agent-memory-mcp copilot-instructions.md

agent-memory-mcp copilot-instructions.md is an instructions file for GitHub Copilot from jthiruveedula/agent-memory-mcp. It costs 917 tokens per session, scanned A, original, MIT.

A GitHub Copilot instruction file for a TypeScript MCP server that provides persistent agent memory across workspaces. It describes memory search, a personal knowledge graph, preference learning, tool recommendations, and reflection.

In plain words
What is it for?
Use it when developing or reviewing the server, its SQLite storage, memory search, graph features, or MCP tools.
Why use it?
It gives Copilot a clear overview of the server’s architecture and intended behavior when changing the code.

Instructions file for GitHub Copilot

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 instructions/jthiruveedula/agent-memory-mcp/copilot-instructions
Clone the repo
git clone --depth 1 https://github.com/jthiruveedula/agent-memory-mcp

Made for: GitHub Copilot.

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.

agentmods badge for agent-memory-mcp copilot-instructions.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/jthiruveedula/agent-memory-mcp/copilot-instructions.svg)](https://agentmods.dev/instructions/jthiruveedula/agent-memory-mcp/copilot-instructions)
Your own site
<a href="https://agentmods.dev/instructions/jthiruveedula/agent-memory-mcp/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/jthiruveedula/agent-memory-mcp/copilot-instructions.svg" alt="Measured on agentmods" height="20"></a>
Per session 917 This file is loaded in full into every session.
When invoked 917 The same file — it is already loaded in full.
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 $0.00917 $0.00917
Opus 5 $0.00458 $0.00458
Sonnet 5 $0.00183 $0.00183
Haiku 4.5 $0.00092 $0.00092

Measured 3d ago against content hash d061f3b88dff, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agent-memory-mcp copilot-instructions.md 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.

.github/copilot-instructions.md · 107 lines

How it starts

The opening of the file, as written. The whole thing — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Memory MCP — Copilot Instructions

Project Overview

This is a TypeScript MCP server that provides persistent, cross-workspace agent memory with:

  • Semantic + keyword memory recall (SQLite FTS5 + vector similarity)
  • Personal knowledge graph (entity/relation extraction)
  • Preference learning from explicit statements and corrections
  • Tool outcome logging and recommendation
  • Self-improvement via reflection (duplicate merge, insight surfacing)

SDK References

Architecture

  • src/index.ts — entry point (starts stdio transport)
  • src/server.ts — MCP server wiring (tools, resources, prompts)
  • src/config.ts — configuration from environment variables
  • src/types.ts — Zod schemas and TypeScript types
  • src/db/schema.ts — SQLite schema with versioned migrations
  • src/db/memory-store.ts — CRUD, FTS5 search, embeddings, graph persistence
  • src/db/embeddings.ts — hash-based local or OpenAI embedding generation
  • src/graph/knowledge-graph.ts — entity/relation extraction and graph queries
  • src/learning/preference-learner.ts — preference extraction from text and corrections
  • src/learning/tool-recommender.ts — tool outcome learning and ranking
  • src/learning/self-improver.ts — reflection, duplicate detection, confidence adjustment
  • src/tools/memory-tools.ts — MCP tool handlers (pure functions, context injected)

Conventions

  • Use Zod schemas in src/types.ts for all tool arguments.
  • Keep tool handlers pure; context is passed via ToolContext.
  • All storage goes through MemoryStore.
  • Embeddings default to local hashing-based vectors; optionally use OpenAI when OPENAI_API_KEY is set.
  • Data is stored in ~/.agent-memory-mcp/ by default (configurable via AGENT_MEMORY_DIR).
  • Schema versioning: src/db/schema.ts manages versioned migrations via _meta table.

Read the full file on GitHub · 107 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 · 107 lines · 917 tokens per session scan A d061f3b88dff

Subscribe to this mod's changes

agent-memory-mcp copilot-instructions.md is an instructions file published in the GitHub repository jthiruveedula/agent-memory-mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 917 tokens to every session, about $0.0046 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 2026-09-01.