Categories
Self-Hosted Workflow Automation MCP AI Assistant Knowledge Graph Agent Platform Personal AI Local-First AIStars
Forks
Watchers
Developer links
Row-Bot
Conversations, goals, memory, and scheduled workflows live together in one private AI assistant that runs on your own server and opens in any browser, on a laptop or a phone. Chat with local models through Ollama, provider API keys, ChatGPT, Claude, or Grok subscriptions, or any OpenAI-compatible endpoint, and every tool call shows up in the transcript. Risky actions pause for Approve or Deny in the chat, on the Home screen, or on a connected channel. Memory grows into a personal knowledge graph with recall, review, and an Obsidian-compatible wiki vault. Ask for a deck, a mockup, or an app and a design or code panel opens beside the chat, with Present, export to PDF, HTML, PNG, or PPTX, a changes view, Git, pull requests, checks, and an interactive terminal. Goals keep going until done, delegated agents get their own conversations, and workflows run on a schedule, a webhook, or a chain, with run history and delivery to channels. Telegram, WhatsApp, Discord, Slack, and SMS channels, voice dictation, and an app catalog for GitHub, Notion, Linear, and Stripe extend it, and health checks propose one fix per problem. Pairing a phone takes a QR code and a one-time invitation, and the server serves a single owner across many devices. 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.
Benefits
- One Private Workspace For Everything
- Chats, goals, memory, workflows, designs, and code folders sit in one system of record on your own host, so no outside account holds your conversations.
- Approvals Before Anything Risky
- Commits, file writes, and other consequential actions wait for Approve or Deny in the chat, on Home, or through a connected channel, so the agent never acts unseen.
- Any Model You Already Have
- Connect Ollama for local models, provider API keys, ChatGPT, Claude, or Grok subscriptions, or any OpenAI-compatible endpoint, and pick a model per conversation from the picker.
- Work Continues Without You
- Scheduled, webhook, and chained workflows keep running with budgets, approvals, run history, and delivery to Telegram, Slack, Discord, WhatsApp, or SMS when you are away.
Features
- Personal Knowledge Graph
- Memories link into a browsable graph with recall, review, and Dream Cycle refinement, plus an Obsidian-compatible wiki vault and document ingestion for sources.
- Design And Code Panels
- Decks, documents, and mockups open beside the chat with Present and export to PDF, HTML, PNG, or PPTX; code folders add diffs, Git, pull requests, and a terminal.
- Goals And Delegated Agents
- Goals pause when progress stalls, delegated agents hold their own conversations with Stop and Message controls, and reusable agent profiles carry model and tool settings.
- Workflow Editor
- Build multi-step prompts with a schedule, webhook, or chained trigger, a delivery target, and a model and approval policy, then review every run.
- Apps, Skills, And MCP
- Connect services from one catalog by sign-in or key, add MCP servers and skills with slash commands, and switch apps per chat with an at-mention.
- Phones And Remote Access
- Invite phones and other computers with a QR code over Tailscale, Wi-Fi, or a public link, each holding a revocable owner session.