general MCP Server
Agentic AI memory with Ebbinghaus forgetting curve decay. +16pp better recall than Mem0 on LoCoMo.
Discovered via github-topic:model-context-protocol and last synced 1mo ago.
Install instructions not detected yet
Check the source repository for the latest setup steps.
~11 days
~19 days
When a recalled memory is outdated or needs merging
e.g. `"coding-agent"`
~38 days
Start of every task — surface relevant context
~24 days
After learning a new preference, fact, failure, or strategy
`private`
Values
Options
When your AI calls it
Default
required
What it means
Query sent to cloud
BOTH_FOUND@5
`2`
Half-life
Strength (default) · Most recent · Recall count
`sachit`
Role
96.2%
Mem0 / Zep / LangMem
98.2%
Detail
31%*
84.2%
90.0%
18%*
Score
72.9%
95.5%
What it does
Asset
P A -. private .-> AP["🔒 Alice-only"] B -. private .-> BP["🔒 Bob-only"] style P fill:#0a2540,stroke:#19cdff,color:#fff style AP fill:#0c1424,stroke:#5a6b80,color:#8294a8 style BP fill:#0c1424,stroke:#5a6b80,color:#8294a8 ``` Role-based access is enforced per agent — what one engineer's agent learns, the whole team benefits from instantly; sensitive context stays scoped to its owner. ```bash POST /pools # create a pool POST /pools/{id}/members # add a member (with role) POST /pools/{id}/memories # contribute a shared memory POST /pools/{id}/retrieve # recall across the pool ``` --- ## 🛡️ Data Rights & Compliance Because memory that stores real data needs the controls to be trusted with it:
What it does