Running a single AI agent is straightforward; running a team of specialized agents that delegate tasks, share memory, and coordinate through structured workflows requires an orchestration layer, and that is exactly what SwarmClaw provides. Define a hierarchy of agents in an org chart where a Coordinator (your CEO agent) delegates research tasks to a Researcher, coding tasks to a Developer, and design tasks to a Designer, each configured with its own LLM provider, tool permissions, and skill set. The Task Board presents a Kanban view of all work items across Backlog, Queued, Running, and Completed columns, with each task card showing its assigned agent, tags, due dates, and approval gates that pause execution until a human reviews and approves. Agents execute work using built-in tools for file operations, shell commands, browser automation, and persistent memory, plus any MCP server you connect via stdio, SSE, or streamable HTTP transport. Durable structured sessions support branching logic, repeat loops, parallel branches with explicit joins, and restart-safe run state that survives crashes without losing progress. Over 23 LLM providers ship built-in: Claude Code CLI, OpenAI, Anthropic, Google Gemini, DeepSeek, Groq, Mistral, xAI Grok, Fireworks, Ollama, and more. Connectors push messages to Discord, Slack, and Telegram, while cron schedules and webhooks trigger agent runs automatically. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Before a language model learns from your data, someone has to label it well; Argilla gives AI engineers and domain experts a shared workspace to label, review, and refine the datasets that fine-tune language models and train NLP pipelines. You build each dataset from the Python SDK, mixing text, chat, and image fields with the exact questions your task needs: single-label classification for intent detection, span questions for named entities, ratings for response quality, rankings for preference tuning, or free text for corrections. Annotators then work through records in a focused labeling interface where model predictions already sit attached as suggestions, turning most reviews into a fast confirm-or-correct decision instead of a blank-page exercise. Full-text search, metadata filters, and status filters slice a hundred thousand records down to the ones needing attention, while vector-based semantic search finds lookalike examples, near-duplicates, and the disagreement hotspots where guidelines need sharpening. Dataset owners watch completion progress, manage who has responded to what, and split work across workspaces with owner, admin, and annotator roles for each team or client. Finished datasets export with responses, suggestions, and metadata intact, locally or straight to the Hugging Face Hub, ready for fine-tuning and evaluation runs. 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.

Nowen Note is a self-hosted knowledge base where your notes, tasks, daily journals, and mind maps live in one private workspace you control. One tree holds folders, rich-text documents, and Markdown notes side by side, with drag-and-drop ordering, unlimited nesting, colored tags, pinning, and full-text search across everything. Each note can switch between a rich-text editor and Markdown with live preview, split view, outlines, tables, code blocks, math formulas, diagrams, comments, and version history. Connect the AI provider you prefer, such as an OpenAI-compatible API, Gemini, DeepSeek, or local Ollama, to continue drafts, rewrite passages, translate, summarize, and ask questions answered from your own notes. Tasks get list, board, calendar, and timeline views with dependencies, recurring rules, reminders, and templates, while daily journals capture short entries, moods, and photos and roll them into AI weekly and monthly reviews. Teammates edit together in real time, and folder-level permissions, passwords, allow and deny rules, share links with expiry dates, and guest comments decide exactly who sees what. Imports arrive from Obsidian, SiYuan, Word documents, web pages, and plain Markdown, attachments can live on local disk or S3-compatible storage, and scheduled backups travel to email or WebDAV. Keep working offline with a cached workspace that syncs when you reconnect, clip pages from the browser extension, and connect other tools through the OpenAPI, SDK, webhooks, and MCP server. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. GPL-3.0 licensed.

In seven wizard steps, PandaWiki sets up a product docs, manual, FAQ, or blog site whose built-in AI answers visitors using only your own content. Those visitors can chat with an assistant that cites its sources and accepts image questions, or switch to a docs-only search that lists ranked pages with summaries. Publishing stays under control: each document has three switches, visible in navigation, reachable by URL, and answerable by AI, and nothing appears or gets learned until it is published. Authors write in a Markdown and HTML editor, or import from URLs, RSS and Atom feeds, sitemaps, offline .txt, .md, .xlsx, .docx, and .pdf files, Notion, Yuque, SiYuan, Wiki.js, Feishu, Confluence, and DingTalk. Pages export to Word, PDF, or Markdown. The wizard covers models, domain, HTTP or HTTPS ports, import, publishing, answer testing, and page decoration. One knowledge base can also feed a web widget and DingTalk, Feishu, WeCom, and Discord bots. Administrators get a dashboard of visits, questions, visitor regions, hot documents, and referring domains. Chat models come from Baizhi Cloud, DeepSeek, OpenAI, or Ollama, while vector and reranking models are built in. The open-source edition covers one wiki site, 300 documents, and one admin, and its console and documentation are in Chinese. 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 1,200+ GitHub stars since its April 2026 launch, Arkon provides an enterprise-grade knowledge management layer that turns scattered organizational documentation into AI-accessible structured context. The platform runs as a centralized MCP server, compiling your SOPs, policies, technical docs, and institutional knowledge into a versioned wiki with draft-approval workflows, then serving that wiki to Claude Desktop, Claude.ai, Cursor, and any MCP-compatible client through a single permission-scoped endpoint. OAuth 2.1 with PKCE authentication eliminates manual token management — employees authenticate through a browser login while the system discovers endpoints automatically via RFC 8414. The RBAC v2 system supports custom roles with granular permissions, department-scoped AI Skills, workspace isolation, and comprehensive audit logging so every query and access event is traceable. RAG retrieval powered by pgvector embeddings enables AI clients to search across all organizational documents with source attribution, while the AI Skills system lets teams define reusable instruction sets scoped to specific departments or roles. The architecture runs seven Docker containers coordinated by Compose: PostgreSQL with pgvector for embeddings and metadata, Redis for caching, MinIO for document storage, a FastAPI backend, two ARQ async workers for embedding generation and document processing, and a Next.js frontend portal accessible on port 3119. API keys are encrypted at rest with Fernet, and no telemetry leaves the deployment. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. PolyForm Internal Use 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.

With 3,100+ GitHub stars, CyberScraper 2077 replaces brittle CSS selectors and XPath queries with natural language data extraction powered by Large Language Models. Users paste a URL, describe the data they want in plain English, and the AI extracts structured results from any website — no HTML parsing knowledge required. The tool supports three LLM backends: OpenAI GPT models for maximum accuracy, Google Gemini for cost-effective extraction, and local Ollama instances for fully private scraping where URLs and data never leave your server. Built on Python asyncio with Playwright browser automation, it handles concurrent page fetching with content-based and query-based LRU caching to minimize redundant API calls. The Streamlit web interface runs on port 8501 and provides one-click export to JSON, CSV, HTML, SQL, Excel, and direct Google Sheets upload. Tor network integration routes requests through onion routing for anonymous scraping of both clearnet and .onion hidden service sites with automatic circuit management and stream isolation. Stealth mode randomizes user agents, manages cookies, and controls JavaScript execution timing to bypass bot detection systems. Multi-page scraping navigates through paginated results with automatic URL pattern detection. Docker deployment packages all dependencies including Playwright browsers into a single container. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Tela keeps a team's documentation as canonical markdown in a self-hosted wiki that AI agents read, search, and write alongside humans through a built-in MCP server. People edit together with live multi-cursor collaboration, threaded comments, backlinks, and full revision history, so every page shows who changed what and why. PostgreSQL full-text search works immediately, and adding an embedder unlocks semantic retrieval and grounded ask-your-docs answers that cite their sources. Connect Claude, Cursor, or another MCP client with a personal access token and the agent can search the wiki, draft and patch pages, answer comment threads, build spreadsheets with real formulas, and assemble presentation decks exportable to PDF and PPTX. Atlas, the built-in documentation engine, points at a git repository or Jira project and drafts cited wiki pages, then keeps them fresh as the sources change. Teams organize work into spaces, invite members by email, and flip any space public to publish a login-free blog with per-author home pages. Content syncs over WebDAV and exports to zip or PDF, and optional AI features run against your own endpoint or a bundled local Ollama profile, so nothing leaves your server unless you wire it up. 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.

Platypus gives a whole team always-on AI agents that reason, call tools, and keep working on your own servers while everyone is offline. Build an agent once by choosing a provider and model, writing its instructions, and capping its tool-calling loop, then reuse that preset across chats and scheduled runs. Agents load reusable Skills on demand and delegate specialist work to sub-agents that appear to the parent as tools. Connect local and remote data through Model Context Protocol servers, or expose an agent to outside agents and chat platforms through A2A endpoints with a token per client. Triggers run agents on a cron schedule, as one-off jobs, or when workspace events such as a card moving on a board occur, and every run records its result. Kanban boards give agents work they can move and update themselves, while notifications and HMAC-signed webhooks push board and workspace events into your own systems with filtering and retries. Facts and preferences are extracted from conversations in the background and injected into future chats, so returning users are remembered. Sandbox backends give agents shell and filesystem access inside an isolated per-workspace environment instead of the host. Organizations and workspaces keep each team's agents and data separate, and blueprints package shared agents, skills, MCP servers, and providers so a new workspace starts pre-equipped. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

OpenLLM serves any large language model as an OpenAI-compatible API endpoint from a single CLI command, handling model download, backend selection, quantization, and port binding automatically. It supports the full spectrum of popular models including Llama 3.3, Qwen2.5, DeepSeek, Mistral, and Phi3, choosing between vLLM and PyTorch inference backends based on hardware capabilities. When vLLM is available, continuous batching with PagedAttention achieves up to 23x throughput improvement over naive serving, while GPTQ and bitsandbytes quantization reduces memory requirements for GPU-constrained deployments. The server exposes a RESTful API on port 3000 with full OpenAI client library compatibility, enabling drop-in replacement for commercial providers in any application using the standard chat completions format. A built-in web chat UI at the /chat endpoint provides immediate interactive testing without external clients. Custom model repositories allow teams to maintain private catalogs of fine-tuned models alongside the default repository that tracks the latest releases. Deployment workflows generate production-ready Docker images automatically, with Kubernetes manifest support for orchestrated scaling. Native integration with LangChain and LlamaIndex supports RAG pipelines, Transformers Agents enables tool-calling workflows, and HuggingFace Hub handles model discovery. Server-Sent Events enable real-time token streaming across all API endpoints. Backed by BentoML's production ML infrastructure. 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.

Before any AI model reads a single customer message, Obsei has already stripped out the names, email addresses, card numbers, and ID numbers hiding inside it. Obsei pulls in what customers are saying from App Store and Google Play reviews, Zendesk, Freshdesk, and Intercom tickets, GitHub issues, surveys, YouTube comments, Bluesky, RSS feeds, SQL databases, and even Gong call transcripts. Every record is pseudonymised on the way in and stored in an encrypted database that never phones home. Then the labelling starts: sentiment, intent, language, and your own custom questions, each answered with a confidence score by a zero-shot classifier running locally on your machine, or by an LLM you choose through your own keys. Answers the model is unsure about are escalated to a stronger model or queued for a human instead of being silently wrong. Related complaints roll up into stable themes with week-by-week trends, and anything mentioned by fewer than five people stays hidden, so individuals cannot be picked out of a chart. When a theme spikes, alerts and digests land in Slack, and individual findings can be routed straight into Jira, Linear, or GitHub issues. Your analysts browse it all in the built-in Studio, and your AI agents can ask questions over MCP and get cited, redacted evidence back, with any action they propose waiting for your approval. 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.

Sketch a wireframe, get working code: Draw a UI turns hand-drawn layouts into web interfaces. It pairs the open-source tldraw canvas with an OpenAI vision model: you sketch a layout - boxes, labels, buttons, arrows, whatever communicates the idea - select the drawing, and click Make Real. The app snapshots your selection as a PNG, sends it to the vision API with instructions to return a single HTML file styled with Tailwind CSS, and renders the result in an iframe directly on the canvas next to your sketch. The loop is iterative: annotate the generated prototype or redraw parts of it, select both the sketch and the previous result, and generate again - the model receives the earlier HTML as context and produces an updated version. Built by Figma engineer Sawyer Hood as one of the first viral GPT-4 Vision demos and the basis for tldraw's "Make Real", it is a Next.js app that runs against your own OpenAI API key. Self-hosting matters here: the upstream demo ships without authentication, so a private deployment keeps your API key from being drained by strangers. MIT-licensed.

Designed for developers on the go, Yep Anywhere turns any smartphone browser into a full-featured control center for supervising, steering, and reviewing autonomous AI coding agents. Operators can monitor live execution across multiple active projects simultaneously without sitting at a desktop terminal. Real-time reasoning feeds. Instant push alerts for permission prompts. One-tap tool approvals. Developers can unblock pending tasks mid-turn, redirect active workflows, or queue sequential follow-up prompts for automatic delivery at the next safe milestone. An integrated source control viewer displays syntax-highlighted working-tree and commit diffs, allowing reviewers to attach line-level comment bundles directly back into the agent context. Mobile voice transcription lets users dictate instructions straight into running sessions, while photo library integration makes uploading bug screenshots effortless. All agent credentials, CLI configurations, and repository data remain private on the host server without requiring third-party cloud database accounts or proprietary device pairing. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

This is a marketing operations control center that replaces fragmented CRM, outreach, content, and analytics tools with a unified self-hosted interface designed for AI agent-assisted go-to-market teams. The CRM module manages leads through a configurable pipeline funnel with stages from New through Sequenced, Replied, Interested, and Booked, tracking source attribution, industry segments, company size, lead quality scores, and LinkedIn URLs per contact. Outreach sequencing supports email campaigns with pause controls, audit endpoints, suppression workflows, and engagement tracking. The content operations surface provides calendar views, content item management, performance metrics, and approval queues for editorial control. Analytics and KPI dashboards show impressions, engagement, and send volumes over configurable time periods, with optional connectors to Plausible, Google Analytics 4, X, and LinkedIn for cross-platform reporting. The OpenClaw-native agent runtime enables dynamic agent and squad discovery, workspace management, session monitoring, and communications surfaces. Automation scheduling uses cron job templates with OpenClaw-compatible schedule variants including cron expressions, every intervals, and at timestamps. The tech stack combines Next.js 16 App Router with React 19, Tailwind CSS 4, Recharts, and Zustand for state management. Authentication supports session cookies, API keys, and optional Google OAuth with role-based access controls. All state persists locally in SQLite via better-sqlite3 with no required external infrastructure. On RepoCloud, deploy Marketing Dashboard on a dedicated VPS with persistent SQLite storage, root SSH access, and complete control over your marketing operations data, all under the MIT license.

Browser Use Web UI lets you describe a web task in plain English and watch as an AI agent autonomously navigates pages, clicks buttons, fills forms, and extracts information without writing any automation code. Backed by over 16,000 GitHub stars, the Gradio-based interface supports 14+ LLM providers through a unified abstraction layer: OpenAI GPT, Anthropic Claude, Google Gemini, Azure OpenAI, DeepSeek, and local Ollama models are all configurable via dropdown menus without touching code or environment files. The BrowserUseAgent handles interactive single-task automation with step-by-step LLM decision-making and vision-based page understanding, while the DeepResearchAgent orchestrates multi-step research workflows using Langgraph state machines that spawn parallel browser instances with asyncio concurrency control. Custom browser support connects your existing Chrome profile to preserve logins, cookies, and sessions across agent runs, eliminating re-authentication overhead. Persistent browser sessions maintain complete interaction history between tasks for debugging and demonstration. The Docker deployment bundles Chrome, Playwright, and a VNC server in a single container, exposing the Gradio interface on port 7788 and a noVNC viewer on port 6080 for real-time observation of agent behavior. MCP integration via MultiServerMCPClient enables external tool access. Screen recording captures agent workflows as video for review and 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.

Describe an app in one sentence and sandboxd, a self-hosted AI app builder, has a coding agent build it in an isolated sandbox and hand back a live preview URL. Start from a blank prompt, a React, Next.js, Express, or FastAPI starter, or an imported public Git repo. Refine it in one persistent chat beside Preview, Code, Terminal, and Git tabs. Pick OpenCode, Pi, or Claude Code. Point OpenCode or Pi at local or remote OpenAI-compatible and Anthropic-compatible endpoints, LiteLLM gateways included. A proxy injects provider keys on the wire, so nothing secret lands in a sandbox. Did the agent get it wrong? Every task is checkpointed first, so one click reverts the turn. Snapshots, forks, and named versions keep known-good points to branch from. Edit files in the browser, review file-by-file diffs, commit, and push. Secrets are write-only and encrypted per app. Idle sandboxes sleep and wake on the next request. One modest server can host per-user previews, coding playgrounds, or an agent platform. The app library installs 80+ curated open-source apps, such as Ghost, n8n, Gitea, and Grafana, each in its own sandbox. Every console action is also a /v1 HTTP call with an OpenAPI spec. Upgrades back up the database, health-check the new version, and roll back on 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.

Vocero CRM turns WhatsApp into your sales floor, with a shared team inbox, a visual pipeline, and an AI agent that answers customers using only what your business taught it. Incoming messages land in a three-column inbox within two seconds, showing sent, delivered, and read states, enforcing the official 24-hour window, and offering approved templates when it closes. Every person who writes becomes a contact automatically and enters a Kanban pipeline you can rename, where dragging a card, adding notes, or archiving a lead takes seconds. The AI agent learns from question-and-answer pairs and free-text knowledge blocks, and answers only from what it knows. It bundles message bursts into one reply and hands the conversation to a human whenever the customer asks or the rules say so. Before the agent ever meets a real customer, the Laboratory sends six simulated customers at it, from the decided buyer to the angry one, and an independent judge scores each conversation from 0 to 100 with findings and one-click fixes you can re-test after every change. Owners create team accounts, message templates sync their approval status from Meta, and WhatsApp tokens sit encrypted at rest while every customer record stays on hardware you 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.

Once a voice agent is imported or built, Lampline connects it to a phone line, sends an AI caller to grade real calls, and keeps it all on your own server. Start by importing a Dialogflow CX or CX Agent Studio export along with a report of anything to check, or build fresh in a drag-and-drop builder that mixes LLM steps with scripted pages for exact lines and form fields. Next, pick one of 20 model providers, including Claude, OpenAI, Gemini, Bedrock, Groq, and DeepSeek, or run Ollama with local speech and no API keys. Test by chat or microphone while each step lights up, and let agents call HTTP and MCP tools and save records in collections of their own. Then connect callers through Twilio, Telnyx, or any SIP trunk, PBX, or session border controller via jambonz, with transfers to a person that carry the call's details as SIP headers. Finally, evals phone the agent over a real line, where an AI Test Caller brings background noise, accents, and interruptions, grades each transcript check by check, and reports typical and p95 response times as callers hear them. Each agent stays a folder of YAML and Markdown that you can review in git and lint or test with the vk CLI. 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.