Skip to main content
Glama
ShmuelOps

hindsight-shared-memory

by ShmuelOps

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
HINDSIGHT_API_HOSTNoThe host address for the Hindsight API server. Upstream default is 0.0.0.0.127.0.0.1
HINDSIGHT_API_PORTNoThe port for the Hindsight API server.8888
HINDSIGHT_API_LLM_MODELNoThe LLM model to use. Fast extraction. Sonnet is more thorough but slower (~30 s per retain).claude-haiku-4-5
HINDSIGHT_API_LOG_LEVELNoThe log level.warning
HINDSIGHT_API_DATABASE_URLNoThe database URL. Embedded Postgres, data in ~/.pg0/instances/hindsight-shared/. Or a postgresql:// URL.pg0://hindsight-shared:5488
HINDSIGHT_API_LLM_PROVIDERNoThe LLM provider to use. Can be claude-code, ollama, openai, anthropic, …, or none (storage and search only, no LLM).claude-code
HINDSIGHT_API_MCP_ENABLED_TOOLSNoComma-separated allowlist of MCP tools.retain,recall,reflect,list_memories,invalidate_memory
HINDSIGHT_API_RERANKER_PROVIDERNoThe reranker provider.flashrank
HINDSIGHT_API_EMBEDDINGS_PROVIDERNoThe embeddings provider. Model BAAI/bge-small-en-v1.5.onnx

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

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