Empirical
One persistent memory layer for ChatGPT, Claude, Cursor and other AI clients
- Pricing
- Freemium
- Platforms
- API, CLI, Web
- Runs
- Remotely
- Version
- 1.0.1
- Listing updated
- 3 days ago
About Empirical
Empirical is a freemium MCP server for knowledge and memory. It runs as a hosted remote server, so there is nothing to install locally.
Empirical keeps a personal memory that any connected model can read. Notes, pasted chats and watched tools feed a graph described as semantic, episodic and procedural, with memories deduplicated, versioned and ranked by recency, relevance and intent. When a model needs context, the relevant slice is injected server-side through MCP or the CLI, and an audit view shows what was injected so it can be approved, redacted or rewritten.
The plugin repository packages the core memory skill plus optional add-ons for work history, recurring failure patterns, project todos and writing in your saved voice. It installs into Claude Code, Codex CLI and GitHub Copilot CLI, and the npm CLI offers an interactive installer plus browser OAuth sign-in. Memories can carry due dates that trigger a calendar alarm, an email and an in-agent heads-up, and can be organised into separate personal, team or client workspaces.
Memory can be exported as JSON or deleted, and the site says it is not used for training. SOC 2 is listed as in progress.
Install
Run in a terminal
claude mcp add --transport http empirical https://empirical.gauzza.com/mcpAdd to Settings → Connectors → Add custom connector
https://empirical.gauzza.com/mcpAdd to ~/.cursor/mcp.json
{
"mcpServers": {
"empirical": {
"url": "https://empirical.gauzza.com/mcp"
}
}
}Add to .vscode/mcp.json
{
"servers": {
"empirical": {
"type": "http",
"url": "https://empirical.gauzza.com/mcp"
}
}
}Add to ~/.codeium/windsurf/mcp_config.json
{
"mcpServers": {
"empirical": {
"serverUrl": "https://empirical.gauzza.com/mcp"
}
}
}Add to your client's MCP settings (most use this shape)
{
"mcpServers": {
"empirical": {
"type": "http",
"url": "https://empirical.gauzza.com/mcp"
}
}
}What it does
- Cross-tool recall
- The same memory is read from ChatGPT, Claude, Cursor, Copilot, Codex and the terminal.
- Memory graph
- Semantic, episodic and procedural memories, deduplicated and versioned.
- Scoped workspaces
- Keep work, personal and client contexts apart.
- Recall audit
- See, approve, redact or rewrite what was injected into a conversation.
- Dated reminders
- A memory with a due date triggers a calendar alarm, email and in-agent notice.
- Portable export
- Export everything as JSON or delete it.
- MCP, REST and CLI
- Several ways to connect agents and pipelines.
Good for
- Carry project decisions from ChatGPT into a coding agent
- Stop re-explaining preferences in every new chat
- Track leads and relationships as memory instead of a separate CRM
- Keep client work separate from personal context
- Record recurring failures so agents avoid repeating them
Pricing
Freemium, from $4.99 a month
Free tier of 100 memories; Starter $4.99, Builder $9.99, Architect $34.99 per month.
Prices change. Check empirical.gauzza.com before you buy.
Empirical FAQ
What does it cost?
Free for 100 memories; Starter is $4.99 a month, Builder $9.99 and Architect $34.99, plus custom Enterprise.
Which agents does the plugin cover?
Claude Code, Codex CLI and GitHub Copilot CLI.
Can I take my data with me?
Yes, memory can be exported as JSON and deleted.
Is my memory used to train models?
The pricing FAQ says no.
Is Empirical free?
Empirical has a free plan, with paid plans for more usage or features. Paid plans start at $4.99 a month.
How do I add Empirical to Claude Code?
Run this command in your terminal: claude mcp add --transport http empirical https://empirical.gauzza.com/mcp
What are the best alternatives to Empirical?
The closest alternatives to Empirical are Codebase Memory, XERJ, Claude Code Ultimate Guide, Nautilus Compass Memory and note1.
Alternatives to Empirical

Codebase Memory
MCP serverLocal MCP server that builds a code knowledge graph for AI coding agents
Runs locally- Open source
- 48.7K GitHub stars
- Knowledge and memory

XERJ
MCP serverLocal search engine for AI agents with cited answers over your code and docs
Runs locally- Open source
- 19.2K GitHub stars
- Knowledge and memory

Claude Code Ultimate Guide
MCP serverMCP server for searching the Claude Code Ultimate Guide from any MCP client
Runs locally- Open source
- 6.5K GitHub stars
- AI models and LLM tooling

Nautilus Compass Memory
MCP serverLocal-first long-term memory layer for AI agents, served over MCP
Not checked yet- 5 tools
- Remote
- Open source
- 1.3K GitHub stars
- Knowledge and memory

note1
MCP serverMCP server giving AI assistants search and summaries across your note1 meetings
- 4 tools
- Remote
- Free trial
- 1 GitHub star
- Productivity
MedXpert 图书馆连接器(通用版)
MCP serverLocal MCP server that searches and answers questions over your own Markdown wiki
Runs locally- 4 tools
- Open source
- Knowledge and memory