Skip to main content
Glama
bdombro

mem0-lite

by bdombro
OverviewSchemaRelated ServersScoreDiscussions
Python
Local

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
MEM0_DIRNoData directory for mem0-lite.~/.mem0
OPENAI_API_KEYNoRequired unless using Ollama. Your OpenAI API key.
MEM0_LITE_DEBUGNoSet to enable debug logging to debug.jsonl.
MEM0_LITE_GIT_GHNoBackground git GitHub integration. Default off.off
MEM0_LITE_USER_IDNoDefault user scope.$USER
MEM0_LITE_AGENT_IDNoOptional agent scope.
MEM0_LITE_GIT_FETCHNoBackground git fetch. Default off.off
MEM0_LITE_GIT_ROOTSNoPathsep-separated allowlist for git toplevels.
MEM0_LITE_LLM_MODELNoLLM model name. Defaults to llama3.2 with Ollama.llama3.2
MEM0_LITE_GIT_PROMOTENoBackground git promote. Default off.off
MEM0_LITE_LLM_PROVIDERNoLLM provider, e.g. ollama. Default is OpenAI via mem0ai.
MEM0_LITE_LOCK_TIMEOUTNoStore lock wait in seconds.30
MEM0_LITE_FEEDBACK_MODENoSet to '1' to enable feedback mode. Default off.off
MEM0_LITE_EMBEDDER_MODELNoEmbedder model. Defaults to nomic-embed-text with Ollama.nomic-embed-text
MEM0_LITE_PLUGINS_DISABLENoComma-separated plugin names to skip, e.g. git.
MEM0_LITE_EMBEDDER_PROVIDERNoEmbedder provider, e.g. openai or ollama.

Instructions

Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.

This server publishes no instructions, or was last inspected before Glama recorded them.

Capabilities

Features and capabilities supported by this server

Protocol revision2025-11-25

CapabilityDetails
tools
{
  "listChanged": false
}
prompts
{
  "listChanged": false
}
resources
{
  "subscribe": false,
  "listChanged": false
}
experimental
{}

Tools

Functions exposed to the LLM to take actions

NameDescription
add_memoryA

Store a memory. Prefer infer=false with a self-contained third-person fact.

memory_type: decision | convention | anti_pattern | user_preference | task_learning | environmental | identity | rule | project
infer=true lets mem0 extract facts from raw conversation; skip for explicit facts.
Never store secrets. Skip small talk, tool dumps, and one-shot commands.
search_memoriesA

Semantic search. Rewrite the query to 3-6 keywords matching stored third-person facts.

Do not pass the user's raw message. Drop pronouns and question words.
When useful, run 2-4 parallel searches with memory_type: decision, convention, anti_pattern, or omit for catch-all.
When MEM0_LITE_FEEDBACK_MODE is enabled, responses include ts; rate useful/miss/noise via rate_memory_call.
get_memory_by_idA

Fetch one memory by id. When MEM0_LITE_FEEDBACK_MODE is enabled, rate via rate_memory_call(call_ts).

list_memoriesC

List memories in scope. Not a substitute for search_memories. When MEM0_LITE_FEEDBACK_MODE is enabled, responses include ts; rate useful/miss/noise via rate_memory_call.

update_memoryA

Replace memory text in place. Prefer this over delete+add when a fact changed.

delete_memoryC

Delete one memory by id.

delete_all_memoriesC

Delete all memories in scope. Requires confirm=true.

rate_memory_callA

Rate a prior retrieval by call_ts (from response ts when MEM0_LITE_FEEDBACK_MODE is enabled).

Call when you used a hit, clearly missed a fact, or got irrelevant noise. Skip empty-and-expected results.
reason: used | empty_ok | miss | noise | stale | bad_query

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/bdombro/mem0-lite'

If you have feedback or need assistance with the MCP directory API, please join our Discord server