com.memxus/memxus

Official9 tools

by gpitrella · TypeScript

Multi-platform AI memory for individuals, groups and teams. One save, recall everywhere.

Multi-platform AI memory system for individuals and teams with unified recall.

Topics

aiai-memoryai-persistencememorymemory-layerpersistent-memory

Captured live from the server via tools/list.

remember

Save important information to long-term memory. Always set collection when the topic is clear: project work → project:<slug>, personal tastes → personal:preferences. Use append_to to extend an existing memory instead of creating duplicates. Vector search indexing completes asynchronously within a few seconds after save.

Parameters (9)

contentstringrequired
The information to remember.
typestring
Category for this memory. Default: general. Use preference for tastes, fact for stable truths, instruction for rules.
collectionstring
Scope slug (e.g. project:memxus, personal:preferences). GitHub/Notion connector syncs use project:<slug> — one collection per project. Partial names work; call list_collections when unsure.
tagsarray
Optional tags. A tag like project:my-app also sets collection automatically.
importancenumber
Relevance weight from 0 (low) to 1 (high) for ranking in recall. Default: 0.5.
append_tostring
UUID of an existing memory to append to (same user). Keeps revision history.
visibilitystring
private = personal only (default). shared = save to a group (set group_id or group_name).
group_idstring
UUID of a shared group. Required with visibility=shared when group_name is not set.
group_namestring
Exact group name (case-insensitive). Alternative to group_id for shared memories.

recall

Search long-term memory. Call list_collections when scope is unclear. For GitHub/Notion synced content use collection project:<slug> (unified per project) or tags github/notion. Connect at dashboard.memxus.com/integrations.

Parameters (9)

querystringrequired
Natural-language search query (e.g. "Henry project stack", "user prefers dark mode").
limitnumber
Max results. Omit for server default (10). Capped per your plan on the server.
typestring
Memory category: general, preference, fact, instruction, or conversation. Omit to include all types.
collectionstring
Scope slug (e.g. project:memxus, personal:preferences). GitHub/Notion connector syncs use project:<slug> — one collection per project. Partial names work; call list_collections when unsure.
tagsarray
Optional tags. A tag like project:my-app also sets collection automatically.
visibilitystring
Optional. Defaults to user dashboard preference (private unless include_group_memories_in_context is on).
group_idstring
UUID of a shared group. Required with visibility=shared when group_name is not set.
group_namestring
Exact group name (case-insensitive). Alternative to group_id for shared memories.
include_skillsboolean
When skill routing is enabled, append official skill suggestions for work intents (build/review/fix/test). Default: auto-detect from query.

get_context

Build a formatted context block for the current topic. Call list_collections when unsure of the exact slug. Partial collection names are resolved server-side.

Parameters (8)

topicstringrequired
Subject to build context for (e.g. "current project", "client meeting notes").
max_memoriesnumber
Max memories in context block. Omit for server default (10). Capped per your plan.
typestring
Memory category: general, preference, fact, instruction, or conversation. Omit to include all types.
collectionstring
Scope slug (e.g. project:memxus, personal:preferences). GitHub/Notion connector syncs use project:<slug> — one collection per project. Partial names work; call list_collections when unsure.
tagsarray
Optional tags. A tag like project:my-app also sets collection automatically.
visibilitystring
Optional. Defaults to user dashboard preference (private unless include_group_memories_in_context is on).
group_idstring
UUID of a shared group. Required with visibility=shared when group_name is not set.
group_namestring
Exact group name (case-insensitive). Alternative to group_id for shared memories.

list_memories

List recent memories. Filter by collection, tags, or type to browse one group.

Parameters (8)

limitnumber
How many memories to return. Omit for server default (20). Capped per your plan.
full_contentboolean
When true, return full memory text instead of a 120-character preview.
typestring
Memory category: general, preference, fact, instruction, or conversation. Omit to include all types.
collectionstring
Scope slug (e.g. project:memxus, personal:preferences). GitHub/Notion connector syncs use project:<slug> — one collection per project. Partial names work; call list_collections when unsure.
tagsarray
Optional tags. A tag like project:my-app also sets collection automatically.
visibilitystring
Optional. Defaults to user dashboard preference (private unless include_group_memories_in_context is on).
group_idstring
UUID of a shared group. Required with visibility=shared when group_name is not set.
group_namestring
Exact group name (case-insensitive). Alternative to group_id for shared memories.

get_memory

Get the full content of a single memory by its UUID (from list_memories or recall).

Parameters (1)

memory_idstringrequired
UUID of the memory to retrieve.

list_collections

List memory collections (folders/scopes) for this user. GitHub/Notion syncs appear under project:<slug> when unified collections are enabled. Call before scoped recall/get_context when the user mentions a project name.

No parameters.

forget

Delete a specific memory by ID.

Parameters (1)

memory_idstringrequired
UUID of the memory to delete (from list_memories or recall).

memory_stats

Show statistics about stored memories (by type and collection).

No parameters.

update

Update an existing memory by ID. Use mode replace (default) to patch fields, or append to extend content. Re-embeds only when content changes.

Parameters (7)

idstringrequired
UUID of the memory to update.
contentstring
New or appended content.
typestring
Memory category: general, preference, fact, instruction, or conversation. Omit to include all types.
collectionstring
Scope slug (e.g. project:memxus, personal:preferences). GitHub/Notion connector syncs use project:<slug> — one collection per project. Partial names work; call list_collections when unsure.
tagsarray
Optional tags. A tag like project:my-app also sets collection automatically.
importancenumber
Relevance weight from 0 to 1.
modestring
replace = patch fields; append = extend content with revision history.

README.md13 KBView on GitHub

Memxus — AI Context Engine

One context engine. Every AI.

Builds persistent context from GitHub, Notion, and your saved decisions — delivered to Claude, Cursor, ChatGPT, VS Code, and any MCP-compatible client.

Website · Docs · Connect your first AI · Glama Inspector

</div>

<div align="center"> <video src="https://github.com/user-attachments/assets/99538f58-e404-4aff-8e9a-c6ea3213fbd3" width="100%" autoplay muted loop playsinline controls> <a href="https://www.memxus.com/demo">Watch the Memxus demo</a> </video> <br> <sub><a href="https://www.memxus.com/demo">Demo page</a> · <a href="https://www.memxus.com/memxus-demo.mp4">Direct MP4</a></sub> </div>

The problem

Every AI tool starts from zero.

Claude doesn't know what Cursor knows. Cursor doesn't know what ChatGPT knows.
Your stack, project decisions, coding preferences and workflow context get repeated again and again.

Memxus fixes that with a shared context engine for your AI tools — not another chatbot, but persistent context built from your real work sources.

Sync GitHub once → every AI knows your stack. Save a decision in Claude → recall it in Cursor → reuse it in ChatGPT.

What is Memxus?

Memxus is the AI context engine — a hosted remote MCP server that automatically builds and delivers persistent project context to every AI client you use.

GitHub repos, Notion docs, commits, PRs, issues, and saved decisions become searchable context. GitHub and Notion connectors are live in production (v1.1.0) — connect from the dashboard or directly from chat via MCP connector tools. Skill routing suggests official AI skills matched to your stack.

No local setup.
No file syncing.
No copy-pasting context between tools.

Connect once with OAuth and your context becomes portable across your entire AI workflow.

Why developers use Memxus

Keep project architecture and stack context available across Claude, Cursor, and ChatGPT
Sync GitHub and Notion into unified project collections — one context per repo
Stop pasting the same context into every new AI session
Get official AI skill suggestions matched to your stack (get_context_with_skills)
Share team context across agents and workflows
Build AI apps with persistent context through MCP or API

Real context from GitHub & Notion

Memxus reads your real work — not generic memory snippets. Synced content lands in a unified collection per project: project:<slug>.

What gets synced

Source	Content indexed into context
GitHub	Repos, READMEs, commits, pull requests, issues
Notion	Selected workspace pages and docs
Manual	Decisions, preferences, and notes via `remember`

How to connect

Dashboard — dashboard.memxus.com/integrations (GitHub App + Notion OAuth)
From chat (MCP) — connect_source → check_connect_status → list_syncable_items → set_sync_selection

How to use synced context

Call recall, get_context, or get_context_with_skills with collection=project:<slug> (or let semantic search find it). GitHub/Notion content is tagged and searchable alongside manual memories.

mermaid

flowchart LR
  GitHub[GitHub repos] --> Sync[Memxus sync]
  Notion[Notion pages] --> Sync
  Manual[Manual remember] --> Sync
  Sync --> Collection["project:slug"]
  Collection --> Tools["recall / get_context / get_context_with_skills"]
  Tools --> Clients[Claude Cursor ChatGPT]

Context Engine tools (6): visible when In-app connect and Skill routing are enabled in dashboard settings. Production ships the full 15-tool manifest for users with v2 prefs on.

Connect in 30 seconds

code

URL:       https://mcp.memxus.com/mcp
Auth:      OAuth 2.1 (handled automatically)
Transport: Streamable HTTP

Claude Desktop (`claude_desktop_config.json`)

json

{
  "mcpServers": {
    "memxus": {
      "url": "https://mcp.memxus.com/mcp",
      "transport": "streamable-http"
    }
  }
}

Cursor / VS Code

json

{
  "mcp": {
    "servers": {
      "memxus": {
        "url": "https://mcp.memxus.com/mcp",
        "transport": "http"
      }
    }
  }
}

Or open directly in Glama Inspector →
https://glama.ai/mcp/inspector?url=https://mcp.memxus.com/mcp

For marketplace reviewers: see REVIEWER.md for OAuth and Bearer token setup.

Supported platforms

Platform	Integration	Status
Claude Desktop / claude.ai	Remote MCP	✅ Live
Cursor	Remote MCP	✅ Live
VS Code / Copilot MCP	Remote MCP	✅ Live
ChatGPT	Custom GPT / API	✅ Live
Gemini	MCP-compatible workflow	✅ Live
Telegram	Bot connector	✅ Live
GitHub	Repo sync (commits, PRs, issues, README)	✅ Live
Notion	Workspace page sync	✅ Live
Discord	Bot connector	🔜 Coming soon
Slack	Bot connector	🔜 Coming soon
Any MCP-compatible client	Remote MCP	✅ Live

Available tools

Registry com.memxus/memxus v1.1.0 — 9 core tools always available, plus 6 Context Engine tools when v2 prefs are enabled.

Core tools (9)

Tool	Description
`remember`	Save context — manual input, decisions, or notes; optional `project:<slug>` collection
`recall`	Semantic search across memories; GitHub/Notion synced content via `project:<slug>` or tags
`get_context`	Formatted context block from GitHub, Notion, and saved decisions for agent prompts
`list_memories`	Browse memories by collection, tags, type, or visibility
`get_memory`	Retrieve full content and metadata by memory ID
`list_collections`	List scopes; GitHub/Notion syncs appear under `project:<slug>`
`forget`	Delete a memory permanently
`memory_stats`	Stats by type and collection
`update`	Patch or append existing memory content, tags, or type

Context Engine tools (6) — v1.1.0

Tool	Description
`connect_source`	Start GitHub App install or Notion OAuth from chat
`list_syncable_items`	List repos or Notion pages available after connecting
`set_sync_selection`	Choose what to sync and trigger initial sync into `project:<slug>`
`check_connect_status`	Poll connection status after `connect_source`
`get_context_with_skills`	Build context + suggest official AI skills for your stack and task
`suggest_skills`	Discover skills from skills.sh without a full context block

Full tool reference: memxus.com/docs/mcp · Marketplace reviewers: REVIEWER.md

Architecture

code

GitHub App ──┐
Notion OAuth ┼──► sync (API + connector tools) ──► Supabase  project:<slug>
Manual MCP   ┘                                              │
                                                            │ pgvector
MCP Client (Claude, Cursor, etc.)                           │
        │                                                   │
        │  POST /mcp   Bearer aimem_*                       │
        ▼                                                   ▼
  mcp.memxus.com  ← This repo (Railway) ──────────►  Supabase (Postgres + pgvector)
        │
        ▼
  Dash-AIMemory (Dashboard + integrations)

Sync runs server-side via dashboard or MCP connector tools — no local files to manage.

Transport: Streamable HTTP (MCP 2.0)
Auth: OAuth 2.1 + PKCE + Dynamic Client Registration (RFC 9728)

Security

OAuth 2.1 + PKCE — no passwords, no API keys to manage
Encrypted at rest (AES-256)
User-controlled memory — view, edit and delete anytime from the dashboard
No local files or manual syncing
Pre-publication secrets audit passed: 2026-06-17

OAuth flow

code

1. Client  →  GET  /.well-known/oauth-authorization-server
2. Client  →  GET  /oauth/authorize  →  redirect to dashboard login
3. User signs in (Google) in the dashboard
4. Client  →  POST /oauth/token  (PKCE)  →  aimem_* bearer token
5. Client  →  POST /mcp  Authorization: Bearer aimem_*

Dynamic Client Registration is supported — clients register automatically on first connect.

Self-hosting

Prerequisites

Node 20+
Supabase project (run supabase/migration.sql after the dashboard migration)
Railway account (or any Node host)

Environment variables

bash

cp .env.example .env

Variable	Description
`MCP_PUBLIC_URL`	Public URL of this server (no trailing slash)
`DASHBOARD_URL`	Dash-AIMemory URL for login redirect
`SUPABASE_URL`	Supabase project URL
`SUPABASE_SERVICE_ROLE_KEY`	Supabase service role key
`OAUTH_CLIENT_ID`	OAuth client ID
`ALLOWED_REDIRECT_URIS`	Comma-separated allowed redirect URIs
`CORS_ORIGINS`	Comma-separated allowed CORS origins
`OPENAI_API_KEY`	(Optional) Vector search embeddings

Run locally

bash

npm install
npm run dev       # tsx watch
npm run build     # tsc → dist/
npm start         # node dist/index.js

Deploy to Railway

Set all variables under Settings → Variables (never commit .env).
MCP_PUBLIC_URL = your Railway networking URL (no trailing /mcp).
Health check endpoint: /health (configured in railway.toml).

Note: Node 20 on Railway — Supabase Realtime needs the ws package (configured in src/lib/supabase.ts).
Optional: set RAILPACK_NODE_VERSION=22 for native WebSocket support.

Development

bash

npm install
npm run dev        # tsx watch
npm run lint       # ESLint
npm run typecheck  # tsc --noEmit
npm run build      # compile → dist/
npm start          # node dist/index.js

Marketplace reviewers: REVIEWER.md · MCP docs: memxus.com/docs/mcp · Registry: com.memxus/memxus v1.1.0

Releases

Add entries under ## [Unreleased] in CHANGELOG.md
Bump version in package.json, server.json, and src/mcp/server.ts
Move the changelog section to ## [X.Y.Z] - YYYY-MM-DD
Commit, tag, and push:

bash

git tag -a vX.Y.Z -m "Memxus MCP vX.Y.Z"
git push origin vX.Y.Z

Pushing a v* tag triggers .github/workflows/release.yml — quality gate + GitHub Release with server.json attached.

Secrets audit

Run from the repo root before making the repository public.
Last audit: 2026-06-17 — PASSED

bash

# 1. Verify .env was never committed
git log --all --full-history -- .env .env.local .env.production

# 2. Check for .env* files added in history
git log --all --oneline --diff-filter=A -- "*.env*"

# 3. Grep current tree for dangerous patterns (exclude .example)
git grep -rn -E "(service_role|anon_key|sk-[a-zA-Z0-9]{20,}|aimem_[a-zA-Z0-9]+|eyJ[a-zA-Z0-9_-]{20,})" \
  -- ":(exclude)*.example" ":(exclude)CHANGELOG*"

# 4. Search full git history for leaked keys
git log --all -p --follow -S "service_role" -- . | head -100
git log --all -p --follow -S "SUPABASE_SERVICE_ROLE_KEY=" -- . | head -100

Check	Expected
Commands 1–2	No `.env` commits (only `.env.example` in initial commit)
Command 3	Only placeholders (`aimem_YOUR_KEY`), test fixtures, SQL comments
Command 4	No real key values in diffs

If commands 1 or 4 find real secrets, rotate keys immediately and run git filter-repo --path .env --invert-paths before publishing.

Roadmap

GitHub connector (repo sync → project:<slug>)
Notion connector (workspace page sync)
MCP Registry v1.1.0 (com.memxus/memxus — AI Context Engine)
Context Engine tools (connect + skills routing)
Discord bot connector
Slack bot connector
Refresh tokens
Multi-client OAuth UX
npm publish

License

Licensed under the GNU Affero General Public License v3.0 (AGPL-3.0).

You can use, modify, and distribute this code freely. If you use it to run a network service (SaaS), you must publish your source code under the same license.

Install

claude_desktop_config.json

{
  "mcpServers": {
    "memxus": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "https://mcp.memxus.com/mcp"
      ]
    }
  }
}

Desktop config is stdio-only; this bridges via mcp-remote. Native remote: Settings > Connectors.

Topics

remember

recall

get_context

list_memories

get_memory

list_collections

forget

memory_stats

update

Memxus — AI Context Engine

The problem

What is Memxus?

Why developers use Memxus

Real context from GitHub & Notion

Connect in 30 seconds

Claude Desktop (claude_desktop_config.json)

Cursor / VS Code

Supported platforms

Available tools

Core tools (9)

Context Engine tools (6) — v1.1.0

Architecture

Security

OAuth flow

Self-hosting

Prerequisites

Environment variables

Run locally

Deploy to Railway

Development

Releases

Secrets audit

Roadmap

License

Install

Claude Desktop (`claude_desktop_config.json`)