Windsurf Persistent Memory — Never Explain Your Stack Again
Windsurf is one of the most capable AI coding editors available — but every session starts blank. It doesn't remember your architecture, your recent bug fixes, or what your team decided last week. This guide shows you how to fix that in 30 seconds.
Why Windsurf forgets — and why that costs you
Windsurf operates within a context window. When a session ends — tab closes, computer restarts, you switch projects — everything is gone. The next session starts cold. No memory of:
- ✗Your architectural decisions and why you made them
- ✗The bug you spent three hours debugging last Tuesday
- ✗Your team's conventions around error handling and logging
- ✗Which third-party APIs have known quirks in your stack
- ✗What the codebase looked like before the last big refactor
Every session is a fresh start. You spend the first few minutes re-explaining context instead of writing code.
The fix: cachly MCP server
cachly connects to Windsurf via MCP (Model Context Protocol). Once connected, Windsurf's AI can use cachly's tools for permanent, cross-session recall.
smart_recallFinds stored lessons and context by meaning, not by exact key
causal_traceFollows a problem back to its root cause through your stored lessons
brain_predictReturns likely failures and the fixes that worked before
brain_from_gitTurns your last 100 commits into lessons during setup
learn_from_attemptsStores a lesson after a fix, so the next session finds it
recall_best_solutionReturns the best known solution for a topic, with a confidence marker
Setup: one command, 30 seconds
npx @cachly-dev/mcp-server@latest autopilotThe wizard auto-detects Windsurf and writes the correct MCP config to ~/.codeium/windsurf/mcp_config.json. One browser click to sign in. No API keys to manage:
// ~/.codeium/windsurf/mcp_config.json (auto-written by cachly setup)
{
"mcpServers": {
"cachly": {
"command": "npx",
"args": ["-y", "@cachly-dev/mcp-server@latest"],
"env": {
"CACHLY_JWT": "your-token-here"
}
}
}
}If you also use Claude Code, Cursor, or GitHub Copilot, the setup wizard detects those too and configures them all in the same pass. Same Brain, all editors.
brain_from_git: context before session one
After setup, cachly automatically runs brain_from_git — it reads your last 100 commits and loads the lessons into your Brain:
# What brain_from_git extracts from your git log:
✓ Fix: JWT expiry check before signature validation (commit a3f91c2)
✓ Revert: Redis pub/sub removed — race condition at scale (commit 8b2e441)
✓ Decision: tRPC over REST — type safety across monorepo (commit f9c1203)
✓ Warning: Stripe webhook order not guaranteed — always idempotentWindsurf arrives at your first session already knowing years of your team's decisions — without you writing a single documentation line.
What a session looks like with cachly
Open Windsurf. On the first tool call, smart_recall fires automatically:
> Good morning. Here's what I remember:
>
> Last session: payments refactor — stripe-webhook.ts
> Team learned: always set idempotency_key for Stripe charges
> → commit a3f91c2, 2025-11-14
>
> brain_predict: ⚠️ Moderate deploy risk
> The k8s namespace change in PR #441 matches a past
> race condition pattern (incident 2024-08-12).No prompting. No manual context. Windsurf just knows.
cachly works across all your editors
One Brain, shared across every tool in your workflow:
Windsurf
✓ supported
Claude Code
✓ supported
Cursor
✓ supported
GitHub Copilot
✓ supported
Run the setup once — cachly configures all detected editors automatically. Switch between editors without losing any context.
Give Windsurf memory in 30 seconds
npx @cachly-dev/mcp-server@latest autopilotAuto-detects Windsurf, Claude Code, Cursor, Copilot. Free tier, no credit card, German servers.
Get your free token →cachly.dev
For solo developers, teams and whole companies
Explain it once. Every AI knows it.
cachly keeps what you explain to your AI in every session. Claude Code, Cursor, Copilot and Windsurf read your rules, decisions and solved bugs: for you alone, for your whole team and for every team in your company. Servers in Germany, with SSO and a DPA for companies.
Servers in the EU · one command, restart your editor, done · 1 project free
Four ways to install
- Claude Code
/plugin marketplace add cachly-dev/cachly-mcp /plugin install cachly-brain@cachlyThen turn on auto-update once:
/plugin→ Marketplaces → cachly → Enable auto-update- Any MCP editor
npx @cachly-dev/mcp-server@latest autopilot- JetBrains
- JetBrains Marketplace: cachly-brain