese, Russian, Arabic, Hindi, Portuguese, and many more - and Argos handles automatic pivoting: with es-to-en and en-to-fr installed, it chains them to translate es-to-fr without a direct model. The API is a straightforward HTTP POST to /translate with source and target language codes, returning JSON - simple enough that the ecosystem has clients in every major language and integrations across tools like Weblate and Mastodon. Beyond plain text it translates HTML while preserving markup and handles whole file uploads (documents in, translated documents out), plus automatic language detection when the source is unknown. A clean bundled web UI serves interactive translation for end users, and optional API keys with rate limits control access. AGPL-licensed and trainable with custom models, it is the standard answer when translation must be private, unmetered, and self-contained - GDPR-sensitive text never touches a third party.

Cognee gives AI agents persistent long-term memory that survives across sessions, replacing the traditional stack of separate graph, vector, and session databases with a unified engine running on a single PostgreSQL instance. The memory-native API exposes four verbs (remember, recall, forget, and improve) enabling agents to persist context, retrieve cited answers, prune outdated knowledge, and self-improve from feedback. Under the hood, Cognee combines pgvector embeddings with a PostgreSQL-native graph store and cognitive-science-grounded ontology generation, delivering hybrid retrieval that fuses semantic similarity, structural graph traversal, and lexical search in a single query. Integrations span Claude Code, Cursor, LangGraph, OpenAI Agents, and any MCP-compatible client through a dedicated MCP server on port 8001, while the Python and TypeScript SDKs provide direct programmatic access. The platform supports swappable backends including Neo4j, FalkorDB, Qdrant, ChromaDB, Weaviate, Milvus, and LanceDB for teams with existing infrastructure. Built-in OpenTelemetry tracing, an experimental dashboard with knowledge graph visualization, multi-tenant user isolation, and audit trails ensure production readiness. Deploy via Docker Compose with optional profiles for PostgreSQL, Neo4j, Redis, and the web frontend. Reached v1.0 in April 2026 with 30,000+ stars. 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.

Teams tired of paying Salesforce or HubSpot per seat run EspoCRM: an AGPL-licensed PHP application with a fast single-page frontend over a REST API, covering sales, support, and marketing in one uncluttered interface. The sales core is complete - leads, contacts, accounts, opportunities with customizable pipeline stages, kanban views, calendars, meetings, and calls. Email is deeply integrated rather than bolted on: IMAP sync links messages to CRM records automatically, and mass email campaigns run with reusable templates, tracking, and Web-to-Lead forms feeding the funnel. Support teams get case management and a customer portal where clients track their own tickets and access a knowledge base. The real differentiator is the Entity Manager: create custom entities, fields, relationships, and layouts from the admin UI without code, with dynamic logic showing or hiding fields conditionally - EspoCRM is as much a business-application platform as a CRM. Formula scripting handles calculated fields and record automation in the free core; the optional Advanced Pack adds visual BPM process design and workflow rules. Role-based permissions with team and territory scoping, full-text search, reports, and a straightforward REST API for n8n or custom integrations round it out. Runs on PHP 8.3+ with MySQL, MariaDB, or PostgreSQL - unlimited users, zero per-seat fees.

With over 7,500 GitHub stars and 140 contributors, Matterbridge is the Go-powered chat bridge that connects over 20 messaging platforms through a single TOML configuration file, letting teams communicate across platform boundaries without forcing anyone to switch applications. The gateway architecture routes messages bidirectionally between any combination of Discord, Slack, Telegram, Matrix, IRC, Mattermost, Microsoft Teams, XMPP, Rocket.Chat, Nextcloud Talk, Keybase, Mumble, Twitch, WhatsApp, VK, Gitter, Zulip, ssh-chat, and Harmony, with transparent username and avatar spoofing so bridged messages appear native on each platform. Message edits and deletes propagate across bridges, file attachments and inline images transfer between protocols, threading and reply context is preserved where platforms support it, and private group bridging enables confidential cross-platform conversations. Multiple independent gateways can run simultaneously, each bridging different channel sets with different protocol combinations. The REST API enables third-party integrations and custom bridges without modifying the Matterbridge codebase, while the tengo scripting engine allows inline message transformation and filtering. Game chat support bridges Minecraft and Counter-Strike server chat into messaging platforms. Deployment runs as a single static Go binary with zero dependencies, or as the official Docker image with the configuration file mounted as a volume. 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.

OpenViking is a self-hosted context database that gives AI agents persistent, structured memory by organizing knowledge, skills, and session history into a hierarchical virtual filesystem accessible through the viking:// URI protocol. Instead of dumping everything into a flat vector store and hoping semantic search finds the right chunks, agents navigate their context with familiar commands like ls, tree, and find, locating exactly the information they need through deterministic paths combined with semantic search. Every resource is automatically processed into three layers: a 100-token L0 abstract for quick filtering, a 2,000-token L1 overview for content navigation, and the full L2 detail loaded only when confirmed necessary. This tiered approach cuts token consumption by 83 to 96 percent compared to conventional RAG while improving task completion rates by 15 to 49 percent on benchmark tests. The built-in memory self-iteration loop automatically analyzes task execution and user feedback, updating agent memory directories so the system continuously learns and improves. You can connect to any LLM provider, including Ollama for fully local inference, OpenAI, or compatible gateways. The Web Studio UI at the /studio endpoint provides visual browsing of the entire context filesystem, and the REST API on port 1933 supports programmatic access. Deploy via Docker, Kubernetes with the included Helm chart, or as a standalone service. 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.

Ralph tracks thousands of assets across data centers and back offices through a unified CMDB, DCIM, and asset management platform, providing the same capabilities as ServiceNow, Device42, and Sunbird dcTrack without per-asset licensing fees. Used by Allegro in production and backed by over 2,500 GitHub stars, it is built on Python 3 with Django and Django REST Framework. Interactive data center floor plans support drag-and-drop rack placement, front and rear rack views showing U-level asset positioning, power consumption tracking per PDU, and ethernet and fiber connection mapping. The back office module manages laptops, desktops, printers, mobile phones, and accessories with user assignment tracking, warehouse inventory, stock-taking audits, and automated loan workflows. IP address management handles network environments with DHCP and DNS integration alongside network topology visualization. Software license tracking monitors per-user and per-core allocations with usage calculations, compliance reporting, and expiration alerts, while vendor support contracts track SLA agreements and warranty renewal dates. The transitions system automates asset lifecycle processes through configurable workflows that trigger HTTP webhooks, custom Python scripts, email notifications, and Puppet and Ansible configuration management integration. Custom fields extend the data model with text, numbers, dates, choices, and URLs per asset type, accessible via the REST API. Multi-tenant architecture organizes assets by regions, data centers, service environments, and business units. Deploy via Docker with the allegro/ralph image alongside MySQL and Redis. 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.

Twitch and YouTube Live, replaced by infrastructure you control: Owncast is a self-hosted live streaming and chat server. Point OBS, Streamlabs, or any RTMP-capable broadcaster at the server's ingest port, and Owncast transcodes the feed with FFmpeg into HLS with multiple quality variants, playing it in a built-in web page with a real-time chat beside it. Chat supports anonymous participation, custom emotes, and moderation tools - message removal, user bans and suspensions - with optional authentication via IndieAuth or a Fediverse account. ActivityPub integration puts the stream on the Fediverse: viewers on Mastodon and compatible services can follow a channel and get notified the moment it goes live. Video delivery can come straight off the server or offload HLS segments to S3-compatible object storage so a modest VPS handles thousands of concurrent viewers while only managing ingest and chat. The backend is a single Go binary with a React frontend - no accounts platform, no database server, no dependency stack - and the player embeds in any website. MIT-licensed, with roughly 9k GitHub stars, zero platform fees, and no algorithm or takedown policy between you and your audience.

Most web links eventually break - the sobering statistic Shiori, a bookmark manager with archiving by default, is built on. Its answer is archiving by default - where possible, every bookmark you save gets a clean, readable offline copy parsed from the page, ads and navigation stripped, so the article survives even after the original URL dies. Conceived as a simple Pocket clone and written in Go, the entire server is a single binary using roughly 25-30 MB of RAM with SQLite out of the box (Postgres and MySQL supported) - genuinely the lightest archiving bookmark manager you can run. Saving is one click through the Firefox and Chrome extensions, and finding things again is where Shiori quietly outperforms its size: full-text search covers the archived page content, not just titles and tags, so you can find that article by a phrase you remember from paragraph six. Reader mode presents the cleaned text; archive mode shows the preserved page. It's dual-interface by design - a pretty web UI (installable as a PWA on mobile) and a complete CLI for terminal devotees - plus a REST API for scripting. Pocket imports work natively, and Netscape HTML handles browser imports and exports. Multi-user support included. MIT-licensed.

With over 14,000 GitHub stars, 1 million managed identities on Logto Cloud, and continuous releases through version 1.42.0 in July 2026, Logto has emerged as the most credible open-source alternative to Auth0, Clerk, and AWS Cognito by packaging OIDC, OAuth 2.1, enterprise SSO, multi-tenancy, and RBAC into a single MPL-2.0 codebase that self-hosts for free with no per-MAU pricing surprises. Every Logto tenant operates as a fully compliant OpenID Provider supporting PKCE-only public clients, DPoP token binding, and RFC 9068 JWT access tokens. Pre-built sign-in flows handle email, phone, social login via Google, Facebook, Azure AD, and dozens of connectors, passkey authentication, and multi-factor verification through TOTP and WebAuthn. Organizations enable first-class multi-tenancy where users belong to multiple tenants with per-organization RBAC scopes on API resources. Enterprise SSO connects to Okta, Entra ID, and any SAML or OIDC identity provider. SDKs for over 30 frameworks including React, Next.js, Angular, Vue, Flutter, Go, and Python integrate authentication into SPAs, web apps, mobile apps, APIs, machine-to-machine, and CLI tools. The admin console provides user management, audit logs, webhook event subscriptions, and custom domain configuration. Personal Access Tokens and token exchange support AI agent architectures and MCP server authentication. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MPL-2.0 licensed.

PrivateBin shares text and files with true zero-knowledge encryption: the server stores only ciphertext it cannot decrypt because the key exists exclusively in the URL fragment that never reaches the server. With over 8,400 GitHub stars and 500,000+ Docker pulls, it has become the standard for privacy-respecting paste sharing where not even the hosting operator can read stored content. All encryption uses 256-bit AES in Galois Counter mode performed entirely client-side in the browser. Burn-after-reading mode destroys pastes on first view, while configurable expiration timers automatically purge content after periods ranging from five minutes to forever. Optional password protection adds a second encryption layer requiring recipients to enter a passphrase before decryption occurs. Discussion threads enable anonymous or nickname-based commenting on pastes with IP-based identicon avatars for visual identity. Markdown rendering with live preview formats pastes as styled HTML, and syntax highlighting through prettify.js supports dozens of programming languages across four color themes. File upload support enables sharing images, PDFs, and media files with in-browser preview. QR code generation converts paste URLs for mobile device transfer. Customizable templates include Bootstrap 5, classic Bootstrap CSS, and Darkstrap themes. Storage backends support filesystem, MySQL, PostgreSQL, SQLite, Amazon S3, and Google Cloud Storage. Deploy via Docker with the privatebin/nginx-fpm-alpine image on port 8080. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. zlib licensed.

With over 21,000 GitHub stars and six years of steady development through version 3.1.0, Neko transforms any Docker container into a fully interactive browser or desktop environment streamed to web browsers via WebRTC with sub-300-millisecond glass-to-glass latency. The Go backend captures X server display frames using the Pion WebRTC library while the Vue.js frontend renders the remote session with native audio synchronization, delivering a significantly smoother experience than Apache Guacamole or noVNC which rely on image-over-WebSocket approaches. Multiple users simultaneously view and collaboratively control the same session with real-time input synchronization and host-managed control passing between participants. Pre-built Docker images cover Firefox, Chromium, Google Chrome, Tor Browser, Brave, Vivaldi, and Microsoft Edge alongside full desktop environments including XFCE and KDE for running any Linux application. Neko Rooms provides multi-tenant deployment with a REST API for programmatic room provisioning, while Neko Apps extends the platform with additional containerized applications beyond browsers. Sessions persist on the server independently of client connections — close your laptop, reconnect from your phone, and resume exactly where you left off. Optional VPN and Tor integration routes traffic through encrypted tunnels for privacy-sensitive browsing. RTMP broadcasting streams sessions to external platforms. The embeddable client supports iframe integration for custom portals and 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.

Graduated as an Apache Software Foundation Top-Level Project with over 15,500 GitHub stars and 100,000+ Docker Hub downloads, Apache Answer delivers the structured Q&A platform that Stack Overflow and Discourse popularized — fully self-hosted under Apache 2.0 with zero vendor lock-in. The Go backend with React frontend serves questions, answers, and knowledge articles with real-time Markdown preview using CommonMark syntax, inline @mentions to ping domain experts, and transparent revision history tracking every edit. Version 2.0 introduced AI workflows including an integrated AI assistant that helps draft and improve answers, a Model Context Protocol server for connecting AI agents to your knowledge base, API key management, and editor plugin support for extending the writing experience. Advanced search filters by tags, usernames, scores, and date ranges, while real-time suggestions surface relevant existing questions as users type to reduce duplicates. The reputation system rewards quality contributions with configurable privilege thresholds, and admin/moderator/user roles control access across the platform. A plugin architecture enables community-built extensions for third-party OAuth login, caching backends, search engines, and storage providers. Theming supports custom layouts, dark mode, and responsive design across devices, with content available in 15+ languages translated by the community. Bulk user import, email domain restrictions, and content access controls secure the platform for enterprise 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.

Run a Stack Overflow of your own: Apache Answer brings the question-and-answer format in-house, maintained under the Apache Software Foundation with an Apache-2.0 license. You use it to run a community forum, product help center, or internal knowledge base where content lives as questions and answers rather than wiki pages. It ships the mechanics that make that format work: voting, accepted answers, a reputation system with privilege levels, tagging, full-text search with filters, revision history on every edit, and admin/moderator/user roles. Content is written in Markdown with real-time preview and code syntax highlighting. A plugin system covers OAuth login (Google, GitHub), S3 storage, external search backends like Algolia, and Akismet anti-spam, and a REST API exposes platform data for integration. The backend is Go, the frontend React, and it runs against SQLite, MySQL, or PostgreSQL. Self-hosting replaces per-seat tools like Stack Overflow for Teams with a flat-cost instance where you own all the content.

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.

Powering authentication for over 15,000 GitHub stargazers and production deployments across startups and enterprises alike, SuperTokens delivers the complete login infrastructure that Auth0, Firebase Auth, and AWS Cognito charge premium prices for — entirely open source under Apache 2.0 with no per-user limits. The Java-based core service runs as a lightweight HTTP microservice that connects to PostgreSQL or MySQL and handles email-password login, passwordless magic links and OTP via email or SMS, social OAuth with Google, GitHub, Facebook, Apple, and any custom OIDC provider, phone-password authentication, and time-based one-time password multi-factor authentication. Session management uses rotating refresh tokens with anti-CSRF and anti-session-fixation protections, verifying tokens locally in your backend SDK without network round-trips to the core. Frontend SDKs for React, React Native, Angular, Vue, and vanilla JavaScript provide pre-built UI components for login, signup, email verification, and password reset flows, all customizable through an override system that lets you add pre- and post-API logic, custom hooks, and user event handlers. The built-in user management dashboard enables administrators to view users, reset passwords, revoke sessions, modify roles, and manage email verification status. Multi-tenancy and organization support powers B2B SaaS applications with tenant-level authentication configuration and Enterprise SSO via SAML and OIDC. Migration tools support bulk importing millions of existing password hashes, TOTP secrets, and role mappings. 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.