Project knowledge for AI tools · Free

Your project has lore.
Your AI tools don't.

Decisions, interviews, meeting notes, research — collected in one place so every AI tool gets the full picture, with citations.

npm install -g @getlore/cli

Then run lore setup to sign in

Set up Lore for me using the instructions at https://getlore.ai/docs/agent-guide

Your AI walks you through it — asks for your email, sends a code, done

Get Started — Free Read Docs

Works with

ClaudeChatGPTGeminiCursorOpenClawCLIAny MCP Client

The Problem

Your project's lore is scattered

Meeting notes in one place. User interviews in another. Architecture decisions somewhere else. Every AI tool starts from scratch — and the details that matter get lost.

Without Lore

“Users want faster exports”

With Lore

“In the Jan 15 interview, Sarah said ‘The export takes forever, I’ve lost work twice this week.’ Two other participants flagged the same issue.”source: user-interviews-jan15.md

Use Cases

Feed it everything. Ask from anywhere.

User interviews → code decisions

Five user interviews last week. Now every AI tool knows what users said — and cites them when making decisions.

“What did users say about onboarding?”

Switch tools without losing context

Claude, ChatGPT, Cursor, Codex, CLI, TUI, and repo-local working copies — same knowledge base, everywhere.

“What were the key findings from the survey?”

See where your project stands

Auto-generated briefs show where your project is, where it's headed, and the evidence behind each decision.

“Generate a brief for the payments project”

Terminal UI

Browse your project's lore

lore browse gives you a full TUI for searching, reading, researching, and reviewing changes — no MCP client needed.

lore browse

Lore TUI — browse documents, search, and research from the terminal

Features

What you get

Project Briefs

Living summaries of each project — status, trajectory, key evidence. Updated automatically.

Search by Meaning

Ask questions, not keywords. Lore understands what your documents are about.

Citations

Every result links to the original source. Know exactly what was said, where, and when.

Deep Research

Cross-references all your sources to answer complex questions with cited reports.

Works Everywhere

Use MCP, CLI, the TUI, or repo-local .lore working copies for native coding agents.

Synced Everywhere

Same knowledge base on every machine via Lore Cloud. Deduplicated automatically.

How It Works

Add once, search from everywhere

Feed in your meeting notes, interviews, research, decisions — everything goes into one searchable knowledge base on Lore Cloud.

Folder sync

Point Lore at any folder. Files are indexed automatically.

lore sync add --path ~/research

From any AI tool

Any connected AI tool can push content. Just say “save this to lore.”

“Save this meeting summary to lore”

CLI

Ingest from the command line, a file, or a pipe.

lore ingest --file notes.md

Query from anywhere

Search from the CLI, the TUI, or any AI tool. Every result cites the original source.

lore search "what did the team decide about auth?"

Getting Started

Get started in 30 seconds

Just your email and two API keys. Free to use — no credit card, no trial period.

Install

npm install -g @getlore/cli

Run setup

Paste your API keys, enter your email, receive a one-time code — done.

lore setup

Start building your lore

Add sources, push content from any AI tool, or start searching:

lore search "user pain points"
lore research "What should we prioritize?"

Send instructions

Set up Lore for me using the instructions at https://getlore.ai/docs/agent-guide

Your AI reads the guide, installs the package, and asks you for your email and API keys.

Paste the code

A 6-digit verification code is sent to your email. Paste it back into the chat.

Done

Your AI finishes setup and starts the background daemon. Ready to search, ingest, and research.

Integrations

Connect to your tools

Add the MCP server

Or configure manually:

Add to .mcp.json in your project root, or ~/.claude.json globally:

{
  "mcpServers": {
    "lore": {
      "command": "npx",
      "args": ["-y", "@getlore/cli", "mcp"]
    }
  }
}

Settings → Developer → Edit Config. Include API keys since Desktop doesn't inherit your shell:

{
  "mcpServers": {
    "lore": {
      "command": "npx",
      "args": ["-y", "@getlore/cli", "mcp"],
      "env": {
        "OPENAI_API_KEY": "your-key",
        "ANTHROPIC_API_KEY": "your-key"
      }
    }
  }
}

Add to .cursor/mcp.json or ~/.codeium/windsurf/mcp_config.json:

{
  "mcpServers": {
    "lore": {
      "command": "npx",
      "args": ["-y", "@getlore/cli", "mcp"]
    }
  }
}

Run npx @getlore/cli setup to configure API keys and sign in. This is required before tools will work.

Available tools

searchFind by meaning or keywords

get_sourceFull document content

list_sourcesBrowse by project or type

list_projectsAll projects overview

get_briefProject context & trajectory

logLog decisions & progress

ingestAdd content (docs, insights, decisions)

research_statusPoll async research results

researchAI-powered deep research

FAQ

Common questions

How is Lore different from AI memory?

AI memory compresses your conversations into short summaries and loses the details. Lore keeps the original documents — meeting notes, interviews, decisions, research — so any AI tool can cite exactly what was said, by whom, and when.

What does it cost?

Lore is currently free. You bring your own API keys — OpenAI for summary extraction, Anthropic for research. Embeddings run on-device. Re-syncing existing files costs nothing.

What can I put into Lore?

Anything that captures your project's knowledge: meeting notes, user interviews, architecture decisions, research, data exports, design docs, and more. Supported formats include Markdown, PDF, JSON, CSV, HTML, XML, plain text, and images.

Do I need to set up infrastructure?

No. Lore Cloud is fully hosted — install, sign in, bring your API keys. Everything else is handled for you.

How does multi-machine sync work?

Run lore setup on each machine. Your data repo URL is saved to your Lore Cloud account, so new machines auto-discover it. Content is deduplicated by hash.

Your project has lore.Your AI tools don't.