Pmll Memory Mcp
by drQedwardscommunityv0.1.1
12
9
The PMLL Memory MCP server provides a persistent memory logic loop for Claude agents, featuring short-term key-value caching and a long-term memory graph for enhanced semantic retrieval.
From the registry: PMLL Memory MCP — persistent KV context memory and Q-promise deduplication.
Install & configure
Install in your client
Paste into the AI you're chatting with — it will figure out the rest
Please install the `pmll-memory-mcp` MCP server into my current AI client (that's you).
Canonical MCP server config (stdio transport):
- command: `npx`
- args: ["-y","pmll-memory-mcp"]
Note: 15 tools: short-term KV memory (5), long-term semantic memory graph (6, adapted from Context+), GraphQL (1), solution engine (3). In-process memory — no API keys needed. Designed as a 3rd initializer alongside Playwright.
Add this MCP server to my current client's config in the correct format for you. If you need secrets or credentials I haven't provided, ASK me — do not invent values or leave raw placeholders. After adding it, tell me how to verify the server is connected.Note: 15 tools: short-term KV memory (5), long-term semantic memory graph (6, adapted from Context+), GraphQL (1), solution engine (3). In-process memory — no API keys needed. Designed as a 3rd initializer alongside Playwright.
Tools (4)
init
Sets up the PMLL silo and Q-promise chain for a session.
peek
Checks the cache for a key without modifying it.
set
Stores a key-value pair in the short-term memory cache.
resolve
Checks or resolves a Q-promise continuation.
Environment variables
PYP_WORKSPACE_ROOTrequiredOverrides workspace detection.PYP_DEBUGEnables debug output.CUDA_VISIBLE_DEVICESControls GPU usage.Packages
pmll-memory-mcp
npmv0.1.1transport: stdio
Details
- Language
- Python
- License
- MIT
- Released
- Mar 8, 2026
- Last commit
- Apr 19, 2026
- Registry name
- io.github.drQedwards/pmll-memory-mcp