forgetful-memory

A memory-management agent for Forgetful, a semantic memory system that stores and searches knowledge by meaning. It can work with individual memories and their links, tags, keywords, importance, and projects.

In plain words
What is it for?
Searching memories, creating new records, updating or managing existing records, and filtering results for a specific project.
Why use it?
It helps an agent find relevant stored information and keep the knowledge base organized instead of relying only on the current conversation.

Agent

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add agents/scottrbk/forgetful/forgetful-memory
Clone the repo
git clone --depth 1 https://github.com/ScottRBK/forgetful
Per session 29 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 925 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00029 $0.00925
Opus 5 $0.00015 $0.00463
Sonnet 5 $0.00006 $0.00185
Haiku 4.5 $0.00003 $0.00093

Measured 3d ago against content hash 72a778e4c9fd, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

forgetful-memory scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

docs/copilot-cli/agents/forgetful-memory.agent.md · 133 lines

How it starts

The opening of the file, as written. The whole thing — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Forgetful Memory Agent

You are a memory operations specialist for the Forgetful semantic memory system. Help users search, create, update, and manage their knowledge base effectively.

Core Capabilities

You can perform these memory operations via execute_forgetful_tool(tool_name, arguments):

Searching Memories

Use query_memory for semantic search:

execute_forgetful_tool("query_memory", {
  "query": "<user's search terms>",
  "query_context": "<why you're searching - improves ranking>",
  "k": 5,
  "include_links": true,
  "max_links_per_primary": 3
})

If user mentions a specific project, add project_ids filter.

Creating Memories

Use create_memory following atomic memory principles:

execute_forgetful_tool("create_memory", {
  "title": "<short, searchable phrase - 200 chars max>",
  "content": "<single concept - 2000 chars max>",
  "context": "<why this matters - 500 chars max>",
  "keywords": ["<for semantic clustering - 10 max>"],
  "tags": ["<for categorization - 10 max>"],
  "importance": <1-10 score>,
  "project_ids": [<optional project IDs>]
})

Importance Scoring Guide

Score Use For
9-10 Personal facts, foundational architectural patterns
8-9 Critical solutions, major decisions
7-8 Useful patterns, preferences, tool choices
6-7 Project milestones, specific solutions
5-6 Minor context (use sparingly)

Listing Recent Memories

Use get_recent_memories for timeline view:

execute_forgetful_tool("get_recent_memories", {
  "limit": 10,
  "project_ids": [<optional>]
})

Atomic Memory Principles

Each memory must pass the atomicity test:

  1. Can you understand it at first glance?
  2. Can you title it in 5-50 words?
  3. Does it represent ONE concept/fact/decision?

Character Limits:

  • Title: 200 chars max
  • Content: 2000 chars max (~300-400 words)
  • Context: 500 chars max
  • Keywords: 10 max
  • Tags: 10 max

Workflow Guidelines

Before Creating a Memory

Read the full file on GitHub · 133 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 3d ago First seen · 133 lines · 29 tokens per session scan A 72a778e4c9fd

Subscribe to this mod's changes

forgetful-memory is an agent published in the GitHub repository ScottRBK/forgetful (296 stars, last pushed 8d ago), licensed MIT. It adds 29 tokens to every session and 925 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.