mempalace_statusLABSCO SUMMARY
Memory for hosted clients, which local-first tools cannot serve.
ChatGPT cannot reach a memory server on your laptop, and its own memory is not something you can search or delete record by record. This is the other shape: a remote endpoint you own, on infrastructure that costs nothing at small scale. The tool surface is large because the structure is — wings, rooms, drawers, diary, knowledge graph and tunnels — so start with the wake-context call and let its guidance lead.
What it is
A remote memory server you deploy yourself on Cloudflare Workers. Memories are kept as drawers and diary entries with a knowledge graph over them, searched by a hybrid of semantic and lexical retrieval, and scoped per tenant. Hosted clients connect over Streamable HTTP with OAuth.
What you get
- mempalace_wake_context — the call to start a chat with, returning bounded, scope-limited context
- mempalace_search and mempalace_check_duplicate — hybrid retrieval, and a duplicate check before you write
- mempalace_add_drawer, mempalace_update_drawer and mempalace_delete_drawer for durable notes, indexed as they are written
- mempalace_get_drawer, mempalace_list_drawers, mempalace_list_wings, mempalace_list_rooms and mempalace_get_taxonomy for browsing the structure
- mempalace_diary_write, mempalace_diary_read, mempalace_diary_search and mempalace_diary_reindex
- mempalace_kg_add, mempalace_kg_query, mempalace_kg_invalidate, mempalace_kg_timeline, mempalace_kg_check and mempalace_kg_stats — temporal facts, with a check for conflicts and staleness
- mempalace_traverse, mempalace_find_tunnels, mempalace_create_tunnel, mempalace_list_tunnels, mempalace_delete_tunnel and mempalace_follow_tunnels for the graph between locations
- mempalace_status, mempalace_reconnect, mempalace_hook_settings and mempalace_memories_filed_away for diagnostics and write status
- Tenant scoping, so separate people or workflows cannot see each other's memory
Requirements
A Cloudflare account with Workers, D1, R2, Vectorize and Workers AI enabled, plus Node.js and an authenticated wrangler. You generate three secrets, mint an access key per tenant, and deploy — no VM, no Docker, no database to administer. There is no shared public instance: you run it. Free-tier limits apply and Vectorize in particular has its own constraints, so check the pricing before rolling it out widely. ChatGPT is the client that has been verified end to end.
Setup effort
Build from source — git clone https://github.com/nazar256/memheaven.git
USE CASES
01
Picking up a project in a new chat
Open with the wake-context call and get bounded startup context instead of re-explaining.
02
Recording a decision so it survives the session
Check for a duplicate first, then write it as a drawer that gets indexed for search.
03
Finding something you told it weeks ago
Search across drawers with both meaning and wording, scoped to your tenant.
04
Keeping work and personal context apart
Store into separate wings and rooms, and search within the one you are in.
05
Catching memory that has gone stale or self-contradictory
Run the knowledge-graph check for conflicts, then invalidate the fact that no longer holds.
06
Keeping a running log of what happened
Write diary entries as you go and search them later by scope.
07
Deleting something you should not have stored
Find the drawer and soft-delete it, which removes its index entries too.
34 tools
Listed in project docs. Your client may show a different list.
mempalace_wake_contextmempalace_list_wingsmempalace_list_roomsmempalace_get_taxonomymempalace_get_aaak_specmempalace_searchmempalace_check_duplicatemempalace_get_drawermempalace_list_drawersmempalace_add_drawermempalace_update_drawermempalace_delete_drawermempalace_diary_writemempalace_diary_readmempalace_diary_searchmempalace_diary_reindexmempalace_kg_querymempalace_kg_checkmempalace_kg_addmempalace_kg_invalidatemempalace_kg_timelinemempalace_kg_statsmempalace_traversemempalace_find_tunnelsmempalace_graph_statsmempalace_create_tunnelmempalace_list_tunnelsmempalace_delete_tunnelmempalace_follow_tunnelsmempalace_hook_settingsmempalace_memories_filed_awaymempalace_reconnectmempalace_syncBEFORE YOU INSTALL
What to know first
Tools you get
34 tools named in the project's documentation.
Requires
Node.js 20+
INSTALLATION
Connect your client
Server setup
TERMINAL
git clone https://github.com/nazar256/memheaven.git
cd memheaven
npm install
cp wrangler.toml.example wrangler.toml
npm run init -- --base-url https://memheaven.<YOUR_WORKERS_SUBDOMAIN>.workers.dev
npm run secrets:generate
npx wrangler secret put JWT_SIGNING_SECRET
npx wrangler secret put TOKEN_ENCRYPTION_KEY
npx wrangler secret put AUTH_KEY_PEPPER
export AUTH_KEY_PEPPER='<YOUR_AUTH_KEY_PEPPER>'
npm run keygen -- --tenant personal --label "Personal"
npx wrangler deployAdd the connector URL https://memheaven.<YOUR_WORKERS_SUBDOMAIN>.workers.dev/mcp in your client and paste the printed raw_key on the /authorize consent page
MCP Clients
ChatGPT
Add the connector using your workers.dev /mcp URL:
CHATGPT · URL
https://memheaven.<YOUR_WORKERS_SUBDOMAIN>.workers.dev/mcpChatGPT performs OAuth discovery and dynamic client registration automatically.
On /authorize, enter a valid raw_key printed by npm run keygen.
Approve the connector.
Any MCP client
ANY MCP CLIENT · URL
https://<YOUR_WORKER_DOMAIN>/mcp
