Agent Memory Engine
by rgolabs
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| MEM_DENY | No | Comma-separated tool names to deny | |
| MEM_ROOT | No | Directory holding namespaces; .memory for a per-project store | ~/.agent-memory |
| MEM_ACTOR | No | Actor name written to the audit log | agent |
| MEM_ALLOW | No | Comma-separated tool names to allow | |
| MEM_OFFLINE | No | 1 forbids model downloads (fails loudly if not cached) | |
| MEM_PROFILE | No | read-only, standard or administrative tool set | standard |
| MEM_CAPACITY | No | Records per namespace before compaction runs (0 = unlimited) | 0 |
| MEM_EMBEDDER | No | onnx:<model>[@dtype] or ngram[:dim] | onnx:all-MiniLM-L6-v2 |
| MEM_LEARNING | No | 1 lets recorded outcomes influence ranking | |
| MEM_NAMESPACE | No | Default namespace; every tool also accepts namespace | default |
| MEM_MODEL_CACHE | No | Pinned model cache, prepopulate for offline hosts | ~/.cache/agent-memory/models |
| MEM_ALLOW_FALLBACK | No | 1 permits the lexical n-gram fallback when the model cannot load | |
| MEM_EMBEDDER_DTYPE | No | q8 (23 MB) or fp32 (90 MB) weights | q8 |
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 | |
This server cannot be deployed
Maintenance
ActivityMaintained
ResponsivenessNo issues