Home › Databases & Data › LLMSlim memory
LLMSlim memory
Long-term memory and context fitting for agents, with no LLM in the loop. Local SQLite.
Connect
Review any command before running it. Package names and URLs come from the server's own registry entry.
Package (pypi 0.12.0)
uvx llmslim
Or add to your MCP client config:
{
"mcpServers": {
"llmslim": {
"command": "uvx",
"args": [
"llmslim"
]
}
}
}
LLMSLIM_MEMORY_DB— SQLite file for the memory (default ~/.llmslim/memory.db)LLMSLIM_USER_ID— Whose memory this server holds (default "default")LLMSLIM_AGENT_ID— Optional agent id, so each agent keeps its own memory
This server takes extra arguments — see its repository.
Related servers
metabase/metabase
Lets AI clients search, explore, query, and visualize data in a Metabase instance.
context-mode
Free, local plugin that keeps tool output out of your coding agent's context window. Sandbox and SQLite FTS5 search, 99% fewer bytes in…
dbx
Query databases from AI agents using connections configured in DBX.
MCP Toolbox for Databases
MCP Toolbox for Databases enables your agent to connect to your database.
convex-backend
Convex database integration to introspect tables and functions and run one-off queries.
instant
Create, manage, and update applications on InstantDB, the modern Firebase.
Data from the Official MCP Registry