What is Orcha

Orcha stores your knowledge one time and gives it to each AI tool that has permission. Files, structured databases, and read-only connected sources are in one workspace. Agents get access through the web app, a REST API, or the Model Context Protocol (MCP). Each access has permissions, citations, and provenance.

What Orcha stores

• Files: Markdown, JSON, and YAML files in a nested folder tree. See Files and folders.
• Structured databases: Typed schemas with relations, saved views, and versioned records. See Databases.
• Connected sources: Read-only documents that Orcha syncs from GitHub, Google Workspace, Microsoft 365, Dropbox, Notion, Atlassian, Linear, Zoom, and Granola. You select what Orcha indexes for each repository, folder, or path. Each citation points to the exact upstream version. See Connected sources.

How agents reach it

• REST API: Endpoints under /api/v1 that use token authentication. See the API reference.
• MCP server: An MCP server over stateless Streamable HTTP at /mcp. It is compatible with Claude Code, Claude Desktop, Cursor, and all MCP clients. See the MCP reference.
• Hybrid retrieval: pgvector semantic search together with PostgreSQL full-text search. Results have line anchors and citations. See Retrieval.
• Filesystem-shaped access: A read-only virtual filesystem over the workspace. You can browse it with ls, tree, grep, and cat through the orcha CLI, REST, or MCP. See Browse context like a filesystem.
• CLI: @tryorcha/cli gives browse, search, and feedback commands in the terminal. People, coding agents, and CI can use it. See the CLI reference.

Where to start

1. Read the Quickstart. It shows how to import your notes, connect a desktop client and a remote agent, and get the same cited answer from both.
2. Connect an agent: Claude Code, Claude Desktop, or Cursor.
3. Connect a source and select what Orcha indexes. Or, import from Obsidian or Notion. The import keeps hierarchy, relations, attachments, and links.