New API is a Go-powered LLM gateway that funnels over 40 AI providers, from OpenAI and Anthropic to Google Gemini, Azure, AWS Bedrock, DeepSeek, and Mistral, through a single OpenAI-compatible endpoint with intelligent routing and enterprise cost controls. Bidirectional format conversion translates between OpenAI Chat Completions, Claude Messages, and Gemini GenerateContent APIs transparently, so clients call any provider using their preferred format while the gateway handles the rest. Routing logic supports weighted random channel selection, priority-based failover, and automatic retry on provider errors to maximize uptime. The React admin dashboard shows usage charts, token consumption tracking, per-model cost breakdowns, and real-time request monitoring. Multi-tenant architecture includes three role levels, token-based authentication, per-user quota management, and a three-phase billing system with tiered pricing via a custom expression language. Multimodal support covers text completion, vision, embeddings, text-to-speech, speech-to-text, image generation, and creative task providers like Midjourney-Proxy and Suno-API. The interface ships in five languages including English, Chinese, Japanese, and French. Docker deployment runs with SQLite or MySQL for persistence. 45,000+ GitHub stars. AGPL-3.0 licensed.

Between your databases and everything that consumes data - BI tools, embedded analytics, AI agents - sits Cube (formerly Cube.js), an open-source semantic layer. Metrics, dimensions, joins, and access rules are defined once as code in YAML, JavaScript, or Python, forming a governed data model that every downstream consumer shares, so "revenue" means the same thing in every dashboard. Caching is two-level: an in-memory cache absorbs bursts of identical queries, and declared pre-aggregations - rollup tables built in the warehouse or in Cube Store, Cube's distributed columnar engine, and refreshed in the background - deliver sub-second latency while cutting warehouse compute costs. The query planner routes each request to cache, rollup, or source automatically. Consumers connect through a Postgres-compatible SQL API (any tool that speaks Postgres works), plus REST, GraphQL, and a Meta API for model introspection. Row-level security and multi-tenancy are enforced in the layer itself, upstream of every client. Sources include Snowflake, BigQuery, Databricks, Postgres, MySQL, Presto, and Athena. Headless by design - bring your own UI.

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.

walgit is a self-hosted Git server that keeps every repository inside one S3 or GCS bucket, so the machine serving your code is disposable while your history stays durable. Point the binary at a bucket, start it, and pushing to a new repository name creates that repository on the spot, with no admin console or provisioning step in between. Developers clone, fetch, and push over smart HTTP with Git LFS support for large files, and big clones are delivered as static bundle files so multi-gigabyte repositories never bottleneck the server process. The built-in web interface lets you browse file trees, read files, review commit history, and inspect diffs directly in the browser. Per-repository policy files control protected branches, fast-forward-only references, and bypass lists, so release branches stay guarded without a separate compliance tool. A JSON API and the dependency-free repos.js SDK let scripts, internal dashboards, and automation agents read repository data programmatically, with long operations streaming progress as server-sent events. Webhooks deliver exactly-once reference events to CI systems, chat tools, and deployment pipelines whenever branches or tags move. Background checkpoints and compaction keep storage tidy on their own, while token or OpenID Connect sign-in decides who may read and who may push. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

With 5,600+ GitHub stars and deep dbt integration, Lightdash is the open-source Agentic BI platform that treats analytics like software — defining metrics, dimensions, joins, permissions, and caching in a governed context layer that powers dashboards, AI agents, data apps, embedded analytics, and MCP server endpoints simultaneously. The dbt Write-Back feature lets business users create custom metrics and models in the UI, then automatically generates pull requests in GitHub or GitLab so every change flows through code review and CI validation before reaching production. Context-specific AI analysts automatically select relevant models and metrics, build queries, and present insights in plain English, while row-level security, user attributes, and customer-facing permissions ensure data governance at every layer. The platform connects to BigQuery, Snowflake, Redshift, Databricks, PostgreSQL, Trino, and ClickHouse through warehouse adapters, with the TypeScript monorepo built on React, Mantine, Vite, and TanStack Query on the frontend plus Node.js, Express, Knex, and PostgreSQL on the backend. Data teams build analytics with coding agents, preview changes from the CLI, validate in CI pipelines, and review charts and dashboards in pull requests — making the entire analytics lifecycle version-controlled and reproducible. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

With over 10,000 GitHub stars and a reputation forged in the frustration of laggy corporate screen sharing, Screego delivers what Microsoft Teams and Zoom screen share consistently fail to provide: instant, high-resolution screen streaming that lets remote colleagues actually read your code. Built on WebRTC peer-to-peer connections, Screego transmits screen data directly between browsers without routing through centralized servers, achieving sub-second latency and native-resolution quality that makes pair programming and code reviews genuinely productive. The server component, written in Go with a TypeScript frontend, deploys as a single binary or Docker container with minimal configuration — set your external URL, generate a secret key, and you're live. An integrated TURN server handles NAT traversal automatically, eliminating the need for separate STUN/TURN infrastructure, with configurable UDP port ranges and support for external TURN servers when scaling beyond a single instance. Authentication supports three modes — requiring login for all actions, only for TURN connections, or none — with user management via simple credential files. Rooms are created instantly and support multiple simultaneous viewers, with system and tab audio sharing available for demonstrations that need sound. The architecture supports reverse proxy deployment behind Nginx, Caddy, or Apache with automatic TLS termination, and recent releases added riscv64 architecture support alongside existing amd64 and arm64 builds. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. GPL-3.0 licensed.

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.

Execute comprehensive multi-angle investigations across scientific journals and web repositories using Local Deep Research, an autonomous intelligence engine designed for researchers, analysts, and knowledge workers. Users can submit complex analytical questions through a self-hosted web console to initiate agentic research cycles powered by LangGraph workflows. The application dynamically queries search providers including SearXNG, arXiv, PubMed, Wikipedia, and Google, iteratively evaluating discovered content to formulate targeted follow-up queries. Discovered academic papers and web sources can be indexed into an encrypted personal library to combine internal documentation with external search intelligence. Reports are synthesized with structured outlines, section headings, and verifiable academic citations that link directly to source references. Individual research sessions, system logs, and user credentials remain isolated in per-user SQLCipher databases protected by AES-256 encryption. Automated subscriptions deliver scheduled news digests and topic monitoring summaries directly to connected notification channels. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Ever Works transforms a single text prompt into a fully researched, written, coded, and deployed website through autonomous AI agents that operate on a configurable 15-step generation pipeline. Unlike one-shot builders, it continuously improves generated content on a schedule, keeping sites fresh without manual intervention. The platform integrates with six AI providers (OpenAI, Anthropic, Google, Groq, Mistral, Ollama) via gateways like OpenRouter and Vercel AI Gateway, while its plugin system connects ten search providers including Tavily, Brave, Exa, SerpAPI, and Perplexity for deep autonomous research. Every generation is Git-native — code and content live in your own GitHub repositories as commits, providing full version control, portability, and zero vendor lock-in. The monorepo ships a NestJS 11 REST API with JWT authentication, a Next.js 16 web dashboard for managing works, a CLI for terminal operations, an MCP server for AI agent integration, and admin tooling. Content management supports items, categories, tags, and collections, while deployment targets include Vercel and Kubernetes. Background processing runs on Trigger.dev with BullMQ scheduling, and monitoring leverages Sentry plus PostHog for error tracking and product analytics. The platform supports OAuth via GitHub and Google, subscription billing, email notifications, and AI chat conversations for natural-language interaction with your generated works. 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.

An agent run can finish without errors and still give the wrong answer, so TraceRoot traces every model and tool call, flags the production runs that missed the mark, and helps your coding agent ship verified fixes. Each run becomes a browsable call tree with inputs, outputs, latency, and cost, searchable by session or filter. Instrument with the Python or TypeScript SDK, the agent-native CLI, or any OpenTelemetry exporter, with ready integrations for LangChain, LangGraph, OpenAI Agents SDK, CrewAI, Vercel AI SDK, Mastra, and Pydantic AI. Detectors use LLM judges to score live traffic against the behavior you define and can post alerts to Slack. Judge outputs cluster into signals, then a background coding agent reads the traces and your connected GitHub code in a sandbox and recommends changes down to the commit, file, and line. Datasets, test cases, and scored eval runs compare versions so regressions surface before a release, and dashboards of widgets chart your trace data. The CLI hands your coding agent, such as Claude Code or Codex, the traces, signals, detectors, and evals to work from. Self-hosting keeps all of that trace data on infrastructure you control. 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 (core edition).

DCM is a visual builder that eliminates docker-compose copy-paste anxiety for home server enthusiasts. The TypeScript and Next.js web interface on port 7576 presents a curated catalog of popular self-hosted applications organized into categories: media management with Jellyfin, Plex, Sonarr, Radarr, and Prowlarr; dashboards like Homarr and Heimdall; databases including PostgreSQL, MariaDB, MongoDB, and Redis; monitoring stacks with Grafana and Prometheus; download clients like qBittorrent and NZBGet; security tools including Vaultwarden; storage solutions like Nextcloud; and home automation via Home Assistant. Select any combination of containers and DCM generates both compose.yaml and .env files with correct volume mounts, environment variables, PUID/PGID ownership, network modes, and port mappings — ready to paste into your terminal. Automatic port conflict detection identifies clashing services and reassigns ports before you ever hit a deployment error. The Template Gallery ships predefined multi-container stacks for common setups: media servers, development environments, database clusters, and monitoring solutions — some incorporating ten or more services in a single template. Built as a static Next.js export served from a 62 MB multi-arch Docker image supporting amd64, arm64, and arm/v7, DCM runs on everything from rack servers to Raspberry Pis. Share generated configurations via URL or download them locally. 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.

One endpoint for every MCP server you run: MCPHub gathers local and remote Model Context Protocol servers behind stable URLs, so AI clients connect once and see what you allow. Claude Code, Cursor, and Cherry Studio can use four routes: everything at /mcp, a named group at /mcp/{group}, one server at /mcp/{server}, or semantic tool search at /mcp/$smart. Smart routing runs vector search on PostgreSQL with pgvector and an OpenAI-compatible key, so the model gets a shorter tool list. Servers attach over stdio, SSE, or streamable HTTP, OpenAPI services can be wrapped as MCP tools, and changes apply without downtime. In the other direction, MCP tools can be exported as an OpenAPI 3.0.3 spec for OpenWebUI and other OpenAPI clients. Bearer keys, OAuth 2.0 (client and server modes), and GitHub or Google sign-in in database mode control access, with per-user visibility for servers and groups. Encrypted per-user credentials let one shared server use each person's own key. Logs show tool-call activity, request status, and latency, health checks track each connection, and the dashboard controls which tools, prompts, and resources each server exposes. Large text tool results can be compressed, interactive MCP Apps are proxied through MCPHub routes, and a built-in market lets you browse a server catalog. Typical uses include a team-wide gateway, per-project groups, and direct single-server routes for debugging. 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.

OpenCode Manager is a mobile-first command center for AI coding agents. Install the PWA on your phone or tablet and you get real-time streaming chat, multi-repository Git operations, and scheduled automation right in your pocket. Git integration handles SSH-authenticated repo cloning, worktree management, unified diffs, and branch operations across all your projects in one dashboard. Chat with coding agents through Server-Sent Events streaming that supports slash commands, @-mentions for files, Plan and Build modes, and Mermaid diagram rendering for architecture discussions. Schedule reusable prompts to run against any repository on intervals or cron expressions, with each run tracking history and linking to sessions so you can pick up exactly where automation left off. MCP server configuration adds local and remote HTTP servers with OAuth support, plugging into the broader Model Context Protocol ecosystem. A dedicated assistant workspace provides an isolated AI environment with auto-provisioned skills for managing schedules, notifications, and settings. Multiple AI providers are supported including Anthropic, GitHub Copilot, and OpenAI-compatible services, each configurable with custom system prompts and granular tool permissions. Push notifications alert you to session events, agent questions, errors, and task completions across all managed repositories.

With over 82,000 GitHub stars and 700,000+ downloads, LobeHub has evolved from its origins as LobeChat into a comprehensive multi-agent AI collaboration platform where humans and autonomous agent teams co-evolve. The platform's Agent Harness architecture functions as an operating system between AI models and applications, handling prompt presets, tool orchestration, lifecycle hooks, planning, filesystem access, and sub-agent management across 25+ model providers including OpenAI, Anthropic Claude, Google Gemini, DeepSeek, Mistral, Groq, AWS Bedrock, Azure OpenAI, and local models through Ollama. Agent Groups enable sophisticated collaboration with sequential, parallel, iterative, and debate orchestration modes, allowing multiple specialized agents to tackle complex workflows simultaneously. The Agent Builder creates production-ready agents from natural language descriptions with auto-configuration, drawing from a marketplace of 505+ pre-built agents and 10,000+ MCP-compatible skills and plugins. Pages provide collaborative document editing with multi-agent co-authoring, while Schedules automate agent runs around the clock without human supervision. The knowledge base leverages PostgreSQL with pgvector for RAG-powered retrieval, and Personal Memory gives agents transparent, editable context that evolves through continual learning. The full self-hosted stack deploys via Docker Compose with PostgreSQL, Redis, RustFS for S3-compatible storage, and SearXNG for private web search, all configurable through environment variables. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. LobeHub Community licensed.

With 16,100 GitHub stars and created by Solomon Hykes (co-founder of Docker), Dagger eliminates proprietary YAML DSLs from CI/CD by letting developers write pipelines as real programs in their preferred language — then executing them identically on a laptop, in GitHub Actions, in GitLab CI, or on any machine with a container runtime. The BuildKit-based Dagger Engine runs every pipeline operation inside OCI containers, constructing a directed acyclic graph where each node is cached by default, parallelized automatically, and produces bit-for-bit reproducible outputs regardless of execution environment. Native SDKs generated from the GraphQL API schema provide Go, Python, TypeScript, PHP, Java, .NET, Elixir, and Rust developers with full type safety, IDE autocomplete, and the ability to unit-test CI pipelines using the same testing frameworks as application code. The module ecosystem enables cross-language composition where a Python team can invoke a Go team's build functions without learning Go, while filesystems, secrets, git repositories, and network tunnels are passed between functions as strongly-typed objects. Pipeline operations cache at container-layer granularity with content-addressed deduplication, and the interactive REPL enables step-by-step pipeline debugging with live container inspection. Host dependencies are explicit and strictly typed, eliminating implicit environment coupling that causes "works on my machine" failures. 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 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.

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.

Tau delivers a complete self-hosted cloud platform where Git is the control plane and WebAssembly is the runtime. The Go binary deploys as interconnected nodes that form a P2P network using libp2p for automatic service discovery, eliminating Kubernetes entirely. Serverless functions compile to WebAssembly for secure multi-tenant execution with automatic horizontal scaling — write in Go, Rust, AssemblyScript, or C and deploy by pushing to Git. Branch-based environments map Git branches to isolated deployments, so staging and production run identical infrastructure from different refs. Static website hosting serves frontends with global distribution and automatic content-addressed deduplication via IPFS-derived storage. The built-in K/V database provides distributed storage with automatic replication across nodes, while object storage handles file management with content addressing. Pub/Sub messaging enables real-time communication between functions and external services including WebSocket support. Spore Drive automates multi-host deployment and rolling updates from a single command across bare metal or VMs running Ubuntu. The Dream CLI provides a complete local development environment that mirrors production exactly — same services, same routing, same deployment flow. Zero-configuration HTTPS provisions TLS certificates automatically for custom domains. The web console at console.taubyte.com provides visual project management, or use the tau CLI for Git-native workflows. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. BSD-3-Clause licensed.