Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
LIVE_MEMORY_MODELNoModel name (e.g., deepseek-chat, claude-3-haiku-20240307).
LIVE_MEMORY_API_KEYNoAPI key for the provider.
LIVE_MEMORY_BASE_URLNoBase URL for OpenAI-compatible provider (e.g., https://api.deepseek.com).
LIVE_MEMORY_DATA_DIRNoDirectory for persistent snapshot storage.~/.claude/plugins/data/live-memory
LIVE_MEMORY_LOG_FILENoPath to a rotating log file (plain text, in addition to journald).
LIVE_MEMORY_PROVIDERNoProvider to use: 'anthropic' or 'openai'. Zero-config uses subscription OAuth with Anthropic.anthropic
LIVE_MEMORY_KEEP_WARMNoEnable background cache keep-warm loop.false
LIVE_MEMORY_LOG_LEVELNoLog level: DEBUG, INFO, WARNING, ERROR.INFO
LIVE_MEMORY_ASYNC_TOOLSNoEnable async fire-and-forget tools (ask_live_memory_submit/result).false
LIVE_MEMORY_CONCURRENCYNoConcurrency model per workspace: 'parallel' (fork window) or 'serial' (one question at a time).parallel
LIVE_MEMORY_LOG_BACKUPSNoNumber of backup log files to retain.
LIVE_MEMORY_LOG_MAX_BYTESNoMax bytes for log file before rotation.
LIVE_MEMORY_REPO_ROOT_MODENoRepo root resolution inside submodules: 'nearest' (submodule's root) or 'outermost' (superproject root).nearest
LIVE_MEMORY_MAX_ANSWER_TOKENSNoHard cap for answer tokens in ask_live_memory.
LIVE_MEMORY_KEEP_WARM_INTERVAL_SNoInterval in seconds for keep-warm pings.
LIVE_MEMORY_KEEP_WARM_MAX_IDLE_SNoMax idle time in seconds before stopping keep-warm for a workspace.
LIVE_MEMORY_MAX_PARALLEL_QUERIESNoMaximum concurrent questions per workspace in parallel mode.4
LIVE_MEMORY_CANONICALIZE_WORKSPACENoSnap cwd to its git repo root (true) or use exact directory (false).true

Capabilities

Server capabilities have not been inspected yet.

Tools

Functions exposed to the LLM to take actions

NameDescription

No tools

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/shofer-dev/claude-code-live-memory'

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