Understand the product loop from upload to grounded answers.

LiquidLM is a knowledge product with a documented API and MCP surface. Start with the product guides, then jump into the generated API and tool references when you need exact fields or commands.

• Indexing pipeline — How uploads, notes, links, and MCP writes become searchable knowledge.
• Search and retrieval — How hybrid retrieval, rerank, temporal metadata, and supersedes filtering shape results.
• Chat with grounded sources — How chat sessions retrieve context, stream answers, and cite knowledge from selected vaults.
• Keyboard shortcuts — Global navigation, block editing, block selection, and chat composer controls.
• Settings, auth, and scopes — CLI login, PAT fallback, token bundles, active orgs, and per-vault grants.
• Data lifecycle — Vault storage, file versions, Trash, restore, reversible forget, audit, and retention expectations.
• Sync a GitHub repository — Connect GitHub and keep repositories synced into a vault, with automatic updates and delete propagation.
• Add LiquidLM to your assistant — Connect verified MCP clients with OAuth. See tested status before you install.
• Connect LiquidLM in ChatGPT — Developer-mode MCP setup with OAuth, tool discovery, and search/fetch verification.
• Connect LiquidLM in Codex — Remote MCP OAuth for Codex CLI with version-specific compatibility notes.
• Connect LiquidLM in Claude Code — User-scoped HTTP MCP with pinned OAuth scopes, search verification, and restart persistence.
• Command-line reference — Install status, login, workspace selection, vault operations, local media fetch, search, and MCP client setup.
• MCP tool reference — Eight native LiquidLM tools plus standard search and fetch compatibility aliases.
• REST API reference — Generated OpenAPI reference for every canonical /v1 route, with field-level schemas and scope badges.
• Changelog — Product and platform updates for LiquidLM — CLI fetch, MCP OAuth, and more.