AI Assist
Freemium
Users prioritizing on-device processing and data privacy
MEMXUS
FreemiumAPI
You explain your project architecture to Claude, then open Cursor and start over — every session, every tool, every time. Memxus is a portable memory layer that carries that context across ChatGPT, Claude, Cursor, Gemini, VS Code, and Slack so you stop re-explaining the same decisions to every assistant.
$12/month or $149/month · Free tier: 150 API calls/day, 40 memories stored, 1 MB storage, basic semantic search, 30-day memory retention, 1 shared group (up to 3 members), community support · Checked Jul 1, 2026
Similar tools
Ruune DesktopFreemiumRuune Desktop pairs a sub-3mm hardware device with a desktop app to capture audio at the chip…
AI AssistFreemiumThe tool installs as a browser extension, captures audio from your active meeting tab, and runs…
AishaFreeAisha centers Black sources and history as design principles rather than as a filter layered on…
DocfilaFreemiumThe core workflow runs scan-to-delivery in four steps: capture a paper document or upload a…
Summary
The core mechanic is save-once, recall-everywhere: you push facts, preferences, and project decisions into Memxus once, and every connected AI tool pulls the relevant slice when it needs it. Integration happens through MCP, a REST API, or native connections — no browser extension, no local install. The vendor states end-to-end encryption where even Memxus staff cannot read your stored memories, which matters when you are saving proprietary architecture decisions or customer insights. The wall appears at team scale: shared workspace memory exists, but without self-hosting, your org's context lives on Memxus infrastructure under their data terms regardless of encryption claims. Teams with strict data residency requirements will need to read the GDPR documentation carefully before committing.
Bottom line: Solid pick for a solo developer or small team drowning in repeated context across three AI tools — less defensible for an enterprise that needs on-premise data residency, where the absence of a self-hosted option forces a harder conversation.
Pricing Plans
SubscriptionLast verified 4 months ago- Price
- $12/month or $149/month
- Free Tier
- 150 API calls/day, 40 memories stored, 1 MB storage, basic semantic search, 30-day memory retention, 1 shared group (up to 3 members), community support
Free
Free
Perfect for trying MCP, GPT Actions, or the SDK
- 150 API calls / day
- 40 memories stored
- 1 MB storage
- Basic semantic search
- 30-day memory retention
- 1 shared group (up to 3 members)
- Community support
Pro
$12per month
For power users and solo builders
- 1,500 API calls / day
- 400 memories stored
- 10 MB storage
- Advanced semantic search
- 90-day memory retention
- Unlimited shared groups (up to 10 members each)
- Priority recall
- Priority email support
- API access
Team
$149per month
For teams standardizing on shared memory
- Everything in Pro
- 25,000 memories stored
- ~352 MB storage
- Unlimited API calls
- Unlimited memory retention
- Unlimited shared groups & members
- Team analytics
- Role-based access control
- Dedicated support
View full pricing on memxus.com →
Pricing may have changed since last verified. Check the official site for current plans.
Find your fit
Before you choose MEMXUS
More options in Productivity. Compare pricing, platforms, and features side by side.
Aisha
Free
Users seeking culturally grounded AI responses
Pros
- Works across ChatGPT, Claude, Cursor, VS Code, Gemini, and Slack through MCP, API, or native integrations — so switching between coding assistants mid-project does not reset your context to zero.
- Semantic, selective recall instead of full-history dumps, which the vendor estimates cuts token usage by up to 90% per session — meaning API costs tied to repeated context re-entry drop alongside the friction.
- End-to-end encryption with a stated architecture where even Memxus staff cannot read stored memories, so proprietary architecture decisions and customer insights do not sit in plaintext on a third-party server.
- Shared workspace memory for teams, so a new developer joining a project can query established conventions and past decisions from day one instead of piecing them together across stale Notion docs and Slack threads.
- No local install or browser extension required, so there is nothing to version-manage, nothing to break on an OS update, and nothing to push through an IT approval queue before a teammate can connect.
Cons
- No self-hosted option exists — your stored memories live on Memxus infrastructure regardless of encryption. Teams under data residency mandates, SOC 2 audit requirements, or internal policies barring third-party cloud storage for proprietary context hit this wall immediately and have no workaround short of switching to a self-hostable alternative.
- Shared workspace memory depends on what team members choose to save, not on automatic capture — so if a developer forgets to push a critical architectural decision, every AI tool on the team recalls an incomplete picture. There is no audit mechanism described in the vendor docs that flags gaps in shared context.
- The API and MCP surfaces handle recall well for structured queries, but the system has no described mechanism for detecting when a saved memory has gone stale. Teams working in fast-moving codebases will find themselves manually auditing the notebook view to avoid every tool confidently recalling outdated decisions — adding maintenance overhead that scales with the size and churn rate of the project.
About
- Platforms
- Web, ChatGPT, Claude, Cursor, VS Code, Gemini, Slack, Telegram
- API Available
- Yes
- Self-Hosted
- No
- Last Updated
- June 18, 2026
Best For
Who it's for
- Developers using multiple coding assistants
- AI power users switching between models
- Companies standardizing context across employee AI usage
What it does well
- Maintaining project architecture and coding preferences across Cursor, Claude and ChatGPT
- Sharing team decisions and recurring knowledge in Slack and other apps
- Preserving product strategy and customer insights for founders across AI sessions
- Reducing context re-entry when switching between multiple AI tools
Integrations
Recommended skills for this tool
Auto-curated by the AIDiveForge recommendation matrix. These skills are predicted to enhance this tool based on category, capability, and domain signals.
-
Meeting Summary Template transform 32%
Turn a transcript into decisions and assigned actions without inventing commitments.
Why: category partial · caps 0/0 · domain ops
-
Standup Note Synthesizer transform 32%
Combine team standup notes while preserving blockers and ownership.
Why: category partial · caps 0/0 · domain ops
-
Runbook Skeleton post 32%
Turn a postmortem into an incident runbook with explicit verification gates.
Why: category partial · caps 0/0 · domain ops
-
OKR Draft Critiquer post 32%
Critique draft OKRs for measurable outcomes and controllable scope.
Why: category partial · caps 0/0 · domain ops
Frequently Asked Questions
- Is MEMXUS free?
- MEMXUS offers a free option alongside paid upgrades. Pricing: $12/month or $149/month. Check the current allowances and terms before choosing a plan.
- Does MEMXUS have an API?
- Yes. MEMXUS exposes a developer API. See the official documentation at https://memxus.com for details.
- What platforms does MEMXUS support?
- MEMXUS is available on: Web, ChatGPT, Claude, Cursor, VS Code, Gemini, Slack, Telegram.
Curated lists that include this category
Every AI assistant starts a session with zero knowledge of what you told a different assistant yesterday. Memxus inserts a persistent, cloud-hosted memory layer between your AI tools and your stored context: you save structured memories — project conventions, coding preferences, product decisions — and any connected tool recalls the relevant context on demand. The workflow runs through MCP, OAuth, or a REST API, covering ChatGPT, Claude, Cursor, VS Code, Gemini, Slack, and Telegram without requiring a local install or browser extension.
The differentiating mechanic is semantic, selective recall rather than dumping full conversation history. The vendor describes this as retrieving targeted context rather than re-sending a complete project brief each session — which, based on their published estimates, reduces token consumption by up to 90% versus pasting full context manually. That means your API bill drops alongside the friction, not just one or the other.
Memxus fits best in two scenarios: a developer running Claude for architecture review, Cursor for code completion, and ChatGPT for debugging, who is tired of re-establishing the same project context in each; and a small team that wants shared workspace memory so new members inherit project conventions from day one rather than from a two-week onboarding cycle. It fits poorly when your security policy requires data to stay on your own infrastructure — Memxus offers no self-hosted option, so your memories live in their cloud. Teams blocked by data residency requirements or internal compliance reviews will hit that wall before the first sprint ends.
On the integration side, the docs describe MCP and API access as the primary developer-facing surfaces, with native integrations handling ChatGPT and Claude directly. Slack connects both as a save source and a recall target. The dashboard gives you notebook-style visibility into what is stored, with edit and delete controls — which means if a saved decision becomes stale, you can update it rather than letting every tool recall outdated context.
Contribute
- Work on MEMXUS? Claim this listing.
- Embed a badge for your README or site.
Sign in to rate this tool or suggest an edit.