Who it is for
People who want the same memory available in every MCP-compatible tool.
Stem
Cross-AI memory: store, recall and link decisions and context
Overview
What Stem does
Stem is persistent memory that is not tied to one assistant. Decisions, facts, preferences and project context are stored as distilled memories, then recalled when a later conversation needs them.
Two things distinguish it from a note store. Memories link into a typed knowledge graph, so related ideas connect instead of sitting as a flat list, and the whole graph can be viewed at the publisher's site. Because it is reached over MCP, the same memory is available to every compatible tool a person connects, which is the point: context is explained once. A free tier exists. Community tier.
Tool surface
Credentials are required first, so five is the listing's count. Storing distilled memories, recalling relevant ones, linking them into a typed graph, and visualising the result are the described operations.
Availability
Where Stem is listed
Stem is listed in the Claude connectors directory only. Awase LLC has no app under the same domain in the ChatGPT directory; 392 of the 3,150 products here are on both marketplaces, and this is not one of them.
The MCP server behind a Claude connector is usually the same server a ChatGPT app would need, so the absence is a distribution decision rather than a technical one.
Claude listing
In the Claude connectors directory
Stem publishes 5 tools to Claude, a deliberately narrow surface; only 22.3% of the 1,253 Claude-listed connectors expose fewer.
The median Claude-listed connector filed under Productivity publishes 12, so this one sits 7 tools below its bucket's median, 336th of 462.
It falls in the 4-6 tools band, which holds 16.2% of the Claude directory.
Stem publishes a remote MCP endpoint. Claude connects to it over HTTP; there is nothing to install locally.
Every connector in the Claude directory is remote, all 1,253 of them, so transport is not a differentiator there.
- Publisher
- Awase LLC
- Verification
- Community-listed (61.5% of the Claude directory)
- Filed under
- Productivity
- Endpoint
-
https://awase.dev/stem - Documentation
- Publisher setup docs
- Published tools
- 5 · 4-6 tools band
- Depth rank in Productivity
- 336 of 462
- Snapshot
- August 2026
Stem is community-listed in the Claude directory, the tier 770 of 1,253 connectors sit in (61.5%). It is the default for a self-published server, and says nothing either way about quality.
In the publisher's words
How Awase LLC describes it
Stem is a persistent cross-AI memory. Connect it once and Claude can store distilled memories (decisions, facts, preferences, project context), recall the most relevant ones in any future chat, link related ideas into a typed knowledge graph, and visualize the whole brain at awase.dev/stem. The same memory is available to every MCP-compatible tool the user connects, so context never has to be re-explained. Free tier included; storage tiers are opt-in.
Quoted from the connector's own Claude directory listing as captured in August 2026. Node8 did not write it and does not vouch for it.
Nearby
Other Productivity connectors
Coconut Context
A versioned markdown context layer shared by people and agents
Claude
Great Arrow Digital
A private workspace memory shared across several AI assistants
Claude
Oneteam
Employee communications, academy courses, and reporting in Oneteam
Claude
skilder
Versioned skills and MCP tools distributed from one governed hub
Claude
UseMyContext.ai
Read-only personal context with cited document answers
Claude · ChatGPT
LILT
Brand-aligned machine and human-verified translation requests
Claude
This is an independent catalogue entry compiled by Node8 from Stem's public marketplace listing as it stood in August 2026. Listing facts come from the marketplaces; the comparisons against the rest of the directory and any live-endpoint measurements are Node8's. Node8 is not affiliated with Awase LLC, and inclusion here is not an endorsement.
Want your company reachable inside ChatGPT and Claude?
Node8 builds MCP servers end to end: deciding which tools are worth exposing, the authentication and permission model, the review submissions, and the onboarding that gets them used. One server serves ChatGPT, Claude, and Microsoft Copilot.