Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
PEON_AI_MODENoAI mode: gated or off (off disables all LLM calls).gated
PEON_DISABLEDNoIf set to any value, disables Peon entirely (for A/B testing).
PEON_DAEMON_URLNoURL of the Peon daemon.http://127.0.0.1:3737
PEON_MEMORY_DIRNoName of the per-project brain directory..peon
PEON_OLLAMA_URLNoURL for local Ollama embedding server.http://127.0.0.1:11434
OPENROUTER_API_KEYNoAPI key for consolidation and embeddings (OpenRouter recommended). Without this, Peon works lexical-only.
PEON_EMBEDDING_MODENoEmbedding mode: api, ollama, local, or off.auto
PEON_EMBEDDING_MODELNoEmbedding model name, e.g., openai/text-embedding-3-small or an Ollama model.
PEON_FLUSH_MIN_CHARSNoConsolidation cost gate: minimum characters before triggering consolidation.6000
PEON_PROCESSING_MODELNoModel used for consolidation.google/gemini-2.5-flash-lite
PEON_CONSOLIDATION_MAX_DELTA_CHARSNoMaximum chunk size for consolidation to prevent truncation stalls.60000

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/VineetV2/peon-mem'

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