live-memory
by shofer-dev
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| LIVE_MEMORY_MODEL | No | Model name (e.g., deepseek-chat, claude-3-haiku-20240307). | |
| LIVE_MEMORY_API_KEY | No | API key for the provider. | |
| LIVE_MEMORY_BASE_URL | No | Base URL for OpenAI-compatible provider (e.g., https://api.deepseek.com). | |
| LIVE_MEMORY_DATA_DIR | No | Directory for persistent snapshot storage. | ~/.claude/plugins/data/live-memory |
| LIVE_MEMORY_LOG_FILE | No | Path to a rotating log file (plain text, in addition to journald). | |
| LIVE_MEMORY_PROVIDER | No | Provider to use: 'anthropic' or 'openai'. Zero-config uses subscription OAuth with Anthropic. | anthropic |
| LIVE_MEMORY_KEEP_WARM | No | Enable background cache keep-warm loop. | false |
| LIVE_MEMORY_LOG_LEVEL | No | Log level: DEBUG, INFO, WARNING, ERROR. | INFO |
| LIVE_MEMORY_ASYNC_TOOLS | No | Enable async fire-and-forget tools (ask_live_memory_submit/result). | false |
| LIVE_MEMORY_CONCURRENCY | No | Concurrency model per workspace: 'parallel' (fork window) or 'serial' (one question at a time). | parallel |
| LIVE_MEMORY_LOG_BACKUPS | No | Number of backup log files to retain. | |
| LIVE_MEMORY_LOG_MAX_BYTES | No | Max bytes for log file before rotation. | |
| LIVE_MEMORY_REPO_ROOT_MODE | No | Repo root resolution inside submodules: 'nearest' (submodule's root) or 'outermost' (superproject root). | nearest |
| LIVE_MEMORY_MAX_ANSWER_TOKENS | No | Hard cap for answer tokens in ask_live_memory. | |
| LIVE_MEMORY_KEEP_WARM_INTERVAL_S | No | Interval in seconds for keep-warm pings. | |
| LIVE_MEMORY_KEEP_WARM_MAX_IDLE_S | No | Max idle time in seconds before stopping keep-warm for a workspace. | |
| LIVE_MEMORY_MAX_PARALLEL_QUERIES | No | Maximum concurrent questions per workspace in parallel mode. | 4 |
| LIVE_MEMORY_CANONICALIZE_WORKSPACE | No | Snap cwd to its git repo root (true) or use exact directory (false). | true |
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
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
No tools | |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
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