Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
MEMORY_DIRNoTier-1 memory search<ws>\.kb\memory
RLM_CONFIGNoExplicit config YAML path
RLM_FILE_PORTNoStable download-server port for this agent
RLM_STATS_LOGNoPer-agent usage JSONL; its parent dir is the shared stack-stats dir
READER_API_KEYNoReader endpoint (any OpenAI-compatible /chat/completions)
RLM_AGENT_NAMENoAgent identity; tool-name suffix + description tag (AGENT.md Domain: overrides the env domain)
READER_BASE_URLNoReader endpoint (any OpenAI-compatible /chat/completions)Ollama
RLM_AGENT_DOMAINNoAgent identity; tool-name suffix + description tag (AGENT.md Domain: overrides the env domain)
RLM_COMMON_RULESNoPath to the engine-wide COMMON-RULES.md served by get_session_rules
RLM_READER_MODELNoReader endpoint (any OpenAI-compatible /chat/completions)qwen3:4b
RLM_MEMORY_SEARCHNoTier-1 memory search1
RLM_READER_ENABLEDNo0 → raw ranked chunks (no distillation)1
RLM_READER_NOTHINKNoSuppress Qwen3/3.5 reader thinking via assistant prefill (fast path)
RLM_READER_TIMEOUTNoReasoning-reader headroom / HTTP timeout (s)120
RLM_RETRIEVAL_MODENogrep or hybrid (opt-in embeddings: pip install -e .[embeddings])grep
KNOWLEDGE_BASE_PATHNoWorkspace root (equivalent to --path)cwd
RLM_ENFORCE_SEMANTICNoAction-time gates1
RLM_GROUNDING_ENABLEDNoVerdict line behaviour1
RLM_ENFORCEMENT_ENABLEDNoAction-time gates1
RLM_GROUNDING_STRICTNESSNoVerdict line behaviourstrict
RLM_READER_THINK_ALLOWANCENoReasoning-reader headroom / HTTP timeout (s)0

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/lukiies/extended-rlm'

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