Butterbase gives AI applications a complete backend they can run themselves, from a dedicated PostgreSQL database for every app to an MCP server that lets agents operate that backend directly. Define schemas declaratively, apply migrations, protect rows with Row-Level Security policies, and call the generated REST endpoints without building a separate data API. Add email and OAuth sign-in with Google, GitHub, Apple, X, and other providers, then tune JWT behavior, post-login hooks, service keys, and API keys for each application. Store files in S3 or R2 compatible object storage with presigned URLs and access controls, and keep regional key-value data with TTLs and an audit trail. Run TypeScript functions on Deno, coordinate chat rooms or rate limiters as durable per-key objects, and stream table changes to live interfaces over WebSocket subscriptions. Route chat and embedding calls through one AI gateway, ingest documents into RAG collections, and build checkpointed agent workflows that can pause for human approval before continuing. Host static frontends and edge handlers, expose webhooks for application events, and manage schemas, storage, functions, realtime channels, and integrations through more than forty MCP tools. 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.

One gateway, every AI model: APIPark gives your applications a single, consistent API for OpenAI, Anthropic, Google Gemini, DeepSeek, and 100+ other models, and gives your team a portal to publish and share whatever gets built on top. Standardized request and response formats mean swapping a provider or rewriting a prompt never touches client code. Pair a model with a prompt template and it becomes a ready-made API for sentiment analysis or translation, listed in the developer portal with its own readme and generated API docs. Model Fallback swaps in the highest-priority available model when one misbehaves. API key balancing spreads traffic across several keys for the same provider. Already have REST services? Import an OpenAPI document, file the service under a category and tags, and let consumers subscribe, with optional manual review before anyone gets access. Any service can be switched on as an MCP tool that AI assistants can discover and call, and local open-source models can be deployed and exposed the same way. Usage charts follow requests, traffic, and tokens per service and consumer. Request logs flow out to files, HTTP endpoints, Kafka, NSQ, or Syslog. 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.

Bifrost is an open-source AI gateway that unifies 23+ LLM providers into a single OpenAI-compatible endpoint with automatic failover, semantic caching, and built-in cost governance, so one provider going down never takes your production AI application with it. Point your existing OpenAI or Anthropic SDK at Bifrost's local endpoint and gain access to OpenAI, Anthropic, AWS Bedrock, Google Vertex, Azure, Groq, Mistral, and Ollama without changing application code. Define fallback chains that automatically switch providers when one returns errors or exceeds latency thresholds, keeping response times stable during outages. The built-in web dashboard at port 8080 lets you configure providers, create virtual API keys, monitor live request traffic, and review analytics without editing configuration files. Semantic caching combines exact hash matching with vector similarity search via Weaviate, serving cached responses for identical or paraphrased prompts in sub-millisecond time to cut costs on repetitive workloads. The MCP gateway connects AI agents to external tools like filesystems, databases, and web APIs, exposing them to clients such as Claude Desktop and Cursor with per-key allow-lists. Four-tier budget hierarchy at customer, team, virtual key, and provider levels enforces spend caps, rate limits, and model restrictions across your organization. Extend functionality through custom Go plugins for analytics, monitoring, or security middleware. Native Prometheus metrics and OpenTelemetry distributed tracing give operations teams full production observability. 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.

Backed by 56,000+ GitHub stars and over 240 million Docker pulls, LiteLLM delivers the open-source AI gateway trusted by Netflix, Lemonade, Rocket Money, and thousands of engineering teams to route every LLM request through one unified API. The Rust-core gateway adds sub-millisecond overhead per request with 8ms P95 latency at 1,000 RPS, 15x throughput improvement and 11x lower memory footprint compared to Python-only proxies. A single OpenAI-compatible endpoint connects to 100+ providers and 1,800+ models spanning OpenAI, Anthropic, Google Gemini, AWS Bedrock, Azure OpenAI, Vertex AI, Hugging Face, vLLM, Nvidia NIM, Ollama, and Mistral with day-zero support for new model releases. The Auto Router V2 classifies request complexity across four tiers using rule-based scoring, semantic keyword matching, and adaptive Thompson sampling to route each request to the most cost-effective model without API calls or training data. Virtual API keys enable multi-tenant governance with per-team, per-user, and per-project cost tracking, budget caps with automatic fallback rerouting, and role-based access control. Built-in guardrails provide PII masking, prompt injection detection, and model-graded evaluation before requests reach providers. The Agent Gateway extends routing from model calls to agent workflows with MCP server integration. Observability integrates with Langfuse, Arize Phoenix, OpenTelemetry, and MLflow for complete request tracing. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

One endpoint, every model you run, and a government-grade paper trail for each request. OpenGateLLM sits in front of your AI infrastructure as the single door: applications call one OpenAI-compatible API, and the gateway decides which backend answers, a self-hosted vLLM cluster, an Ollama box in the corner, a Hugging Face TEI embeddings service, or a hosted provider when you allow one. You publish friendly model names as routers and attach real provider APIs behind them, then load-balance across those backends by shuffle or least-busy so a second GPU node starts earning its keep the moment you register it. Chat completions, embeddings, reranking, OCR, and audio transcription each get their standard endpoint, so existing OpenAI SDK code, LangChain, and LlamaIndex projects point at a new base URL and keep working. Governance is built in rather than bolted on: organizations, users, and roles control who may call which model, API keys authenticate every request, and rate limiting keeps one enthusiastic team from eating the whole cluster. Usage monitoring follows every inference, and carbon footprint estimates attach to models through their hosting zone and parameter counts. Retrieval-augmented generation against Elasticsearch or Qdrant plugs into the same surface. No chat history is stored, which is rather the point when the data is yours. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Routerly is the one front door for every AI model your apps use: point your OpenAI or Anthropic client at it, and it chooses the right model for each request, enforces your budget, and keeps the receipts. Nothing in your code changes except the base URL, and from that moment streaming chat completions and messages flow to OpenAI, Anthropic, Gemini, Mistral, Cohere, xAI or your own Ollama models behind a single token. Nine routing policies score every candidate in parallel: cheapest, fastest, healthiest, most capable, biggest context, least rate-limited, fairest, most budget left, and one that asks a small model to judge which model fits the task. When the winner errors or times out, the next candidate takes over automatically, and the recorded routing trace shows exactly why each model won or lost. Guardrails can block or log content that breaks your rules, and phone numbers, card numbers, SSNs, IBANs and emails can be scrubbed out before anything reaches a provider. Every call is logged with tokens, USD cost and latency, and hard limits per model, project and token reject overspending requests before a provider can charge for them. Projects keep separate tokens, model lists and budgets for each team or tool, role-based permissions decide who may change what, and alerts land in Slack, email, webhooks or PagerDuty when budgets or providers misbehave. 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 OpenAI-compatible endpoint, 1,600+ models behind it: Portkey Gateway sits between your app and every major LLM provider, deciding in real time where each request should go. When a provider times out or returns errors, automatic retries with exponential backoff kick in, and fallback rules quietly move traffic to your second-choice model before users notice anything. Load balancing spreads calls across multiple API keys and providers by weight, conditional routing sends each request down a different path based on its content or metadata, and per-request timeouts cut off providers that hang. Guardrails inspect inputs and outputs as traffic passes through: block banned words, screen for sensitive content, and enforce the checks your compliance team asked for, with dozens of pre-built rules ready to attach. Text is only the start: the same API shape reaches vision models, speech-to-text, text-to-speech, image generation, and realtime websocket APIs, so multimodal features stop multiplying your integration work. Routing policies live in JSON configs you attach per request or per client, which means experiments, cost controls, and provider migrations ship as configuration changes, not redeploys. 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.

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.

Drag nodes onto a canvas and ship an LLM app: Flowise is an open-source visual builder for AI agents and LLM applications, written in Node.js on LangChain.js and licensed Apache-2.0. You assemble flows by dragging nodes onto a canvas: models, prompts, memory, vector stores, retrievers, and tools, then wire them together and test in the built-in chat panel. Three builder types cover increasing complexity: Assistant for simple RAG chat over uploaded files, Chatflow for single-agent systems with techniques like rerankers and Graph RAG, and Agentflow for multi-agent orchestration with branching, looping, shared flow state, and human-in-the-loop checkpoints. Over 100 integrations connect data sources, vector databases, and both proprietary and open-source models, plus MCP client and server nodes for standard tool interop. Finished flows are exposed as REST APIs, embedded chat widgets, or via JS and Python SDKs - each flow gets an endpoint the moment it is saved, removing the deployment gap between a working prototype and something your application can call. Execution logs, visual step debugging, and external log streaming trace behavior, while input moderation and rate limiting act as guardrails; RBAC, SSO, and workspaces cover team deployments. Self-hosting keeps prompts, encrypted credentials, and conversation data on your own instance, which matters when flows handle internal documents or customer data - and wiring a model, prompt, memory, and vector store on the canvas replaces the boilerplate a hand-coded LangChain project would need.

Drag an AI agent onto a canvas beside a Gmail trigger, a condition, and a Google Sheets step, and ByteChef runs the whole thing as one durable workflow that resumes where it stopped. Runs that fail or wait for a human pick up from the step they reached. The visual editor maps values between steps with data pills, and its 250+ connectors double as agent tools and MCP tools. An agent combines a model from twelve LLM providers, including OpenAI, Anthropic, Mistral, and Ollama, with chat memory, knowledge-base retrieval, and tools. It streams structured answers. Flow controls cover conditions, branches, loops, parallel and fork-join paths, subflows, error handling, and approval steps that pause for a person. Workflows start from webhooks, polling, schedules, forms, or app events, and code steps run JavaScript, Python, or Ruby. Workflows can be exposed through an MCP server for Claude Desktop, Cursor, or Windsurf, and ByteChef consumes external MCP servers too. Data Tables add typed relational tables with a spreadsheet-like grid and CSV import and export. The Agent Playbook opens a chat with the agent as you build it. Every run is listed with per-step input, output, and errors. 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 + EE 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 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.

Backed by over 56,000 GitHub stars and a growing ecosystem of client and server SDKs covering Flutter, React Native, Swift, Kotlin, Python, Node.js, Deno, and more, Appwrite provides a complete backend platform that replaces Firebase and Supabase with a fully self-hostable architecture. The authentication module supports email and password, phone OTP, magic links, OAuth providers including Google, GitHub, Apple, and Facebook, anonymous sessions, and JWT token management with configurable session policies. The database service provides a document-oriented store with collections, indexes, query filters, pagination, and real-time subscriptions that push changes to connected clients instantly via WebSocket. The storage service handles file uploads with built-in image manipulation including cropping, resizing, format conversion, and compression, served through a CDN-ready URL structure. Serverless functions execute custom backend logic triggered by HTTP requests, scheduled cron jobs, or database events, with runtime support for Node.js, Python, PHP, Ruby, Dart, Swift, Kotlin, and Java. The messaging service enables push notifications, SMS, and email delivery through configurable providers including APNS, FCM, Twilio, Vonage, Mailgun, and Sendgrid. Team management with role-based permissions, webhook integrations, and health monitoring APIs complete the platform. The admin console provides a web-based dashboard for managing all services, monitoring usage metrics, and configuring project settings. Deployment runs via Docker Compose with MariaDB for metadata and configurable storage adapters. 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.

An entire backend in a single Go executable: PocketBase embeds SQLite with realtime subscriptions, authentication and user management, file storage, and an admin dashboard, all behind a REST-ish API. SQLite runs in WAL mode, which outperforms client-server databases for the read-heavy workloads typical of small and mid-sized apps. Authentication supports email/password, one-time passwords, and 15+ OAuth2 providers including Google, Apple, and GitHub, with stateless tokens. Clients subscribe to record changes over server-sent events, and official JavaScript and Dart SDKs cover web, mobile, and Flutter frontends. Collections, rules, and API access permissions are managed visually in the admin UI. When you need custom logic, extend it with JavaScript hooks running in the embedded JS VM of the prebuilt binary, or import PocketBase as a Go library and compile custom business logic into your own single-file backend. File storage attaches uploads to records with thumbnail generation for images and optional S3-compatible external storage. All state lives in one pb_data directory, so backup is a directory copy and upgrade is replacing a binary - one of the lowest-maintenance backends you can run. The contrast with Firebase is the point: where usage-based pricing scales with reads, writes, and bandwidth, PocketBase runs the entire backend at flat hosting cost, and the data is a plain SQLite file you can copy anywhere. MIT-licensed.

With 37,000 GitHub stars and over 45 million downloads powering 500,000+ deployed projects, Directus is the most widely adopted open-source backend platform that connects to your existing SQL database without requiring schema migrations or data duplication. Point it at PostgreSQL, MySQL, MariaDB, MS SQL, SQLite, OracleDB, or CockroachDB and it instantly generates production-ready REST and GraphQL APIs complete with filtering, sorting, pagination, field selection, and relational queries — all derived from your actual schema with zero configuration. The visual Studio provides a full no-code management interface where non-technical teammates create content, manage assets, build dashboards, and configure access policies without engineering involvement. Field-level granular permissions govern every API request and Studio action through composable policies applied to roles, users, and AI agents identically. A built-in AI Assistant writes copy, translates content across languages, creates records, and routes items for review directly within the Studio interface. The native Model Context Protocol server connects Claude Desktop, Cursor, ChatGPT, or any MCP-compatible tool to your live data governed by the same access policies. Real-time WebSocket subscriptions push collection changes instantly for collaborative editing and live dashboards. Extensibility covers custom endpoints, hooks, interfaces, displays, layouts, modules, and operations. Deploy via Docker with environment-variable configuration or use Directus Cloud for managed hosting. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. BSL-1.1 licensed with free self-hosting.

pRESTd points at your PostgreSQL or MySQL database and instantly serves every table as a REST API, so the CRUD backend you were about to spend a week writing already exists. Every table answers at its own address with filtering, ordering, pagination, and column selection in the query string, and batch endpoints group several operations into one call. When a table endpoint is not enough, drop a SQL file into the queries folder and it becomes a named route with bound parameters, or store the scripts in the database and manage them through the admin API. Turn on the auth module and the server issues JWTs from your own users table, checks them on every route, and enforces table-level permissions so public tables stay open while payroll stays shut. The same database also appears as a read-only MCP endpoint, which lets Claude, Cursor, and other AI clients discover your tables and query them with your permissions instead of a copied export. One process can front several databases at once, Postgres and MySQL side by side, each under its own alias for tenants or reporting replicas. An embedded Studio in the same binary browses the catalog and rows, builds GET requests, and invokes MCP tools, so you can inspect everything from the browser before writing a line of client code. 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 2,600+ GitHub stars, MetaMCP solves the MCP server sprawl problem by aggregating any number of upstream servers into a single authenticated endpoint that any MCP client connects to once. Group servers into namespaces — development tools in one, data sources in another — then publish each namespace as its own SSE, Streamable HTTP, or OpenAPI endpoint with API-key authentication in headers or query parameters, or full OAuth per the MCP Spec 2025-06-18 standard. The aggregation engine discovers tools, resources, and prompts from all active servers in parallel, prefixes tool names with server identifiers to prevent collisions, and applies configurable middleware including tool filtering to reduce context-window bloat and description overrides to improve LLM comprehension. The web management UI lets you configure MCP servers with stdio, SSE, or Streamable HTTP transports, toggle servers active or inactive per namespace, create and revoke API keys per endpoint, and inspect discovered tools with their schemas. Nested MetaMCP support enables hierarchical architectures where one MetaMCP instance consumes another, creating multi-level tool organization with automatic name resolution. Compatible with Claude Desktop, Claude Code, Cursor, Open WebUI, and any MCP-compatible client through a single connection URL. The Docker container packages the TypeScript backend with PostgreSQL for configuration persistence, exposing the management UI on port 12005 and MCP endpoints on configurable ports. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.