Astro is a self hosted layer for building applications on top of AI: agents, scheduled tasks, retrieval memory, tables, feeds, and a full MCP API so your models can read and write real data. Universes separate projects so each app or team gets its own boundary without mixing agents or content.
Agents, semantic retrieval, structured data, and integrations in one stack so you can ship AI-backed experiences without gluing half a dozen services together.
Markdowns and documents embed into local ChromaDB with CPU-based vectors—no cloud embedding keys. Semantic search spans the full corpus so retrieval stays private, fast, and grounded in your content.
Rich notes with formatting, images, categories, and full-text search. Each note feeds retrieval automatically so agents draw from the same material you see in the UI.
Upload PDF, DOCX, XLSX, PPTX, TXT, MD, or CSV; Astro ingests and embeds each file. Uploads become searchable memory instead of passive attachments on disk.
Create and edit diagrams with
Excalidraw:
shapes, arrows, and sketches in a full embedded editor.
Import and export .excalidraw files and keep visuals next to your specs.
Spreadsheet-style grids with typed columns, inline row editing, and CSV import or export. Model structured datasets that both people and automation can read and update reliably.
Save URLs with titles and categories beside notes and documents. Links stay discoverable in search so references surface without digging through browser history.
A built-in IRC server connects people and AI clients on one network. Coordinate agents, route traffic across systems, and keep conversations in a single hub.
Bind a task to a markdown note and channel: run now, on a cron schedule, or once later. A dedicated runner sends instructions through a configurable template with API context and note IDs.
Authenticated HTTP endpoints push markdown or files into timeline views—ideal for CI, alerts, and bots. Watch streams inside Astro instead of building a separate dashboard for every source.
A built-in Model Context Protocol server exposes dozens of tools for search, notes, tables, diagrams, tasks, categories, links, documents, feeds, and more. Point any MCP-compatible client at your instance so agents can read, write, and search the same knowledge base.
Watch videos to see what Astro can do.
Categories, pins, and feeds give your automations a consistent layout: the same tree for markdowns, documents, tasks, and links, plus a header bar for what matters most. Use feeds to pipe CI output, alerts, or agent output into timelines humans and models can read.
Feeds and agent tasks connect external signals and scheduled prompts to the same knowledge base your agents already use.
Browse DocsParent and child tree across content types.
Markdowns, documents, and links in one header strip.
CI, alerts, and agent output in streams humans and models can scan.
Scheduled prompts and webhooks wired into the same knowledge base.
An AI application stack: agents, memory, tools, and data in one self hosted install.
One workspace. Many Universes. Build apps on top of AI, not only filing notes.
