Your prompts never have to leave the building: TextGen runs open large language models on your own hardware behind a chat interface and an API that speak fluent OpenAI. Load GGUF or Hugging Face weights through llama.cpp, ik_llama.cpp, Transformers, ExLlamaV3, or TensorRT-LLM, and switch models or backends from the interface without restarting the server. Chat mode gives you conversations with characters and system prompts, notebook mode behaves like a familiar completion editor, and both accept image attachments for vision models and documents for context. Models that support tool calling can search the web, fetch pages, and do math through single-file Python tools, and MCP servers plug in for larger tool catalogs. Start it with the API flag and the same model answers at chat, completions, and messages endpoints that mirror OpenAI and Anthropic, complete with streaming, logprobs, embeddings, and optional API key authentication. Portable builds for Linux, Windows, and macOS bundle every dependency, so the distance from download to a running model is an unzip and one shell command. Because everything is local, prompts, documents, and outputs stay on machines you control, and parallel request handling lets a single loaded model serve a whole team's tools at once. 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.

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

With 17,000 GitHub stars, 460+ contributors, and deployments across telecommunications, automotive, and financial services running on over 10,000 CPU cores at the largest known installations, Apache APISIX delivers a fully dynamic API gateway achieving 140,000 QPS on eight cores with sub-millisecond latency through NGINX's event-driven architecture and LuaJIT-compiled plugin execution. The 100+ open-source plugins cover authentication (JWT, OAuth 2.0, OIDC, Keycloak, LDAP), observability (Prometheus, Datadog, SkyWalking, OpenTelemetry), traffic management (rate limiting, circuit breaking, canary releases, traffic splitting), and security (CORS, IP restriction, CSRF protection) — all hot-reloadable without process restarts via etcd-based real-time configuration synchronization. Multi-protocol support handles HTTP, gRPC, MQTT, TCP, UDP, and WebSocket traffic for both north-south API access and east-west service mesh communication. AI gateway capabilities proxy requests to 20+ LLM providers with semantic caching, token-aware rate limiting, provider failover routing, and content moderation. Custom plugins extend the gateway in Lua, Go, Java, Python, or WebAssembly. Radixtree route matching handles 100,000+ routes without performance degradation. Functions as a Kubernetes ingress controller with native service discovery for Consul, Nacos, and Eureka. Deploy via Docker or Helm charts with horizontal scaling through etcd cluster coordination. 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 net worth is scattered across banks, brokers, a pension, and a mortgage, and no single screen shows all of it at once. Aurelio Finance gathers those pieces on your own server: record each institution's cash and holdings as dated situations, then let later transactions roll them forward so today's balance always traces back to a photograph of what you held and the events after it. Every position is priced from the market with its cost basis, gain, and dividends, while the look through view opens your ETFs and funds to show real exposure by country, sector, company, and currency, so overlapping funds stop hiding concentration. Recurring investment plans, homes and other real assets, and the loans against them sit beside income, expenses, and your savings rate, and each financial goal shows the return it needs to be reached. When you want a second opinion, Ask Aurelio reads your own records, can search the web, and proposes changes as cards you confirm or reject, never silently editing your data. Its analysis mode goes further, letting an analyst and a confidant argue over your portfolio before a synthesis tells you what to look at first, and surviving ideas land on a watchlist that your totals never count. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Your closet already knows what you own; Wardrowbe is the part that remembers it for you and decides what goes together tomorrow morning. Photograph garments one at a time or several in a single shot, and a vision model tags each piece with its type, color, pattern, fabric, style, and formality, with a confidence score you can correct. From that catalog the app builds complete outfits out of clothes you already have, weighing your local weather, the occasion, notes you attached to individual pieces, and the aesthetic you described. A daily suggestion can arrive on a schedule through ntfy, Mattermost, or email, so the outfit is waiting before you are. Accept, reject, and rate what you wear, and the history calendar keeps every past recommendation while the feedback sharpens the next ones. Pairings work the other way around too: pick one item and get outfits built around it, each with a plain-language explanation of why the combination works. Analytics show what you actually wear, what never leaves the rail, and how your colors distribute, and the wardrobe view flags pieces that need washing. Households manage several members' wardrobes with personalized suggestions for each person. Everything runs against any OpenAI-compatible endpoint, so Ollama with a local multimodal model keeps the whole pipeline offline and free. The interface speaks eight languages and follows your browser by default. 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 43,000 GitHub stars and adoption by companies including Nasdaq, Samsung, and Expedia, Kong Gateway is the world's most deployed open-source API gateway, processing billions of API requests daily across hybrid-cloud and multi-cloud architectures. Built on the battle-tested NGINX engine with OpenResty's LuaJIT runtime, Kong delivers sub-millisecond proxy latency while supporting REST, gRPC, GraphQL, WebSocket, SOAP, and Kafka protocols. The plugin architecture includes authentication via JWT, Basic Auth, HMAC, key authentication, OAuth 2.0, and LDAP, alongside rate limiting with configurable windows per consumer, IP address, or API key. The AI Proxy plugin provides a universal LLM API that routes across OpenAI, Anthropic, Google Gemini, AWS Bedrock, Azure AI, Databricks, Mistral, and Hugging Face through a single standardized interface, while MCP proxy capabilities convert REST APIs into MCP tools and provide traffic governance for AI agents. Kong supports declarative configuration via YAML for GitOps workflows, a RESTful Admin API for dynamic configuration, and decK CLI for version-controlled infrastructure-as-code management. Upstream health checking with active and passive probes enables automatic failover, and the ring balancer distributes traffic across upstream targets with consistent hashing, round-robin, or least-connections algorithms. The Kong Plugin Hub hosts over 100 community and official plugins covering logging, monitoring, transformation, security, and traffic 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.

Spreadsheets and old Access databases give way to custom business apps that a team builds itself in a browser with Saltcorn, a no-code database application builder. Tables hold related records with typed and calculated fields, and CSV files import straight into them. Views start from patterns such as list, show, edit, filter, kanban, calendar, gantt, map, and chart, then take shape on a drag-and-drop canvas with a layers tree and desktop, tablet, and mobile previews. A view can embed another view, so clicking a row narrows the others and builds a cross-filtering dashboard with no glue code. Triggers react to row changes, schedules, logins, and API calls, while visual workflows branch, loop, and pause for a person's form before resuming days later. An AI copilot drafts tables, pages, and workflows from a plain-language prompt. The same views also become native Android and iOS apps with offline mode, PDF or image documents, and responsive emails. Every table, view, and page carries a minimum user role, and an auto-generated REST API exposes the data. Packs such as project management and an address book start an app from a ready template. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Most AI chat integrations bolt an LLM onto a text box and call it customer support; AgentDesk builds the entire helpdesk around AI agents that handle first responses, escalate to humans when they cannot answer, and track follow-up work through integrated ticket workflows. Each AI agent binds to a specific LLM configuration, one or more knowledge bases, a set of callable Skills, and MCP tool integrations, creating specialized support personas for different product lines or departments. When a customer message arrives, the agent retrieves relevant FAQ entries and document chunks through RAG-powered vector search (Qdrant), then passes retrieved context through an Answerability Gate that determines whether the knowledge base can support a reliable answer; if not, it triggers a fallback response and recommends human handoff instead of hallucinating. Human agents pick up escalated conversations in a dedicated workspace that preserves the full AI conversation history, customer profile, conversation tags, and linked tickets, so they never start from scratch. The ticket system converts conversations into tracked work items with category assignment, status flows, progress notes, and team routing. An admin dashboard provides user management, role-based access control, team scheduling, and automatic conversation assignment rules. Model configuration supports any OpenAI-compatible provider, letting you wire in LLMs, embedding models, and reranking models with per-model context limits, timeout settings, and rate controls. 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.

A budget model, the launch document that explains it, and the slides that present it can live side by side in one self-hosted office workspace that people and AI agents edit together. Personal and Team Spaces organize Sheets, Docs, Slides, relational Bases, and Boards, with Recent, Trash, file import, and export views keeping everyday housekeeping close at hand. Sharing follows role and node aware access control, including anonymous viewing, so a single table or document can be opened to a reader without exposing the whole space. Data and references stay connected across artifacts as the workspace changes, which keeps a figure corrected in a sheet consistent with the document that quotes it. The Workspace Agent drafts and revises content in isolated Worktrees, verifies its own changes, and hands the result to a person for review before anything reaches the trunk. Several review rounds can happen while humans keep editing in the Browser, and nothing merges until someone approves it. The Workspace CLI connects existing agents to your deployment, so automation can create content, inspect data, render screenshots and PDFs, and run layout checks before review. Sign-in accepts passwords, GitHub, Discord, or application OAuth, and files move in and out as XLSX, DOCX, PPTX, and CSV without a separate conversion project. 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.

Built for brands that want AI search engines to quote them, GEOFlow is an open-source admin system that turns approved knowledge into reviewed articles and publishes them across every site you run. Load documents or import trusted web pages into knowledge bases that are chunked into evidence units, with optional semantic planning and vector retrieval. Combine them with title libraries (AI can draft up to 100,000 titles), keywords, images, authors, and prompts, then set a task's generation limits, cadence, and publishing scope. Chat and embedding models connect through OpenAI-compatible endpoints or native Gemini, with automatic fallback to the next model when a call fails. Each draft passes an AI quality gate that checks evidence, citations, advertising rules, and publishing context, records scores with source locations and revision advice, and holds risky articles for a human reviewer. Approved articles appear on the built-in site with SEO metadata, Open Graph, Schema, sitemaps, and llms.txt, or travel to hosted subdomain sites, GEOFlow Agent packages, WordPress through its REST API, or any HTTP endpoint. A manual publishing workbench and Chrome assistant cover platforms that need a person, while analytics track traffic, AI crawlers, and brand visibility in generative engines. An API, command-line tool, and agent skill support automation. 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.

Customermates delivers a modern CRM purpose-built for teams who want practical customer management without enterprise-heavy complexity. The platform manages contacts, organizations, deals, services, and tasks through clean pipeline workflows while integrating AI agent capabilities, REST API access, webhook events, n8n automation connections, and Model Context Protocol tooling for AI-native operations. Team collaboration features include role-based permissions, comprehensive audit logging tracking every data change, and workspace organization for multi-team deployments. The deal pipeline provides customizable stages with drag-and-drop management, while task assignments and service tracking connect directly to contact and organization records for complete relationship context. API-first architecture exposes all CRM data through documented endpoints enabling custom integrations, reporting dashboards, and third-party tool connections. The n8n integration enables no-code workflow automation for lead routing, follow-up sequences, notification triggers, and cross-system data synchronization. Self-hosting requires only two files — a Docker Compose configuration and environment variables — with the published image at ghcr.io/customermates/customermates:latest running database migrations automatically on first boot. PostgreSQL provides the data layer with no additional infrastructure dependencies beyond a reverse proxy for TLS termination. The Community Edition includes unlimited users, unlimited records, full API access, n8n automation, and audit logging at zero cost. 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.

Instead of burying your documents in a vector index you cannot inspect, LLM Wiki v2 files them into a Markdown wiki you can read, browse, and question. Drop text, Markdown, or PDF files anywhere on the page and each one is catalogued automatically, filed into a folder that says what it holds, and linked to the notes it relates to. Ask a question and the answer cites the exact notes it used, with clickable sources you can open, verify, and correct. New documents update the note on their subject instead of piling up as disconnected chunks, so what you teach it stays taught. A small classifier routes filing and questions through the folder tree, keeping the wiki quick and cheap as it grows, and you can browse the tree, follow see-also links, move or delete notes, and watch the tokens spent by both the model and the classifier. Connect OpenRouter, OpenAI, Gemini, a local Ollama, or any compatible endpoint, and expose the same wiki to Claude Code or Codex as long-term memory they can recall from and write to. Because every note is plain Markdown in a folder you own, the whole knowledge base can live in git beside your other files. 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.

CaseCite puts a law firm's own files under questioning, returning cited answers, contract reviews, and drafted agreements without surrendering a single document to an outside legal platform. Ask a question across the indexed corpus and receive answers tied to the exact source passage, then narrow the search to selected files or a folder when only those should count. For bigger questions, deep research lays out a plan of sub-questions you can edit first, verifies every quote against its source, and keeps a step log of what was searched. Contracts can be analyzed, questioned one at a time, or compared clause by clause across two to four agreements against a baseline, with redlines exported as native Word tracked changes. Tabular review extracts the fields you define from hundreds of contracts at once, shows the supporting passage and estimated cost beside each value, and exports to Excel or CSV. Drafting starts from up to four precedent documents, and long agreements get a section plan for your approval before each section is written and reconciled. Each client engagement lives in its own matter workspace with controlled access and an activity feed, while case lookup, citation checking, judge analytics, dockets, oral arguments, and authority maps cover the caselaw side. 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.

DB-GPT lets a team talk to its data: ask a business question in plain English, and an AI agent plans the work, writes the SQL, runs it, and hands back charts and a written report. Connect MySQL, PostgreSQL, SQL Server, ClickHouse, DuckDB, Doris, StarRocks, or MaxCompute, or drop in CSV and Excel files, including several at once. Every step appears in a live task view with its query, result table, code, and console output, and the agent pauses to ask clarifying questions, with answer options, when the data cannot settle the matter. Reusable skills package proven procedures, including CSV analysis, SQL analysis, and financial report analysis, and a skill creator helps write new ones. Code executes in a sandbox, parallel sub-agents split larger jobs, and an agentic knowledge-base search answers questions over uploaded documents. Scheduled tasks run saved conversations on a cron timetable with on/off switches and execution history, while MCP connectors link tools like Notion, Linear, Tavily, and GitHub. Pick OpenAI, DeepSeek, Qwen, SiliconFlow, Ollama, or vLLM for the model, then use the application and AWEL workflow tools to build data apps of your 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.

Deploy autonomous conversational AI agents and coordinate complex multi-agent workflows through EDDI, an open-source orchestration middleware that turns declarative configuration files into secure, production-grade enterprise assistants. Engineering teams connect AI models from twelve different commercial and local providers, using bilateral Model Context Protocol tools to let external desktop clients and coding assistants interact directly with running conversational services. Autonomous agents collaborate through structured group interaction patterns including round table discussions, peer reviews, Delphi consensus rounds, and devil's advocate debates to refine generated solutions before delivery. Declarative workflow extensions automate external REST API calls with dynamic request templating, extracting structured properties into persistent conversation memory and chaining multi-step service interactions without custom script glue. Built-in secret vaults safely manage sensitive API credentials, while the centralized web dashboard provides live conversation inspection, token quota enforcement, and comprehensive audit logging for regulatory compliance. 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.

Folivox turns an ebook sitting on your server into a finished audiobook read aloud in a voice you choose, cloned from a short sample, or performed by a whole cast of characters. Drop in an FB2, EPUB, DOCX, PDF, or TXT file and the studio detects the book language, restores chapters, poems, and epigraphs, cleans page furniture away, and spells numbers, dates, money, and abbreviations out in full for nine fully supported languages. Narration runs locally through CosyVoice 3 or the multi-speaker Fish Audio Drama 3, which can give each character their own voice like a radio play, or through ElevenLabs, OpenAI, Gemini, or Cartesia with your own key after a cost estimate you approve. A markup editor finds the dialogue, assigns lines to speakers, and lets you fix mistakes and listen before committing to a ten-hour render. Every fragment is listened back to with Whisper and re-read until the best take survives, while a crash-safe journal means a stopped render resumes where it left off and edited chapters redo only what changed. The finished book arrives as one chaptered M4B with cover and metadata, or one MP3 per chapter, loudness-normalised and ready for any player. 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.

big-AGI is an open-source generative AI workspace that provides a unified, local-first interface for orchestrating multi-model reasoning, automated code execution, and custom persona workflows across private infrastructure. Users query multiple large language models simultaneously through the Beam scatter-gather engine, which prompts independent AI systems in parallel, compares candidate completions side by side, and merges optimal passages into a single refined response. Knowledge workers assemble tailored AI personas equipped with specialized system instructions, custom temperature settings, and predefined document context to handle domain-specific tasks ranging from architectural design reviews to legal contract analysis. The application renders rich multimedia outputs including interactive Mermaid sequence diagrams, LaTeX mathematical formulas, syntax-highlighted code blocks with live execution previews, and AI-generated image generation canvases. Teams integrate local inference servers like Ollama and LocalAI alongside commercial API endpoints to route confidential datasets strictly through internal networks while monitoring per-prompt token usage and operational latency. Users attach complex PDF documents, spreadsheets, and source code repositories for automatic parsing and semantic retrieval, while local-first storage engines ensure private chat transcripts and custom presets remain encrypted on host drives. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

37Studio is a self-hosted AI video studio and social media desk that turns a short brief into on-brand videos, posts them to nine social platforms, and drafts replies to the messages that come back. Paste a company website and it builds a brand library of logos, photos, fonts, and colours, plus a knowledge base every later video and reply draws on. An editor agent builds each video as an animated composition, checks its own rendered frames, and takes revision requests in plain words. The same workflow yields hook reels, captioned clips, explainers, podcast clips, promo ads, and thumbnails, and any finished video can become a template. A two-hour recording becomes a shelf of short clips: transcription runs locally in about 100 languages at no cost, and YouTube or Drive links import directly. Publishing reaches Facebook Pages, Instagram, YouTube, TikTok, LinkedIn, X, Pinterest, Bluesky, and Mastodon in one action, now or scheduled, each with its own caption. Autopilot goes further: state a content plan in one sentence and a fresh video is made before every slot, waiting for one-click approval. Messenger, Instagram, and WhatsApp messages and social comments land in one inbox, with replies drafted in the customer's language under rules each brand sets. Exact AI spend shows on every project, and an MCP server lets your own AI tools run the studio. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.