Empirical Docs

Searchable Empirical documentation for CLI install, bot setup, and OAuth connector integration.

• Overview: What Empirical is, how memory flows across tools, and where to start.
• Install CLI: Install Empirical CLI, configure local coding clients, and bootstrap headless OAuth tokens.
• Your First Memory: Capture your first durable memory and verify recall in one minute.
• Concepts: Core concepts: scopes, relevance ranking, durable notes, and recall behavior.
• Claude Code: Install and validate Empirical MCP inside Claude Code.
• Cursor: Connect Cursor to Empirical memory with manual MCP configuration.
• Windsurf: Configure Windsurf MCP manually for Empirical and verify live recall.
• Claude Desktop: Configure Claude Desktop to use Empirical MCP over OAuth.
• ChatGPT: Connect hosted /mcp endpoint to ChatGPT and complete OAuth.
• MCP in Claude: Choose the right Empirical MCP setup for Claude Code, Claude Desktop, or Claude on the web.
• MCP in Codex: Install the Empirical CLI, register the hosted MCP server in Codex, authenticate, and verify a tool call.
• MCP in Copilot: Install Empirical into Copilot’s MCP configuration, complete OAuth, and verify memory recall.
• Bring Obsidian notes into Empirical: Manually curate durable Obsidian notes into Empirical; there is no live vault connector.
• Bring Logseq notes into Empirical: Manually curate durable Logseq notes into Empirical; there is no live graph sync.
• Bring Markdown notes into Empirical: Turn selected Markdown files into durable Empirical memories without importing every file.
• Bring Notion notes into Empirical: Manually export and curate useful Notion pages; there is no live Notion sync.
• CLI Details: Index of every CLI command family with links to memory, OAuth, workspace, Skills Kit, plugin, and diagnostic deep dives.
• empirical doc: Progressive disclosure: list topics or print agent-readable instructions for any topic.
• empirical kit: Create, source, activate, sync, and inspect reusable Skills Kits across coding agents.
• empirical skill: List installed Skills, push authored SKILL.md files into Kits, inspect versions, and roll them back.
• CLI-direct integration: Use Empirical memory commands without MCP, from any shell environment.
• Native Empirical plugin: Install the native Empirical plugin so supported coding agents discover Empirical without competing side-loaded Skill files.
• Memory commands: Understand why Empirical memory exists and how to query, write, maintain, and export it from the CLI.
• Workspace commands: Understand workspace boundaries, project and team use cases, switching context, invites, and safe deletion.
• CLI authentication: Choose interactive browser login or headless authentication for automation and containers.
• OAuth commands: Detailed browser, headless, Docker, and advanced client-credential OAuth flows.
• Plugin commands: Install and diagnose native Empirical plugins for supported coding agents.
• Policy commands: Inspect and control local agent behavior around memory use and discretionary writes.
• Device commands: Inspect registered agent devices and the Skills Kits they resolve.
• Doctor and update: Diagnose CLI authentication, connectivity, workspace, plugin, and version problems.
• Empirical Memory plugin: The required core plugin: native memory guidance and the Empirical MCP connection.
• Work History plugin: Optional project history capture for concise completed-work summaries.
• Scar Tissue plugin: Optional prevention guidance for recurring failures and sharp edges.
• Todo plugin: Optional project-based todo tracking with status, next actions, and completion evidence.
• REST API: REST endpoints for memory operations and service integrations.
• MCP tool reference: Reference the Empirical MCP functions for memory, relationships, workspaces, and agent self-discovery.
• MCP Server: MCP architecture, tool surface, auth modes, and deployment guidance.
• Headless & CI: Production runbook for token refresh, secret storage, and CI safety checks.
• Self-hosting: Run Empirical infrastructure in your own environment with OAuth and MCP enabled.
• Security Model: Security boundaries, OAuth credential handling, and audit posture.
• Data Export: Export and portability guidance for memory records and operational continuity.
• Bot Setup: Production bot runtime setup with OAuth credentials, token refresh, and troubleshooting.
• OAuth Connector Setup: Field-by-field connector settings for tools that integrate to Empirical MCP over OAuth.
• Claude Web App Install: Interactive setup flow for connecting Claude web app to your Empirical MCP endpoint.