Memstate + GitHub Copilot
Give GitHub Copilot structured memory that persists across sessions.
GitHub Copilot loses context between sessions. Memstate gives Copilot a persistent memory layer via MCP — your tech stack, architecture decisions, and project context are always available.
Get Your API Key
Sign up for free — no credit card required.
Sign Up FreeAlready have an account? Go to API Keys →
Add MCP Configuration
Add this to your GitHub Copilot MCP config file. Replace YOUR_API_KEY_HERE with your key.
{
"servers": {
"memstate": {
"command": "npx",
"args": ["-y", "@memstate/mcp"],
"env": {
"MEMSTATE_API_KEY": "YOUR_API_KEY_HERE"
}
}
}
}Save to:
.vscode/mcp.jsonVS Code Copilot uses a different config format
GitHub Copilot in VS Code uses "servers" (not "mcpServers") in its mcp.json config file.
You can also add MCP servers via VS Code → Extensions → search @mcp, or run MCP: Add Server from the Command Palette.
Add Agent Rule
This rule tells GitHub Copilot to load your project context before tasks and save summaries after — automatically, every session.
# Memstate MCP - Memory Storage
This project uses Memstate MCP for persistent, versioned memory across sessions.
## REQUIRED: Start and end every task with memory
**BEFORE starting any task**, load relevant context so you don't redo past work or revert intentional decisions. **Prefer targeted retrieval** — do not dump the full memory tree by default.
**Default — search by what you're working on:**
```
memstate_search(query="<task topic>", project_id="<your_project>")
```
**When you know the exact keypath — fetch that subtree only:**
```
memstate_get(project_id="<your_project>", keypath="<subtree>")
```
**Full tree (discovery only):** `memstate_get(project_id="<your_project>")` with **no keypath** returns **every memory** in the project. Use this only when you need to explore the full tree to discover keypaths and values — not as the default before every task.
**AFTER completing any task**, save what you did so the next session has context:
```
memstate_remember(project_id="<your_project>", content="## Task Summary\n- What was done\n- Key decisions made\n- Files modified", source="agent")
```
Reading before tasks and saving after are both important. Skipping them means the next session starts blind.
## Tool reference
| Tool | When to use |
|------|-------------|
| memstate_search | **Default before tasks.** Find relevant memories by meaning. Returns ranked results without flooding context. |
| memstate_get | Fetch a **specific subtree** when you know the keypath. With no keypath, returns the **full project tree** — discovery/exploration only. |
| memstate_remember | **End of every task.** Save markdown summaries, notes, decisions. |
| memstate_set | Store a single key=value fact (e.g. config.port). Not for summaries. |
| memstate_history | View version history of a keypath. |
| memstate_delete | Soft-delete a keypath (history preserved). |
## Project naming
Use a short snake_case name matching your repo or topic (e.g. my_app, api_service). All related memories should share the same project_id.Paste into .github/copilot-instructions.md or AGENTS.md at your project root.
Test It — Onboard Your Project
Restart GitHub Copilot, open a project, and paste this prompt. It will create your first memories and confirm everything is working.
Replace <your_project> with a short name for your repo (e.g. my_app).
I'm onboarding Memstate AI memory for this project. Please:
1. Analyze this codebase and write a concise high-level architecture overview in markdown — covering the main components, tech stack, key directories, and how data flows through the system.
2. Save it to Memstate using: memstate_remember(project_id="<your_project>", content="<the markdown>", source="agent")
3. Then call memstate_search(query="architecture overview", project_id="<your_project>") and show me the results so I can confirm it worked.What to expect
Your agent will analyze the codebase, write an architecture overview, save it to Memstate, then confirm with search results. You'll see structured memories like project.my_app.architecture — this context is now available in every future session automatically.
Related Resources
Mem0 vs Memstate
See how Memstate compares to Mem0 on the LoCoMo benchmark. Memstate scores 5.3x higher on fact recall accuracy (92.2% vs 17.5%) and 4.7x better on conflict detection (95.0% vs 20.2%).
What is AI Agent Memory?
Learn how structured, versioned memory differs from traditional RAG and vector search.