For a solo founder, FounderOS is one live dashboard where AI-assisted departments take care of the busywork of running a company. Home shows system health, agent counts, and inbound message volume, plus a free-text bar that turns a sentence into a task, a note, or an instruction for a named agent. Comms merges email, Slack, WhatsApp, and meeting threads into one inbox with unread counts, needs-reply flags, snooze, mark done, and reply starters that include a drafted answer. Funnel tracks touches, new leads, conversions, and revenue by source, with a pipeline from first touch to converted client. Agents shows a roster of AI seats and a conductor that delegates work, with runs by seat, open task lanes, and the items waiting on you. Tasks adds in-progress, overdue, and runtime stats beside a schedule. The Knowledge Visualizer maps notes, skills, agents, and accounts into a network with matrix, timeline, ranking, and findings views. Clients, Brand Deals, Finances, Social, and Content Lab sit in the same sidebar, and every integration stays optional until you connect it. A bundled demo company makes exploring easy. Creators, small agencies, and one-person businesses get a daily operating view in a single tab. 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 $50M+ from Benchmark, Y Combinator, and NVIDIA with 800+ contributors and 39,000+ GitHub stars, MindsHub Cowork is the unified AI workspace where open-source models handle entire projects — research, reporting, internal tools, scheduled operations — and return finished, shareable deliverables. The platform runs two interchangeable open-source agent harnesses, Anton and Hermes, swappable from a dropdown without losing context. A built-in Model Router pre-wires 25+ models spanning Anthropic Claude, OpenAI GPT, Google Gemini, DeepSeek, Qwen, Kimi, Grok, and MindsHub Air with automatic failover — no per-provider API keys required. A secure credentials vault connects BigQuery, PostgreSQL, Salesforce, HubSpot, Zendesk, Gong, Gmail, Google Drive, Notion, Linear, Stripe, and Slack, keeping secrets scoped per connection so agents never see raw keys. Agent output becomes publishable artifacts — documents, dashboards, apps, and code — each deployable to a live shareable URL. Cross-session persistent memory, a reusable skill library, and a background scheduler supporting hourly, daily, and weekly cadences enable autonomous recurring workflows. The architecture separates a React/Vite frontend (shipping as both Electron desktop app and web SPA) from a FastAPI backend with a versioned REST API at /api/v1 covering conversations, projects, artifacts, schedules, and connectors. Self-host via Docker Compose with nginx on port 3000 and the API on port 26866, or deploy on-prem, in a VPC, or air-gapped. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Memoh delivers an open-source multi-agent platform where every AI agent gets its own computer — not a chat window but a fully isolated container with dedicated filesystem, desktop environment, browser, network stack, and persistent long-term memory that survives across sessions, days, and platforms. The containerd-based runtime ensures each bot operates in complete isolation with snapshot and data import/export capabilities. The memory engine uses LLM-driven fact extraction with hybrid retrieval combining dense embeddings via Qdrant, sparse vectors, and BM25, plus 24-hour context loading and automatic compaction — with Mem0 and OpenViking as drop-in alternatives. Ten communication channels connect agents to users through Telegram, Discord, Lark, QQ, Matrix, WeCom, WeChat, Email, Web UI, and group chats with cross-platform identity binding. MCP tool calling enables agents to interact with external services, while browser automation drives GUI workflows for web research and data extraction. Agent hosting supports running external coding agents like Codex and Claude Code inside Memoh workspaces via ACP with per-bot configuration. Scheduled tasks run without human triggers, and agents proactively reach out when needed. The web dashboard built with Vue 3 and Tailwind CSS provides streaming chat, tool call visualization, file management, model and provider configuration, and bot lifecycle management. Deploy via Docker Compose with PostgreSQL, Qdrant, sparse service, and the Go backend server. 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.

Open Net Worth is a self-hosted personal finance system where an AI agent named Lucius works a real multi-currency ledger, a zero-based budget, and an investment book through guarded write tools instead of merely describing your money. Record every account you own or owe, from bank accounts and cards to loans, retirement funds, and brokerages, then reconcile balances, split transactions, and review statement imports before anything books. Budget with Ready to Assign envelopes, category targets, and credit card payment tracking, or switch to a simple 50/30/20 split and project cash flow months ahead. Track holdings, buys, sales, dividends, tax lots, realized gains, options, and equity grants, with watchlists and price alerts for the positions you follow. Lucius can categorize transactions, reconcile accounts, build reports, and act in connected apps, and every tool carries a permission level you control, so sensitive changes pause on a confirm card before they land. Schedule automations for a daily briefing, a weekly report, or a bank sync, and save repeatable jobs as skills he follows again. Connect SimpleFIN, Plaid, Enable Banking, Alpaca, or Interactive Brokers, import from YNAB or Lunch Money, and bring an Anthropic, OpenAI, or local Ollama model. 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.

On a Doop design canvas every frame is real HTML, so Claude Code, Codex, Cursor, or any MCP client can design beside you as teammates watch every cursor and edit arrive live. Agents connect with one command or a one-click install and, once access is approved through OAuth, work as you and report their status and tasks on the canvas. The built-in Doop Agent has six roles, among them UX Lead, Copywriter, and Accessibility, picks up board cards and @mentions in comments, and runs on a connected ChatGPT subscription or an OpenAI, Claude, Gemini, or OpenRouter key. The editor covers frames, shapes, pen paths, rich text, flex layout, layers, pages, rulers, design tokens, and version history. Prototype mode wires clicks, hovers, and key presses to screen transitions, and the finished flow plays full screen or goes out as a shareable link. Marking a frame ready for dev can start an automation that queues agent steps, creates Linear tickets, or posts to Slack. Websites, live apps, GitHub repositories, and PDF pages import as starting points. Frames export as PNG, JPG, or PDF, or as public image links that re-render when the design changes. 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.

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.

A team of coding agents, run in parallel from your desk, your browser, and your phone: Vicoa is an agentic IDE and control center, so one developer can steer a whole fleet instead of babysitting terminal tabs. Run 40+ coding agents side by side in one workspace: Claude Code, Codex, OpenCode, Gemini, Cursor, GitHub Copilot, Kimi, and more are built in, and 30+ additional agents connect through the Agent Client Protocol. Each agent gets its own git worktree and branch, so several can change one repository without overwriting each other, and every session's status sits in one list. Connect Mac, Windows or Linux machines, a VPS, or a remote server, pick where each session runs, and bring existing subscriptions or API keys. Start a session at your desk and steer it from the iOS or Android app on the train: approve a step, answer a question by dictation, or review the live git diff and file tree from your phone, with push notifications when an agent needs a decision or finishes. Plan work on the task board and start a session straight from a task, schedule cron automations that pick work up on their own, and share a live session link so teammates can watch or prompt alongside you. Host the backend and realtime server yourself with Docker, or drive everything from the CLI. 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.

PandaDOS is a self-hosted control plane that turns Claude Code and Codex into long-running coding agents you direct through an issue queue from any browser, instead of babysitting a terminal. You file an issue with the outcome and acceptance criteria, and PandaDOS clarifies missing requirements, plans the work, picks the agent, and drives implementation, verification, and delivery in stages. Three approval levels, cautious, balanced, and automatic, decide which actions proceed alone; safe reversible steps continue automatically while destructive, irreversible, production, or secret-related decisions always come back to you. The browser workspace shows the real agent conversation, a native terminal, project files, Git history and diffs, and an execution summary, so you can inspect or intervene at any moment from a phone or laptop. Agents run on local or SSH-connected executor machines inside tmux sessions, and work sharing one repository is serialized while independent projects proceed in parallel without conflicting edits. Modules keep one assigned agent and durable project knowledge, so context from finished issues carries into the next task instead of evaporating when a chat ends. Teams can sign in through Feishu, ask the project manager questions in chat, and receive subscription notifications and approval cards on their phones. 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.

Describe the change in chat, and LoopForge opens a Docker sandbox, checks out your repositories, hands the work to specialist agent roles, and opens the pull request. That is the conversational path: a Main Bot coordinates planning, implementation, review, and testing roles, each with its own prompt, executor, model, rules, skills, and tools, and you can queue or steer messages mid-reply, then pause, resume, or take over a run at any point. When a way of working proves itself, you freeze it as an SOP: a visual canvas of agent steps, deterministic script steps, human gates, and sub-workflows that every requirement then follows in the same order with the same checks. Four built-in SOPs cover backend delivery, frontend delivery, product proposals, and bug fixes, and each one can be copied, edited, and versioned per project. A Needs review inbox collects every gate waiting on you, with per-node status, tool traces, logs, and artifact snapshots as the evidence behind each approval. Recurring AI tasks run on schedules with the same workspace and workflow access, and insights reports track engineering metrics and token costs per run and per conversation. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Production AI agents fail in quiet ways, and Latitude records every trace, session, and tool call so each failure can be found, grouped, and fixed. One line of telemetry from the TypeScript or Python SDK, or any OpenTelemetry exporter, sends traces from OpenAI, Anthropic, LangChain, LlamaIndex, CrewAI, and dozens of other providers and frameworks. Failing traces are clustered into signals with status, size, and trend, and flaggers and annotation queues let reviewers score outputs by hand. Evaluations are generated from those judgments and tracked with an alignment score. Semantic and exact-text search covers every trace, and saved searches, filters, and behavior groupings keep recurring questions one click away. Dashboards report cost per session, tool failure rates, and agent score across outcome, reliability, speed, and safety. Memory views show how an agent's stored memory changes over time, with diffs and the trace behind each edit. Monitors raise alerts, regression datasets replay fixes against the traces that failed, and Agent Dispatch hands the evidence to a coding agent. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

While you sleep, a crew of Claude Code agents in a single Docker container keeps building: you plant a mission, the farm splits it into sub-agents on their own branches, and only work that passes your tests ever lands in the repo. Open the farm in your browser and every agent is a pixel Claude walking its plot, tending a task at a terminal or napping when the budget says stop, with the quest log, mission board, and a hatchery for new agents a click away. Each account is paced against its real five hour and weekly usage, measured live, always leaving you twenty percent and never paying overage, and teammates' agents message each other and hand jobs to whichever account still has room. Talk to any agent from the Claude app on your phone, post quests, set schedules like weekday issue triage at nine, and watch live dashboards the agents maintain themselves. Whiteboards let you sketch while an agent draws back full Mermaid architectures for the whole farm to see, the farm's logged-in browser does website work as you, and Slack mentions, Blender scenes, and other models from GPT to a local Ollama all plug into the same queue. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Always-on AI teammates that each get a real computer of their own, with a browser, files and a terminal, working from your hardware instead of a vendor cloud: that is OpenSuperBot. You hire a teammate from the sidebar with a name and a one-line job, and it works inside its own sealed computer with a browser, shell and persistent workspace. At a login wall the bot asks you to take over its live screen and sign in once inside its own browser profile, so passwords never pass through the gateway. Group threads let you ask the whole room at once: everyone answers in parallel, the chief of staff closes with a dispatch table, and @names pick which teammates respond. Nothing leaves the workspace without your say-so, because outward actions stop at a draft-and-hold approval chip. Standing approvals cover repeat sends to one destination for an hour or a day, and money and bookings always ask. Memory is a visible file you control: tell a bot a rule and it posts the exact change as a chip, and forget removes it the same way. Routines come from plain conversation, so a daily digest, a secret webhook trigger or a quiet status-page watch can be scheduled in chat. Each teammate runs a model you pick, with daily token budgets and live step cards for every action. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

WebCodex gives ChatGPT, Claude, and other MCP clients a real development environment on machines you own, so an AI assistant can edit your actual repositories instead of a pasted snapshot. A self-hosted Server authenticates every request and routes it to a Runner sitting next to your code, where file edits, Git operations, test runs, shell commands, and long jobs execute with your real toolchain. Your projects never move into a hosted workspace; only the tool results you authorize travel back to the model. The browser Runtime Console shows project readiness, the work queue, session activity, and connected Runners, and it is where you decide pending approvals or accept and reject finished work, because the model cannot approve its own changes. Runners join with a short-lived pairing code and stay connected over QUIC, WebSocket, or polling, so machines behind NAT still work. One-command sharing opens a temporary session for a single repository, while durable setups run the Server and Runner as system services behind your own HTTPS domain. Workflow Sessions keep evidence and context across conversations, so long tasks survive closed browser tabs and threads you pick up days later. 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.

Where AI agents and people share one real-time workspace, an agent blocked on your decision never waits unnoticed until morning, and that workspace is AgentRQ, a human-in-the-loop task manager for agent fleets. In that workspace agents pull assigned tasks over MCP, report progress as they work, ask questions in the open, and pause visibly instead of going dark. Cards travel from Not Started to Ongoing to Blocked to Done on a list or Kanban board, and a Blocked card returns to work the second you answer from any device. Sensitive tool calls wait for an Allow click; flip YOLO on a task and they proceed automatically, still recorded call by call in a searchable trajectory. A timeline under every task totals how long the agent worked, waited, or stayed blocked. Scheduling spawns tasks on a cadence, completed tasks fire named events, and events hand new tasks to subscribed workspaces, chaining a release pipeline without glue code. Each project lives in an isolated workspace with its own agent, memory, skills, and Slack channel, and workspace memory carries yesterday's lessons into today's session. Voice-dictated tasks transcribe on device, 55 ACP-compatible agents connect through one gateway, and agents running on your own machines expose their terminals and resource use remotely. 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.

Your front desk phone rings at midnight and nobody sane is awake; QuickVoice answers it with an AI agent you configured, on servers you own, with call recordings you control. Build agents in the web console: write the prompt, pick speech-to-text, language model, and voice, set the first message, then link a real phone number from Twilio or Telnyx through LiveKit SIP trunks. Inbound callers get a receptionist that answers questions from your uploaded knowledge base, PDFs and web pages chunked and embedded for live retrieval, while outbound mode fires single quick calls or batch campaigns for reminders and follow-ups. Agents can invoke allowlisted MCP tools mid-call, so checking an order status or booking a slot happens inside the conversation instead of after it. Every call lands in the log with transcript, recording, and metadata, searchable from the analytics dashboard, and privacy controls redact personal data by default, can suppress recordings entirely, and sweep old transcripts on a retention schedule. Multi-language voices, per-agent runtime overrides for campaigns, organization accounts with API keys and audit logs, and Stripe billing hooks round out a platform built for teams who would rather inspect their voice stack than rent a black box. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

ENZO is a self-hosted AI workspace where you bring your own provider API keys and chat with more than 300 models from nine providers in one streaming interface with normal, thinking, research, and coding modes. You describe an agent in plain English and a two-pass builder drafts its full operating manual, picks the tools the task needs, and keeps improving from your activity through a per-agent neural layer you can inspect. Seventy-four bundled skills give agents ready-made domain playbooks, and a skill editor lets you write your own. Agents can read Gmail, check Calendar, search the web, and run a deep-research loop that writes its own queries under hard budgets so it cannot burn your key. Coding mode writes a multi-file project, boots it, and previews it live while telling you when something is broken. A unified model marketplace compares providers with live health checks, download counts, and benchmarks, and a built-in music player streams songs with a five-band equalizer. Your keys stay sealed in a passphrase-encrypted browser vault and travel only to the provider you picked, so there is no ENZO account, usage meter, or subscription taking a cut. 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.

Preloop is a self-hostable control plane that governs every AI agent tool call and model call, and can run ticket-triggered agent work that returns as reviewable pull requests. An MCP firewall can allow, deny, or hold any tool call for approval, with require-justification rules written as YAML and CEL policy. Human approvals arrive on mobile, watch, Slack, Mattermost, email, webhook, or the command line, and agents can ask a person a question before continuing. The model gateway speaks OpenAI, Anthropic, and Gemini formats, applies budgets and allowed-model lists, and attributes token spend by model, agent, session, API key, flow, and user. Flows start agents from GitHub, GitLab, Bitbucket Cloud, Jira, webhooks, or CI jobs, in hosted containers or on private runners that connect over an outbound WebSocket. Twenty-one presets review pull requests, implement issues, triage tickets, scan for vulnerabilities, and collect evidence packs. Operators can steer a running agent from the console, phone, or watch with notes, then review the resulting pull request. One session timeline records tool calls, model calls, policy decisions, approvals, spend, outcomes, and synchronized recordings. Fleet Map shows people, devices, agents, models, and observed work in one view. An account kill switch blocks gateway and tool traffic and stops managed runs, with audited recovery. 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.

Analytics teams, and increasingly the AI agents working beside them, get one shared definition of the business from Malloy Publisher instead of a pile of SQL queries that each compute revenue slightly differently. You model what your data means once: the sources, the joins, the measures, and who may see what. Agents then compose queries against that model over MCP, so there is no wrong join, no invented column, and no fan-out that double-counts while looking plausible, and the same question returns the same numbers tomorrow. Applications and BI tools reach the same model over REST, and unattended agents use the same governed path instead of scraping raw tables. Reports declared in Malloy read top to bottom or lay out as tile grids you can build by dragging, no-build HTML data apps ship inside the package, and the built-in Console lets anyone browse environments, packages, models, and results without writing code. Access rules decide who may query and which rows they see, discovery curation decides what is even visible, and a single annotation materializes an expensive source or pre-aggregates it on a schedule. Local files work through built-in DuckDB, while BigQuery, Snowflake, Postgres, Databricks, and others connect when the data already lives there. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.