With 12,800 GitHub stars and backing from the same developer who created ControlNet, Stable Diffusion WebUI Forge replaces Automatic1111's inference backend with a dynamic GPU memory management system that runs SDXL 30-75% faster while consuming significantly less VRAM — enabling 1024x1024 generation on 6GB cards where A1111 requires 8GB or more. The Gradio 4 interface provides txt2img, img2img, inpainting, and outpainting workflows with a Forge Canvas supporting pressure-sensitive input from Wacom tablets and Microsoft Surface devices. Native Flux.1 model support loads Flux Dev and Schnell checkpoints using BitsandBytes NF4 and FP8 quantization for deployment on consumer GPUs without model splitting. Built-in ControlNet integration includes all preprocessors — Canny, Depth, Normal, OpenPose, MLSD, Scribble, Segmentation, Tile, and IP-Adapter — without requiring separate extension installation. The extension ecosystem maintains full compatibility with popular Automatic1111 extensions including Adetailer for face enhancement, After Detailer, Regional Prompter, and Dynamic Prompts. LoRA loading supports standard, LyCORIS, and DoRA formats with automatic weight detection. The API provides RESTful endpoints for txt2img, img2img, extra single/batch processing, and progress monitoring enabling headless batch generation. Deploy via one-click installer package, Python virtual environment, or Docker with NVIDIA GPU passthrough. 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.

Design a website on a canvas, manage its content in spreadsheet-style tables, and publish plain HTML, all from one self-hosted Instatic server. Designers see several breakpoint frames side by side, or switch to live mode and edit one full-size page in place. A built-in design system expands one brand color into a full shade scale, generates fluid type and spacing scales, and writes the utility classes into a single small stylesheet. Reusable Visual Components take typed parameters and named slots, templates set site-wide or per-post-type layouts, and loops repeat a design over posts or media. Editors work in custom post types and data tables, and posts move through draft, scheduled, and published states. Forms on the site save their submissions to tables of your own. An AI agent can do the building, placing real, editable nodes on the canvas using Claude, OpenAI, OpenRouter, or Ollama with your own key, and an MCP connector lets Claude, ChatGPT, and other remote agents work on the site too. Super Import converts a whole static site into pages, styles, tokens, and media. Teams get roles built from 38 capabilities, TOTP two-factor sign-in, and an append-only audit log, plus site branches with private copies, shareable preview links, and merge review. Everything published is baked to plain HTML and CSS on disk. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Point Sourcebot at your GitHub, GitLab, Bitbucket, Azure DevOps, Gerrit, or Gitea repositories and get regex, symbol, and filtered search results in under a second across thousands of repos and branches. Backed by Y Combinator with production deployments at NVIDIA, Shutterstock, SeatGeek, Arista, and Red Hat, the Zoekt-powered engine deploys as a single Docker container with zero external data transmission. Ask Sourcebot connects reasoning models like Claude Opus to your entire codebase, enabling natural language questions that return structured answers grounded with inline citations and navigable code snippets, backed by automatic tool calls that search code, follow references, and read files across all indexed repositories. Ask connectors extend this to Jira, Slack, Linear, and Confluence via MCP, pulling external context alongside code for debugging and documentation. IDE-level code navigation provides goto definition and find all references across repository boundaries without local cloning. The built-in file explorer renders any indexed file with syntax highlighting, breadcrumb navigation, and git blame showing per-line commit attribution. An analytics dashboard tracks daily, weekly, and monthly search activity. Permission syncing from GitHub and GitLab enforces access control lists so users only see repositories they are authorized to access. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. Other licensed.

ODS turns a GPU machine or server you already own into a complete private AI stack with a single install command, replacing a shelf of separate tools with one system that serves models, chat, agents, automation, and search from your own hardware. The installer reads your GPU, VRAM, memory, and disk, then downloads a GGUF model matched to that hardware tier, and a compact bootstrap model starts answering within minutes while the full model finishes downloading. From the web dashboard you watch every service's health, ports, and resource use, restart what misbehaves, and check storage and updates without touching a terminal. You chat with local models in Open WebUI, hand background work to the Hermes and Portal agents, and build automations in n8n that connect the stack to more than 400 other apps. Documents you add become searchable knowledge through Qdrant vector storage, so answers cite your files instead of the model's memory. SearXNG and Perplexica answer web questions without trackers or accounts, Whisper transcribes speech, Kokoro reads text aloud, and ComfyUI generates images, all on the same box. Every bundled service is an extension you can enable, disable, or replace, and a Privacy Shield scrubs personal data before anything reaches an optional cloud model through the LiteLLM gateway. 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 20,000 GitHub stars and adoption by companies building everything from telehealth platforms to AI voice agents, LiveKit is the most widely deployed open-source real-time communication server available. The Go-based Selective Forwarding Unit handles hundreds of concurrent participants per node with adaptive bitrate streaming, simulcast layers, SVC codec support for VP9 and AV1, and end-to-end encryption. Client SDKs span JavaScript, Swift, Kotlin, Flutter, React Native, Rust, Python, Unity, and ESP32 embedded devices, while server-side APIs cover Node.js, Go, Ruby, Java, Python, Rust, PHP, and .NET. The Agents framework enables building AI-powered voice and video applications — real-time speech-to-text, LLM-driven conversations, and computer vision pipelines — running as server-side participants in any room. Egress records sessions to S3-compatible storage or streams to RTMP endpoints, while Ingress pulls external feeds from OBS via RTMP, WHIP, or SRT into LiveKit rooms. The SIP bridge connects traditional telephony to WebRTC rooms for hybrid conferencing. JWT-based authentication, webhook notifications, room-level moderation APIs, and selective subscription give operators granular control. Deploy as a single binary for development, Docker Compose for production single-node, or Kubernetes with the official Helm chart for distributed multi-region clusters using Redis for state 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.

Oh My CPA gives a CLIProxyAPI gateway a proper control room, where providers, OAuth credentials, client keys, model routing, and the cost of every request are managed and watched from one self-hosted console. You add providers such as Codex, Claude, Gemini, xAI, DeepSeek, Vertex AI, and OpenAI-compatible services, each with credentials, retry and error policies, priority, weight, and an enable switch the gateway actually enforces. OAuth accounts are signed in from the console, with quota window readings, refresh schedules, and per-credential model aliases kept next to the keys they belong to. Client keys can be created, named, and revoked, and those names follow the traffic into request records and filters so you always know which key spent what. The dashboard follows request volume, token throughput, cache hit rate, and cost from the last fifteen minutes out to ninety days, with a year-long token heatmap for the long view. Insights compare keys, models, providers, and credentials against the previous period, while the live routing view shows which credential each request travelled to and whether it was rerouted. Every request stays searchable, with duration, time to first token, token breakdown, and the raw log in a detail drawer. A playground tests any routed model with text and images before your users do. 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 2,700 GitHub stars, Auto Company is the first open-source framework that runs a fully autonomous AI company 24/7 — 14 specialized agents modeled after Jeff Bezos (CEO strategy), Werner Vogels (CTO architecture), Charlie Munger (critical analysis), DHH (full-stack engineering), Kelsey Hightower (DevOps), Seth Godin (marketing), and eight more domain experts collaborate through dynamic squad formation to ideate products, write code, deploy infrastructure, and execute marketing campaigns without human intervention. The five-layer architecture separates execution, orchestration, cognition, workflow routing, and observability, while the consensus memory pattern uses a single markdown file as a relay baton between cycles — no vector databases, no Redis, no embeddings required. A bash loop invokes Claude Code or OpenAI Codex CLI every 30 seconds, each cycle selecting 2-5 agents from the 14-person pool based on task context. Over 30 reusable skills handle specialized tasks from frontend design to competitive analysis and deployment automation. Circuit breakers trigger cooldown after consecutive errors, rate-limit detection auto-sleeps on API throttling, and sandbox rollback protects against destructive changes. The Python-powered web dashboard displays real-time cycle status, cost tracking per cycle averaging under $2, and agent activity visualization, with CLI control via make start, stop, monitor, pause, and resume. Supports macOS via launchd, Windows via WSL with systemd, and native Linux deployment. The npx create-auto-co command scaffolds a new AI company in seconds. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Give your coding agents a board they can work, not just read: Kanzo is a self-hosted kanban board where you and your agents move the same tasks through the same columns at the same time. Tell an agent to take the next task and it moves the card to doing, comments as it works, and leaves the result where you can read it in the browser. Projects follow the code automatically: the agent finds the right board from the Git remote of the repository it is working in, and you can link more repositories to a project from its menu. Press n to add a task, search every project with a slash or Command-K, paste an image straight into a card or comment, and park half-formed ideas in an optional Backlog column that agents leave alone until you promote them. The whole board is one folder, and a private Git repository you own keeps it in step across a laptop, a desktop, and a Raspberry Pi, with conflicts resolved by choosing which side to keep. Statuses are yours to rename in the config file, the board exports cleanly to Markdown or JSON, and one click in the sidebar installs updates and restarts the 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.

Type a sentence like 'draw a seaside lighthouse under moonlight, with a small sailboat and stars' and Draw Agent Studio sketches it on a live canvas you can then keep editing by chat. Follow-up messages move objects, change colors, delete elements, and undo or redo steps, so refining a diagram becomes a conversation instead of a wrestling match with shape handles. The same canvas accepts direct manual work: select and drag shapes, draw freehand with the pen, or drop text onto the page to finish details the model missed. Researchers and writers use it to build flowcharts from a paragraph of method notes, grouping stages, adding quality checks and feedback loops, and restructuring sections on request. Canvases save automatically as you work, and finished pieces export as PNG, JPG, WebP, or SVG images, or as editable Excalidraw files for further hand editing elsewhere. You bring your own model connection, choosing OpenAI, Claude, Gemini, Azure OpenAI, Ark, DeepSeek, Kimi, Groq, OpenRouter, Bedrock, Vertex AI, or a local Ollama or OpenAI-compatible endpoint. A built-in connection test sends a real image and verifies recognition and tool calling before you save, and your API keys stay encrypted on the server rather than in the browser. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

OpenGrokBot gives you always-on AI teammates that live on your own hardware, each with a computer of its own. Every teammate is a folder with a persona and hard boundaries, a thread in your sidebar, and a contained machine with its own browser profile, workspace, and persistent memory that survives between asks. You manage the crew from a workbench-style web client: message one teammate or the whole group, watch its browser screen live, set routines like a morning digest, and check what each one used today. The safety model is the point: credentials live inside the teammate's own browser profile, so at a login wall it asks you to take over its screen instead of asking for a password; standing instructions change only through a diff you approve; and a teammate cannot approve its own holds. Teammates hand work to each other under an allowlist with a hop limit, optional daily token ceilings stop spending for the rest of the day, and a stop button kills even a shell command mid-flight. Computers can be a Docker container per teammate, or Docker-free local browsers with sandboxed commands. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Doca puts rich text, Markdown, spreadsheets, slides, and an infinite canvas under one login and one permission model, giving individuals and small teams a self-hosted workspace for writing together. Every format supports real-time co-editing with presence, comments, saved history, and manual snapshots, and rich text and Markdown documents can be restored to an earlier version. Documents live in knowledge libraries with tree navigation, invitations, inherited permissions, share links, and trash, while personal files and shared folders sit on local disk or S3-compatible storage. Knowledge books go further: they subscribe to sources, run an editable workflow, keep source evidence, and route results through human review. A personal AI assistant, powered by whichever model you configure, searches authorized documents, reads PDF and Office attachments, edits images, and prepares browser drafts. MCP services let external AI clients such as Codex use those tools under your permissions. Sign in with a password, OIDC, Google, GitHub, WeChat, or QQ, review registrations before they go live, and send webhooks to other systems. A plugin SDK and marketplace add business modules, and a browser extension clips pages into documents. The interface ships in Chinese and English. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Imp runs large AI chat models privately on one NVIDIA RTX 50 or RTX PRO graphics card, exposing them through OpenAI and Anthropic compatible APIs plus a built-in browser chat. Start it with a single Docker command, point it at a model, and the chat opens in your browser with saved conversations and a live readout of generation speed. Coding agents such as Claude Code and Codex connect by changing one base URL, so your editor talks to the model on your own hardware instead of a rented cloud endpoint. Tool calls, structured JSON output, streaming responses, and reasoning models all work over the wire, and requests can be protected with an API key, per-IP rate limits, and concurrency caps. Load GGUF files you already have or NVFP4 and FP8 SafeTensors checkpoints straight from Hugging Face with no conversion step before the first answer. When a model is bigger than the card, mixture-of-experts weights stay in system RAM while the busiest experts are cached on the GPU, so a 123.6 GiB model still answers from a 32 GB card. Supported models can also read images alongside text, and tokenize, health, and model listing endpoints make the server easy to wire into scripts and monitors. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Generic AI writing sounds like nobody in particular; BullFlow writes from your own company knowledge instead. It first builds a private knowledge base from your documents, images, audio, and video plus structured records for your company, brand, products, customers, and cases. Ingestion runs entirely on local open models: OCR reads scans, semantic splitting and chunking prepare text, and hybrid vector plus full-text search retrieves passages with their sources and relevance scores shown under every answer. A creation agent then works in one conversation: it searches the knowledge base, drafts articles with images embedded in the text, generates image sets or short videos, and exports finished pieces as PDF or Word. Output adapts to where it is going, long-form articles for article platforms, multi-image posts with matching copy for image feeds. A separate distribution gateway sends one finished piece to many accounts across Chinese and international social platforms, checks account health on a schedule, and returns publish results and metrics by webhook. Around all of that sits a commercial shell: multiple tenants with isolated data, roles from super admin to finance, credit billing measured per token, image, and second, subscriptions, invoices, referral commissions, and a conversion funnel in the operations backend. Scheduled rules can generate and publish on a timetable with nobody watching, and notifications report each completion or failure. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Instead of juggling a chat window, a folder of reference images, and a notebook of half-remembered prompts, Infinite Canvas puts the whole image-making process on one zoomable board. Drop in text, image, video, and generation-settings nodes, then wire them together so every result stays connected to the prompt and references behind it. Add one or several OpenAI-compatible endpoints, choose default text, image, and video models, and set image count, aspect ratio, quality, and transparent backgrounds per node. Batch results arrive as linked nodes that remember their prompt, model, and dimensions, so any of them can be retried later with the same settings. A prompt library searches seven built-in sources plus your own JSON sources and inserts the winner straight onto the board. An asset shelf keeps reusable images, clips, and audio within reach. Projects can be duplicated, exported, and synced between devices over WebDAV. Want a helper? A local Canvas Agent lets Codex read the active board and edit it through MCP, with approvals and permissions shown in a side panel. Plugins add node types, inspectors, and toolbar actions. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

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

The most feature-complete open-source alternative to Google's NotebookLM — a self-hosted research platform where you upload PDFs, videos, audio files, and web pages into organized notebooks, then chat with your content, generate multi-speaker podcasts, and run semantic search across everything without sending a single byte to Google's servers. The podcast engine supports 1-4 fully customizable speakers with backstories, personalities, and expertise profiles, generating professional audio dialogue through OpenAI, ElevenLabs, Google TTS, or completely local text-to-speech via Kokoro for maximum privacy. Content processing uses token-based chunking with RAG-powered retrieval grounded in your uploaded sources, while both full-text keyword search and semantic vector search via SurrealDB enable conceptual discovery across all notebooks. The 18+ supported AI providers include OpenAI, Anthropic, Google Gemini, Groq, Ollama, LM Studio, and more — configurable per task so you can route cheap models to summarization and powerful models to analysis. Content transformations extract insights, generate summaries, create study guides, and produce structured outputs from any source material. The MCP integration connects Open Notebook to Claude Desktop, VS Code, and other MCP clients for seamless workflow integration. A full REST API on port 5055 enables complete automation of notebook management, source upload, and podcast generation. Deploy via Docker Compose with the application container, SurrealDB v2 on RocksDB, and optional TTS containers. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Keep is an open-source AIOps and alert management platform built with Python FastAPI and Next.js. It provides a single pane of glass for monitoring alerts from 110+ integrations, alert deduplication, correlation, enrichment, and filtering, YAML-based workflow automation similar to GitHub Actions, AI-powered correlation and summarization, and customizable dashboards for incident management. With 12,100+ GitHub stars, Y Combinator backing, and an Elastic partnership, Keep is the open-source AIOps platform that centralizes alert management across your entire monitoring stack into a single customizable dashboard. Alert deduplication identifies duplicate notifications across providers, correlation groups related alerts into incidents based on rules or AI-powered semantic analysis using pluggable LLM backends supporting OpenAI, Anthropic, and local models via Ollama, and enrichment adds context from external sources like CMDBs and databases. Workflow automation follows a GitHub Actions paradigm with declarative YAML files defining triggers, conditions, and actions that can query MySQL, update Jira tickets, send Slack messages, execute Python scripts, or call REST APIs. Authentication supports no-auth, database, Auth0, Keycloak, OAuth2 Proxy, Okta, and OneLogin. The Common Expression Language enables advanced alert querying, slicing, and rule-based grouping to reduce noise. On RepoCloud, deploy Keep on a dedicated VPS with Docker Compose, root SSH access, and complete control over your alert infrastructure, all under the MIT license.

Thirteen-plus LLM providers, one unified client: NextChat (formerly ChatGPT-Next-Web) is an open-source AI chat interface built on Next.js that spans OpenAI GPT-4, Anthropic Claude, Google Gemini, DeepSeek, Groq, Azure endpoints, and self-hosted backends like Ollama, LocalAI, and RWKV-Runner. Its defining trait is minimalism - the first screen loads in about 100 KB, the desktop client is roughly 5 MB, and there is no database or user system to operate; chat history lives locally in the browser with optional WebDAV or UpStash Redis sync. The Mask system saves reusable prompt-template personas you can share and debug, long conversations auto-compress to fit context windows, and Markdown rendering covers LaTeX, Mermaid diagrams, and code highlighting with streaming responses. Plugins add web search and calculators, MCP support enables external tool calling, and Artifacts previews generated content in a separate pane. Ships as a web app, Docker image, and Tauri desktop builds for Windows, macOS, and Linux, translated into 20+ languages. MIT-licensed.