Skip to main content
Glama
furui

furui

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
FURUI_DB_PATHNoSQLite file path (created on first use). Default: ~/.furui/furui.db.~/.furui/furui.db
FURUI_PIN_FLOORNoLowest recency factor a pinned memory can reach (0–1). Default: 0.5.0.5
FURUI_HALF_LIFE_DAYSNoDays for an untouched memory to lose half its recency. Default: 30.30

Instructions

Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.

furui is your long-term memory. Memories fade unless they are used.

  • remember: store durable facts, preferences, decisions and lessons -- not transient chatter. Use importance 1-5 (5 = critical, 3 = normal) and a few short tags. Pin only things that must never be forgotten.

  • recall: search before answering questions that may depend on past context. Every memory returned is reinforced, so recall only what you actually need.

  • forget: delete a memory that is wrong or obsolete.

  • prune: periodically run with dry_run=true, review the list, then run again with dry_run=false to delete stale memories. Pinned memories are never pruned.

  • stats: inspect the overall health of memory (sizes, score spread, prunable counts).

Capabilities

Features and capabilities supported by this server

Protocol revision2025-11-25

CapabilityDetails
tools
{
  "listChanged": true
}
logging
{}
prompts
{
  "listChanged": true
}
resources
{
  "subscribe": false,
  "listChanged": true
}

Tools

Functions exposed to the LLM to take actions

NameDescription
rememberC

Store a new long-term memory.

recallA

Search memories by keyword overlap, ranked by relevance x current score.

Every returned memory is reinforced: its recall_count goes up and its decay clock resets. An empty query returns the strongest memories overall.

forgetA

Permanently delete one memory by id (works on pinned memories too).

pruneA

List or delete unpinned memories whose current score is below a threshold.

A brand-new importance-1 memory scores 1.0; an importance-3 memory left untouched for one half-life scores 1.5. Thresholds around 0.25-1.0 are typical.

statsA

Summary of the memory store: counts, score distribution, prunable counts, config.

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

TDQS

A3.6/5.0

Scored across 5 tools

Disambiguation5/5

Each tool maps to a distinct memory operation: remember (create), recall (search + reinforce), forget (delete by id), prune (threshold-based bulk cleanup), and stats (observability). The only adjacent pair—forget vs prune—is explicitly separated by id-based vs score-threshold deletion semantics and the pinned/unpinned distinction.

Naming Consistency4/5

All names are single-word, lowercase, and prefix-free, which reads as one coherent vocabulary. The minor deviation is that four are verbs (remember, recall, forget, prune) while stats is a noun, but it is conventional enough not to cause confusion.

Tool Count5/5

Five tools is well-scoped for a long-term memory store: one per lifecycle stage plus a diagnostics tool. Nothing appears redundant or padded, and no operation feels crammed together with another.

Completeness3/5

Create, search/read, single delete, bulk cleanup, and stats are covered, but there is no update operation to change importance or otherwise edit a memory, and no way to pin/unpin even though pinned state is referenced by forget and prune. Retrieval is also limited to keyword-overlap search with no direct get-by-id, which agents may need for confirm-before-forget workflows.

Maintenance

ActivityMaintained
ResponsivenessOutdated data