memory-agent

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

In plain words
What is it for?
Saving and recalling preferences or architectural decisions, searching past context, compacting many memories, and deleting or exporting stored memories.
Why use it?
It reduces the need to repeat earlier decisions and helps the agent recover useful context from past work.

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/timothywarner-org/copilot-memory-store/memory-agent
Clone the repo
git clone --depth 1 https://github.com/timothywarner-org/copilot-memory-store
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. 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 $0.00015 $0.00903
Opus 5 $0.00008 $0.00451
Sonnet 5 $0.00003 $0.00181
Haiku 4.5 $0.00002 $0.00090

Measured 2d ago against content hash 22d3c945b4d4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 2d 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.

  1. 2d 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 8mo ago), licensed MIT. It adds 15 tokens to every session and 903 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 2026-08-31.

Related

Other agents, from other repositories

python-architect

Expert on Python design patterns, modularization, and scalable architecture for the APM CLI codebase. Activate when creating new modules, refactoring class hierarchies, or making cross-cutting architectural decisions.

microsoft/apm · 45 tokens

doc-writer

APM documentation writer. Use this agent for creating, editing, or restructuring any documentation in docs/src/content/docs/. Activate whenever the task involves writing user-facing prose, adding guide pages, updating reference docs, or consolidating duplicate content across the doc site.

microsoft/apm · 51 tokens

cdo

APM Chief Documentation Officer. Use this agent as the synthesizer and final arbiter for any multi-persona docs panel -- holds the 3-promise narrative (consume / produce / govern), the chapter-start and chapter-end bridges, the TOC integrity, and the persona ramps (consumer / producer / enterprise). Activate to…

microsoft/apm · 95 tokens

algorithmic-patterns

Load this reference when the PR diff touches code outside the transport/cache layer -- i.e. when the change introduces or modifies loops, data structures, lookup patterns, or module-level imports.

microsoft/apm · 0 tokens

apm-expert

Expert on APM (Agent Package Manager). Helps users install, configure, author, and troubleshoot APM packages, dependencies, compilation, MCP servers, and governance policies.

microsoft/apm · 39 tokens

test-coverage-expert

Test-coverage expert paired with the DevX UX lens. Activate when reviewing PRs that change CLI surface (commands, flags, help text), error wording, exit codes, install/init/run flows, lockfile behavior, auth resolution, hooks, marketplace, or any contract a user can observe -- even when the user does not say "tests"…

microsoft/apm · 151 tokens