LocalKeep

LocalKeep is for anyone who wants a chronological memory layer for chatbots wheretheydirectly controlwhatthe model remembers about them. Instead of forcing you to rely on a black-box cloud memory that the model invents around you that you can't even edit, LocalKeep lets you curate titled, dated, editable memory banks directly on your own machine where you write the entries and manage them locally via a localhost Hub UI. When a conversation requires your prior context, Claude queries your local data through a secure, native Model Context Protocol (MCP) connector.

AI Chat apps are great atsoundinglike they remember you, but struggle at recalling theexactthing you care about —whathappened, onwhichdate, aboutwhom? Consumer memory features tend to lack the capacity for true temporal reasoning, flattening your history into a soft, generic vibe summary instead of understanding that Event A triggered Event B three months ago, causing its reasoning to fail when you need something specific: a life event, a research arc, a decision you logged months ago. Worse yet, consumer AI memory is a black box: you don't get to decidewhatthe model chooses to remember about you,howit interprets your life, orwhenit invents context around you.

LocalKeepfixes both structural flaws at once by replacing fragile, model-invented timelines with a rigid, chronological source ofyourtruth, all while givingyouabsolute editorial control. You decide exactlywhatthe AI is allowed to know about you. You write the entries, you anchor the dates, and you keep them local on your own machine. Claude simply acts as the lookup engine via MCP when a conversation requires your prior context. LocalKeep bridges the gap between structured personal logging and intelligent AI retrieval, ensuring your context is curated byyou—not hallucinated by an LLM.

- Anyone frustrated that chat memory can’t reliably fetch dated facts or understand timelines
- People who already maintain meticulous personal diaries, work logs, or research archives. Instead of settling for a generic chat-app paraphrase, you get to inject yourexactwords and historical data into the prompt as an unyielding source of truth.
- Users who trust Claude for its reasoning capability, but demand that their foundational context database remains stored locally under their own roof. (Note: Querying memories via MCP still sends theretrieved text fragmentsto Anthropic during the session).

- Is:A lightweight customizable local Hub UI to manage your dated memory banks, paired with an MCP server that Claude Desktop can call.
- Isn’t:A standalone chat application, a cloud-hosted memory API, or a background utility that silently scrapes your personal conversations.

The Hub UI intentionally adopts a retro, Windows 95/MS Paint-inspired homage with customizable features to ensure LocalKeep feels like a deeplypersonal toolrather than an impersonal, rigid dashboard. By putting adjustable interface elements right at your fingertips, the UI signals that you are entering an intimate, offline workshop for your mind—a space you can shape and reconfigure to feel entirely like your own.

pip install localkeep # or: uv tool install localkeep

In Claude Desktop, register the MCP server (claude_desktop_config.json):

{ "mcpServers": { "localkeep": { "command": "localkeep-mcp", "args": [] } } }

If the GUI can’t findlocalkeep-mcpon yourPATH, use the absolute path fromwhich localkeep-mcp(the Hub’s Connect panel copies this for you).

Memories default to~/.localkeep/localkeep.dbwhen installed via pip. Override withLOCALKEEP_DATA_DIRorLOCALKEEP_DB_PATH.

Claude will not reliably call MCP tools unless you also setPersonal preferences:
- Claude Desktop →Settings→Profile→Personal preferences
- Paste the LocalKeep instructions (Hub → Connect →Copy instructions, or seesrc/localkeep/assets/claude-personal-preferences.txt)
- Quit Claude completelyand reopen
- When LocalKeep asks to run a tool, clickAlways approve

git clone https://github.com/zuneracodes/localkeep cd localkeep uv sync --group dev uv run localkeep-hub # http://127.0.0.1:8000 # optional live reload: LOCALKEEP_HUB_RELOAD=1 uv run localkeep-hub

Bug reports and pull requests are welcome viaGitHub Issues. Please runuv run pytestbefore opening a PR.

Cross-tool proactive memory + suggestions for Claude Code, Kimi Code, Cline, Cursor. Teach once, use everywhere.