Developed by Tsinghua University researchers and validated across more than 700 students, OpenMAIC converts raw prompts, PDFs, Office documents, audio, and video into complete, multi-agent virtual learning environments. The platform leverages Next.js, LangGraph state machines, and a pluggable `@openmaic/storage` layer to orchestrate autonomous AI professors and student avatars that lecture, debate at roundtables, answer inquiries, and illustrate complex equations on a real-time SVG whiteboard. Its Pro Agent Workbench features durable PostgreSQL-backed sessions, twenty specialized curriculum-building skills, and granular JSON Patch slide editing with full `.pptx` import fidelity. OpenMAIC supports rich scene modalities including automated quiz grading, Project-Based Learning milestones, and Deep Interactive Mode offering in-browser code execution, interactive mind maps, and Three.js 3D physics simulations. Built-in audio pipelines connect with VoxCPM2 for zero-shot voice cloning, Azure STT, and FunASR for speech recognition, alongside a dedicated Chromium-FFmpeg rendering microservice for one-click MP4 video exports. Flexible model routing interfaces seamlessly with OpenAI, Anthropic Claude, Google Gemini, Amazon Bedrock, DeepSeek, and local Ollama or Lemonade instances, while OpenClaw integration enables direct classroom generation from Slack, Discord, Feishu, and Telegram. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Every prompt your application sends is a small buying decision, and OrcaRouter Lite makes it a smart one instead of a habit. Point your app at one OpenAI-compatible endpoint on your server, and each request is shopped across the providers whose keys you hold: OpenAI, Anthropic, Google, xAI, DeepSeek, and dozens more. Send model set to auto and the router picks the cheapest model that can actually do the job, checking whether the request needs tools, vision, or JSON mode before it commits your money. Prefer a different tradeoff and you can switch the whole gateway between balanced, cheapest, fastest, and quality strategies, with quality picks driven by real benchmark scores rather than vibes. Clients that speak Anthropic's or Gemini's native protocols connect directly too, so Claude Code, the OpenAI SDK, and google-genai all land on the same routing pipeline. Streaming responses flow through untouched, and every answer reports which model really served it. The built-in dashboard shows recent requests, spend, latency percentiles, unreachable providers, and a savings tile that tells you what your traffic would have cost if you had blindly used a flagship model for everything. Your provider keys stay encrypted on your own box, your analytics never leave it, and if every local provider has a bad day, the hosted OrcaRouter can step in as a failover safety net. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

NarraLume is a writing studio for long novels where the AI proposes and you dispose, so a book stays yours across tens of thousands of words. Everything lives around the story bible: your stated intent, outline, entities, confirmed facts, relationships, chronology, and foreshadowing, kept as the single source of truth that planning, drafting, and review all read from. You can write chapters by hand in the studio, save versions and comments, ask for a selection edit, or delegate a chapter, a run of chapters, or a whole quick-creation plan to a model; whatever comes back arrives as a candidate with diffs, never as silent edits to your manuscript or canon. Review findings come with evidence you can accept, reject, or mark as false positives, and when generated prose collides with a locked fact the task stops and waits for your ruling instead of improvising around it. The run center keeps every AI job's steps, model calls, and checkpoints recoverable, the long-form lab searches story memory and previews plot impact without touching the book, and delivery ends with quality checks, exports, snapshots, and full-library backups. 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.

Your AI application is burning through API tokens faster than you can refresh the billing page, and you have no idea which prompt template is responsible. OpenLIT plugs that visibility gap with a self-hosted observability platform built specifically for LLM workloads. Add one line of code to instrument 90+ LLM providers, agent frameworks, and vector databases, then watch every request flow through a tracing dashboard that shows tokens consumed, latency measured, and dollars spent per call, per model, per environment. The requests view lists every LLM interaction with provider, model, cost, and token breakdown in a filterable table, while the trace detail panel lets you drill into individual spans to read the exact prompt sent and response received. Prompt Hub turns prompts into versioned artifacts you deploy, rollback, and A/B test without touching application code. OpenGround compares models side by side on the same input, so you can evaluate cost-versus-quality tradeoffs before committing to a provider. Automated evaluations run LLM-as-a-judge scoring on live production traces, flagging hallucinations, bias, and toxicity in real time. The Vault stores and rotates API keys centrally so secrets stay out of your codebase. Custom dashboards let you build drag-and-drop monitoring views with charts, stat cards, and tables backed by SQL queries against ClickHouse. GPU utilization, memory, temperature, and power metrics feed into the same platform for end-to-end infrastructure visibility. 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.

OpenAgentCore puts Codex, Claude Code, and MiniMax Code behind one self-hosted Agents API, so your applications start agent sessions through the official OpenAI SDK while the work runs on machines you control. Set OPENAI_BASE_URL to your installation and issue a Project API key, and the same client code that talks to OpenAI now talks to your Core. Each session runs a native harness, exactly as it runs on a developer's machine, with the model provider, model ID, and protocol you configure per harness or per session. Choose where sessions execute: microsandbox nodes you operate, Docker, E2B, or a self-hosted workstation, VM, or container connected by the oac-daemon with a credential scoped to one environment. Idle microsandbox sessions release their compute and resume on a compatible node with workspace files intact, so long investigations do not rent a machine while they sleep. The Web console walks operators through setup, tracks sessions and turns, manages models and credentials, and issues keys, while the separate Core API serves operators and the Agents API serves applications. Durable execution state in PostgreSQL keeps events, results, and schedules recoverable across restarts. Sandbox providers, workspace filesystems, harnesses, and model providers all plug in through defined protocols, so every layer can be replaced on its own. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Headroom answers the question every multi-plan AI subscriber asks mid-task: which of my accounts still has room to work? It puts the live limits, reset times, credits, and spend of Claude, Codex, Cursor, Copilot, Grok, Antigravity, and Vercel AI Gateway accounts on one self-hosted dashboard instead of seven provider pages. Connect each account once, through its official CLI sign-in or a credential import, and a background scheduler refreshes every figure on schedule, renews tokens before they expire, and keeps 90 days of readings. Five-hour sessions, weekly pools, per-model limits, credit balances, banked resets, and on-demand spend sit side by side, and unreported figures show as unknown rather than a fake zero. Compare ranks same-provider accounts by the room they have left and names the one to use next, while Timeline lays every reset window on a two-week calendar. Analytics charts when you work, when you run dry, and whether each plan fits, and Wallet totals subscriptions, usage spend, and top-ups in one currency with renewals and budget alerts. In-app notices, Telegram messages, and signed webhooks warn about low limits, expiring resets, and broken sign-ins, and optional automations can spend a banked Codex reset or log a credit top-up the moment it lands. Personal, work, and side-project accounts stay separate under one owner login with passkeys and a Privacy Mode that blurs emails on screen. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

ToolHive is an open-source MCP server management platform that lets you run, secure, and orchestrate Model Context Protocol servers in isolated containers, giving AI agents structured access to tools like GitHub, databases, and cloud services without exposing host credentials or network. Every server launches inside its own sandboxed container with a minimal permission file, network access filtering, and encrypted secrets management, preventing misbehaving connectors from reaching beyond their defined scope. The built-in registry provides a catalog of vetted servers you can install with one command, while custom images and package-manager references let you onboard proprietary connectors without writing Dockerfiles. Platform teams deploy the Kubernetes operator to declare MCP servers as cluster resources using Custom Resource Definitions, with automated lifecycle management and multi-namespace isolation. The Virtual MCP Server gateway aggregates multiple backends behind a single endpoint, centralizing OIDC authentication, tool filtering, and composite cross-server workflows so clients connect once instead of juggling separate URLs. An MCP Optimizer analyzes tool schemas via semantic search and surfaces only relevant tools per request, cutting token consumption by up to 85%. OpenTelemetry traces and Prometheus metrics deliver full visibility into tool execution, latency, and request audit trails across every managed server. 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.

GEOInflow is a self-hosted analytics platform that shows website owners which AI crawlers visit their pages, what those crawlers read, and how much traffic and revenue AI search actually sends back. Import a sitemap, CSV, or JSON inventory and the coverage report compares it against observed crawl logs, flagging important pages that no AI crawler has ever requested and directories where coverage keeps dropping. The built-in catalog recognizes 61 AI crawler identities, including crawlers from OpenAI, Anthropic, Perplexity, Google, Microsoft, ByteDance, Baidu, Kimi, and Tencent Hunyuan, and separates training, AI search, and user-triggered visits. Verification combines declared user agents with official IP ranges and DNS evidence, so a spoofed crawler name never counts as a confirmed visit. Browser tracking connects AI search referrals to landing pages, custom events, goals, funnels, and conversions, letting teams measure whether visibility in AI answers turns into signups and sales. Alongside the GEO reports, teams get pageviews, unique visitors, referrers, geography, devices, heatmaps, retention, and visitor paths, with CSV, JSON, and ZIP exports for any selected scope. Workspaces, team permissions, and public sharing links let agencies and publishers give each client or department its own dashboards without exposing raw data or other sites. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Paste one SQL query result into a browser and get an interactive entity-relationship diagram instantly, with no installations, no credentials, and no account required. ChartDB's "Smart Query" runs a single statement in your existing database client that exports table definitions, relationships, indexes, and column types as JSON metadata, meaning the application never touches your database passwords. The canvas renders draggable entities with cardinality markers, collapsible grouping areas, and sticky notes for documentation. AI-powered DDL export generates migration scripts between dialect pairs like PostgreSQL to MySQL or SQLite to CockroachDB, analyzing your schema to produce target-specific DDL with correct type mappings and constraint translations. Import paths cover Smart Query JSON, raw DDL scripts, and DBML files from tools like dbdiagram.io. The AI layer connects to OpenAI or any compatible inference server including local vLLM instances running models like Qwen2.5-32B. Database coverage includes PostgreSQL (with Supabase and Timescale extensions), MySQL, SQL Server, MariaDB, SQLite (with Cloudflare D1), CockroachDB, ClickHouse, and Oracle. Exports to SVG with inline styles or SQL DDL in any target dialect. Ships as a React/Vite frontend behind Nginx in Docker, deployable on RepoCloud with dedicated VPS resources under the AGPL-3.0 license.

With over 27,500 GitHub stars, 350 contributors, and 220 releases since 2022, InvokeAI delivers an industry-leading creative engine that serves as the foundation for multiple commercial AI art products. The web-based UI supports an extensive model ecosystem including Stable Diffusion 1.5 through 3.5, SDXL, Flux.1 Dev, Flux.1 Schnell, Flux.1 Kontext, Flux.2 Klein 4B and 9B, CogView 4, Z-Image, Anima, and Qwen Image — plus externally-hosted models from OpenAI GPT Image, Google Gemini, BytePlus, and Alibaba Cloud via API key integration. The Unified Canvas provides a fully integrated workspace with in-painting, out-painting, brush tools, layer management, and regional guidance for compositing AI-generated content with existing artwork. The node-based Workflow Editor enables building complex generation pipelines with branching logic, connecting text encoders, VAEs, ControlNets, IP-Adapters, and LoRA weights into reusable graphs. Model management handles automatic downloading from HuggingFace and Civitai with conversion between safetensors, diffusers, and checkpoint formats. The backend runs on Python with CUDA, ROCm, and MPS acceleration supporting NVIDIA, AMD, and Apple Silicon GPUs. Multi-user accounts allow shared access to a single InvokeAI server with per-user galleries and settings. 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.

Zapier's job, on your own server: Activepieces is an open-source workflow automation platform built to be exactly that replacement. Flows are built in a visual no-code editor with triggers, actions, loops, conditional branches, auto-retries, raw HTTP steps, and code steps that run JavaScript or TypeScript with full npm package support. Integrations are "pieces" - type-safe TypeScript npm packages with hot reloading for local development - and the catalog spans 600+ services, with the large majority contributed by the community. The platform is AI-first in two directions: native AI pieces call OpenAI, Anthropic, Google, and Azure models inside flows, and every piece automatically doubles as an MCP server, so assistants like Claude Desktop and Cursor can invoke your integrations and workflows through natural language. A built-in MCP server also exposes 30 tools for building flows, managing tables, and running tests agentically. Flows are fully versioned with draft and locked states. The core is MIT-licensed and runs on TypeScript with PostgreSQL and Redis.

Inference Gateway puts a single OpenAI-compatible API endpoint in front of OpenAI, Anthropic, Groq, Cohere, Ollama, DeepSeek, Google, Mistral, MiniMax, Moonshot, Nvidia, and llama.cpp, so your application code never changes when you switch models or providers. The Go binary starts on port 8080 and normalizes authentication, streaming protocols, and response formats across all backends transparently. Native Model Context Protocol support auto-discovers tools from connected MCP servers and injects them into LLM requests without client-side management, enabling server-side tool execution across any provider that supports function calling. Agent-to-Agent protocol integration allows distributed agent communication through a declarative Agent Definition Language that generates production-ready Go or Rust servers from a single YAML manifest. The dedicated Kubernetes Operator manages Gateway, Agent, MCP, and Orchestrator custom resources with automatic HPA scaling, OIDC authentication, and service discovery that rebuilds MCP configurations when the discovered server set changes. Prometheus metrics and OpenTelemetry tracing provide full request-level observability across the entire inference pipeline. Middleware controls enable per-request provider selection, model routing, and fallback strategies. Official SDKs in Go, Python, TypeScript, and Rust provide typed client interfaces with streaming support. Docker Compose deployment requires only environment variables for API keys. A CNCF Sandbox applicant. 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.

LearnHouse delivers a modern open-source learning platform that replaces proprietary course builders with a self-hosted alternative shipping a rich feature set out of the box. The Tiptap-powered block editor supports videos, documents, embeds, quizzes, and file uploads in a Notion-like interface with real-time co-editing powered by Hocuspocus and Yjs CRDT synchronization over WebSocket. AI tutoring integrates Google Gemini and LlamaIndex for RAG-powered context-aware assistance that adapts to course content, while interactive Playgrounds use AI to generate simulations, diagrams, and learning exercises. The platform handles the full course lifecycle: chapters and activities organize into collections and learning paths, assignments support automated and manual grading, and code blocks execute student submissions in 30+ languages with auto-grading. Analytics dashboards track learner engagement, progress, and completion rates in real time. The backend runs on FastAPI with SQLModel and Alembic migrations against PostgreSQL 16 with pgvector for AI embeddings, while Redis handles caching and session management. The frontend builds on Next.js 16 with React 19 and Tailwind CSS v4. Deployment uses an interactive CLI wizard that configures domain, database, admin account, SSL via Let's Encrypt, and optional features like email via Resend, S3 storage, and Google OAuth, then generates a Docker Compose stack ready to start. On RepoCloud, deploy LearnHouse on a dedicated VPS with root SSH access, persistent PostgreSQL storage for your course data, and complete control over AI provider keys and branding customization, all under the AGPL v3 license.

Draw it, write it as code, or hand it to your AI agent: OpenFlowKit is an open-source diagram canvas where the picture and the text behind it are always the same diagram. Drag shapes on the canvas or type a few forgiving lines, and each side regenerates the other as a single undo step. Ten diagram types share that one language: architecture with C4 views and cloud icons, sequence, flowchart, entity-relationship, state, class, mind maps, git graphs, charts, and wireframes. Paste Mermaid, Structurizr, or D2 and it converts into editable shapes, and Copy as Mermaid sends a flowchart or sequence back out for your README. Paste a GitHub repository instead and Map mode draws its architecture for you, with every arrow citing the exact file and line behind it, and a CLI that maps a local checkout for private repos. Connect Claude Code, Cursor, or any MCP client and the agent draws on your live canvas, restyles what is there, and screenshots its own work to check it. A built-in assistant works with your own key from Claude, OpenAI, Gemini, Groq, Mistral, OpenRouter, or a local Ollama, and exports cover PNG, SVG, PDF, JSON, and animated SVG, GIF, MP4, or WebM you can drop into documentation. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Rakazo lets you hire AI bots the way you would onboard teammates: each gets a job, persistent memory, its own sandboxed computer, and a schedule, and it reports back in chat while you check in from any device. Start from templates such as Sales Outbound, Inbox Manager, Talent Scout, Expense Manager, Coding Agent, or Chief of Staff, then tune the instructions, tools, and limits until the bot works the way your team works. Every bot can run on a different model, so research uses one provider while coding uses another, and a local model served by Ollama or LM Studio keeps sensitive work off third-party servers. Bots work on real computers with a browser, terminal, file system, and graphical desktop you can watch or take over, choosing shared team computers or isolated private ones. When a task outgrows one bot, it delegates pieces to peer bots or short-lived subagents and folds their results back into its own thread. Voice mode lets you dictate messages and hear spoken replies, while routines run on schedules so follow-ups, reports, and inbox sweeps happen while you are away. You decide which actions need your approval before a bot takes them, and integrations via Composio, Pipedream Connect, MCP servers, and OpenAPI documents connect bots to tools you already use. 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.

Build a voice AI agent that answers calls, qualifies leads, books appointments, and transfers to a human when needed, all from a drag-and-drop workflow builder in your browser. Dograh ships as a Docker Compose stack (API, web UI, Postgres, Redis, MinIO) that you self-host on any Linux server with automatic HTTPS provisioning via Let's Encrypt. The visual workflow builder lets you design multi-turn conversation flows by connecting nodes for greetings, intent classification, tool calls, and handoffs; describe your use case in plain English and the platform generates the LLM prompt and node graph for you. Connect your own speech-to-text, LLM, and text-to-speech providers (OpenAI, Anthropic, Gemini, ElevenLabs, Deepgram, local Whisper, Kokoro, or any OpenAI-compatible endpoint) or use the built-in Speech-to-Speech mode with Gemini Flash Live and GPT-Realtime-2 for sub-200ms latency. Telephony plugs in through Twilio, Vonage, Vobiz, or Cloudonix for inbound and outbound calling, with live agent transfer when the conversation needs a human. Webhook tool calls connect to Salesforce, HubSpot, Google Calendar, Cal.com, or any REST API without writing orchestration code. The ClonedVoice feature mixes real human voice recordings for high-frequency phrases with neural TTS fallback for dynamic content, cutting costs while improving caller trust. A built-in MCP server lets AI coding agents like Claude Code or Cursor design, test, and edit workflows through natural language. Deploy on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. BSD 2-Clause 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.

Backed by over 21,800 GitHub stars and more than 1,000 community contributors, Airbyte has become the standard open-source data movement platform, powering ELT pipelines for organizations ranging from startups to Fortune 500 enterprises. The platform provides 600+ pre-built connectors covering PostgreSQL, MySQL, MongoDB, Snowflake, BigQuery, Redshift, S3, Salesforce, HubSpot, Stripe, Shopify, Google Analytics, and hundreds of additional APIs, databases, and SaaS applications. The no-code Connector Builder lets practitioners create new source connectors in minutes by pointing at an API documentation URL, while the Python CDK enables custom connectors with full programmatic control for complex authentication flows and pagination strategies. Airbyte's AI agent capabilities include the MCP Gateway for Model Context Protocol integration, the open-source Agent SDK compatible with pydantic-ai, LangChain, OpenAI Agents, and FastMCP, and a Context Store that lets AI agents query business data across connected systems without runtime API stitching. Change Data Capture streams incremental updates from PostgreSQL, MySQL, and SQL Server using Debezium, while dbt integration handles post-load transformations within the pipeline. Self-hosted deployment uses Kubernetes via the abctl CLI tool, which bootstraps a local kind cluster with a single command, or Helm charts for production clusters with Keycloak OIDC authentication and secrets management through AWS Secrets Manager, Google Secrets Manager, or HashiCorp Vault. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. ELv2 licensed with MIT-licensed connectors.