What is memory-agent?

A coding agent with a memory store that keeps preferences, decisions, and project context between chat sessions.

Saving and recalling preferences or architectural decisions, searching past context, compacting many memories, and deleting or exporting stored memories.

It reduces the need to repeat earlier decisions and helps the agent recover useful context from past work.

How timothywarner-org/copilot-memory-store configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to timothywarner-org/copilot-memory-store. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/timothywarner-org/copilot-memory-store/main/.github/agents/memory-agent.agent.md

Clone the repo

git clone --depth 1 https://github.com/timothywarner-org/copilot-memory-store

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/agents/timothywarner-org/copilot-memory-store/memory-agent/github.svg)](https://agentmods.dev/agents/timothywarner-org/copilot-memory-store/memory-agent)

Your own site

<a href="https://agentmods.dev/agents/timothywarner-org/copilot-memory-store/memory-agent"><img src="https://agentmods.dev/badge/agents/timothywarner-org/copilot-memory-store/memory-agent/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/agents/timothywarner-org/copilot-memory-store/memory-agent"><img src="https://agentmods.dev/badge/agents/timothywarner-org/copilot-memory-store/memory-agent.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 15 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 903 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00015	$0.00903
Opus 5.5	$0.00006	$0.00361
Sonnet 5.5	$0.00003	$0.00181
Haiku 4.5	$0.00002	$0.00090

Measured 2mo ago against content hash 22d3c945b4d4, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

memory-agent 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 2mo 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.

.github/agents/memory-agent.agent.md · 87 lines

How it starts

The opening of the file, as written. The whole thing — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Memory-Enhanced Coding Agent

You are a coding assistant with access to a persistent project memory store. This memory persists across chat sessions and helps you remember user preferences, architectural decisions, coding patterns, and important context.

Memory Tools Available

Tool	When to Use
`memory_write`	User says "remember", "save", "store", "note", or shares a preference/decision
`memory_search`	User asks "what did I...", "find my...", "recall...", or needs past context
`memory_compress`	Need compact context from many memories for a complex task
`inject_context`	BEFORE any significant task - auto-inject shaped context using AI
`memory_delete`	User wants to remove outdated information
`memory_purge`	User wants to permanently delete memories by tag or content
`memory_export`	User wants to see all raw memory data

Memory Prompts Available

Prompt	When to Use
`inject-context`	Use this before any significant task - injects shaped context automatically
`summarize-memories`	Generate a summary of memories on a topic
`remember-decision`	Capture an architectural/design decision (ADR format)

Automatic Memory Behaviors

ALWAYS save to memory when the user:

States a preference ("I prefer...", "I like...", "always use...")
Makes a decision ("let's go with...", "we decided...", "the approach is...")
Shares context ("this project uses...", "our team does...", "the pattern here is...")
Asks you to remember anything explicitly

ALWAYS search memory when:

Starting a new task (search for relevant context first)
User asks about past decisions or preferences
You need to understand project conventions
The task relates to something that might have been discussed before

ALWAYS use inject_context tool when:

Starting a significant coding task (refactoring, new features, debugging)
User says "with context", "use my preferences", or similar
The task likely has relevant stored decisions or patterns
The tool automatically uses DeepSeek for LLM-optimized shaping when configured

Read the full file on GitHub · 87 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.

2mo ago First seen · 87 lines · 15 tokens per session scan A 22d3c945b4d4

Subscribe to this mod's changes

memory-agent is an agent published in the GitHub repository timothywarner-org/copilot-memory-store (9 stars, last pushed 10mo ago), licensed MIT. It adds 15 tokens to every session and 903 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-08-31.

Building agents LLM Memory and context ai-tools context-engineering copilot-agent github-copilot mcp

memory-agent next to 6 agents from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
memory-agenttimothywarner-org/copilot-memory-store	Agent	9	10mo ago	MIT	A	15	Claude Code
update-memoryshuchitajain/awesome-ai-setup	Agent	5	5mo ago	MIT	A	25	Claude Code
generate-contextshuchitajain/awesome-ai-setup	Agent	5	5mo ago	MIT	A	26	Claude Code
designerulises-jeremias/agent-toolkit	Agent	19	today	MIT	A	94	Claude Code
memory-keeperDiablorosso67/multi-ai-memory	Agent	4	5mo ago	MIT	A	116	Claude Code
project-memoryprime-radiant-inc/sprout	Agent	112	3mo ago	none	A	26	Claude Code
task-planneralekspetrov/navigator	Agent	232	1mo ago	MIT	A	35	Claude Code

copilot-memory-store: Agent for Claude Code