cachly-mcp

# 🧠 cachly AI Brain — MCP Server

> ### ChatGPT and Claude remember your conversations.
> ### cachly remembers your codebase.
>
> The bug you fixed. Why you chose Postgres. The deploy step that always breaks — and
> everything your teammates learned. **It stays when someone leaves the team, and it
> comes along when you switch assistants.**

<p align="center">
  <a href="https://www.npmjs.com/package/@cachly-dev/mcp-server">
    <img src="https://img.shields.io/npm/v/@cachly-dev/mcp-server?color=violet&logo=npm" alt="npm version" />
  </a>
  &nbsp;
  <a href="https://www.npmjs.com/package/@cachly-dev/mcp-server">
    <img src="https://img.shields.io/npm/dw/@cachly-dev/mcp-server?color=blue&label=weekly%20installs" alt="npm downloads" />
  </a>
  &nbsp;
  <a href="https://cachly.dev">
    <img src="https://img.shields.io/badge/Free%20tier-€0%2Fmo-brightgreen" alt="Free tier" />
  </a>
  &nbsp;
  <a href="https://cachly.dev/legal">
    <img src="https://img.shields.io/badge/GDPR-EU%20servers-green" alt="GDPR: EU servers" />
  </a>
  &nbsp;
  <img src="https://img.shields.io/badge/122_MCP_tools-violet" alt="122 MCP tools" />
  &nbsp;
  <img src="https://img.shields.io/badge/License-Apache--2.0-yellow" alt="License: Apache-2.0" />
</p>

<p align="center">
  <strong><a href="https://cachly.dev/sign-up">⚡ Get your free Brain → cachly.dev</a></strong><br/>
  <sub>Free forever · no credit card · 1-command setup · German servers · GDPR</sub>
</p>

---

## The story you already live every day

You are a good engineer. You want to **ship**, not babysit a forgetful assistant.

But every session starts at zero. Your AI doesn't remember the race condition you
chased for three hours on Tuesday. It doesn't know your deploy gotchas. It can't tell
you that **Carol already solved this exact bug in March** — because Carol's knowledge
lives in Carol's head, and yours in yours.

So you re-explain. You re-research. Your team makes the same mistake in five different
branches. And when someone leaves, their hard-won knowledge walks out the door with them.

> **The villain isn't your AI. It's amnesia.** Context death between sessions, and
> knowledge silos between people. The average developer loses **~45 minutes a day**
> re-establishing context that should already exist.

You don't need a smarter model. **You need a memory that doesn't reset — and one that
your whole team shares.**

---

## Meet your guide

cachly is the brain layer that sits under whatever AI you already use. We've watched
hundreds of teams lose the same knowledge the same way, and we built the fix:

- **It learns automatically** — from every commit, every fix, every session. No extra calls.
- **It arrives pre-briefed** — your AI opens each session already knowing your stack.
- **It's shared** — one engineer's solved bug becomes the whole team's reflex.
- **It's provable** — quality-aware recall beats raw text search by **+33.3 % Precision@1**
  ([see the benchmark](./BENCH.md)). A claim without a number is marketing; this is the number.
- **It's neutral** — speaks [MCP](https://modelcontextprotocol.io), so it works with
  Claude, Cursor, Copilot, Windsurf, Cline, Zed. Switch models anytime — **your brain stays.**

We're not the hero of this story. **You are.** cachly is the thing that makes you the
engineer whose AI never forgets and whose team compounds knowledge instead of losing it.

---

## Taste it first — no account, no risk

```bash
npx @cachly-dev/mcp-server@latest demo
```

Run it in any project folder. It reads YOUR git history and shows what your AI *would*
know — your bugs fixed, your patterns, your past decisions. Nothing leaves your machine.

```
┌─────────────────────────────────────────────────────────────┐
│  Brain Preview — What your AI would know                    │
├─────────────────────────────────────────────────────────────┤
│  Commits: 847   Lessons: 634   Contributors: 7              │
│  Date range: 2024-01-12 → 2026-05-14                        │
├─────────────────────────────────────────────────────────────┤
│  Security fixes your AI would know:                         │
│  • fix(auth): JWT expiry check before signature validation  │
│  • security: sanitize webhook payload before JSON.parse     │
├─────────────────────────────────────────────────────────────┤
│  Bug fixes your AI would remember:                          │
│  • fix: Redis pub/sub race condition under high concurrency │
│  • fix: k8s readinessProbe threshold too low for cold start │
│  • fix: Stripe idempotency_key missing on retry path        │
├─────────────────────────────────────────────────────────────┤
│  With cachly, your AI arrives pre-briefed every session.    │
└─────────────────────────────────────────────────────────────┘
```

Like what you see? Make it permanent in the next step.

---

## Brain-first — Semantic Cache as Proof-Point

cachly is not a semantic cache with a brain bolt-on. The Brain is the product. The
Semantic Cache is the **proof-point** — it shows ROI in dollars from day one, with zero
trust required. It opens the door. The Brain is why teams never leave.

| | Wedge — Land | Moat — Retain |
|---|---|---|
| **Feature** | Semantic Cache | AI Brain (Lessons, Recall, Team-Sharing) |
| **Value** | Measurable cost savings from day one | Compounding team intelligence |
| **Metric** | Cache-hit rate, $/month saved | Lessons retained, WoW trend, recall quality |
| **Analogy** | Datadog APM (surfaces the problem) | Stripe (becomes critical infrastructure) |

**The org-level advantage:** Brain lessons and cache hits are shared across the whole
team — one person's fix becomes every agent's reflex. Anthropic Projects Memory is
per-user and model-locked. cachly is team-wide and model-neutral. That's the structural
moat no first-party tool can build.

---

## Setup — one command

```bash
npx @cachly-dev/mcp-server@latest autopilot
```

Autopilot does everything in a single command: it auto-detects every AI editor you use,
writes the MCP config, signs you in via browser device-flow (one click, no password, no
credit card), and bootstraps your brain from git history. Restart your editor and your AI
arrives pre-briefed — every session, automatically.

> **Already inside Claude / Cursor / Copilot?** Paste this to your AI and it configures everything itself:
> ```
> Set up cachly for this project. Run: npx @cachly-dev/mcp-server@latest autopilot
> It gives my AI persistent memory across sessions. Follow the browser login
> (one click, no credit card), then restart the editor.
> ```

**Our agreement with you:** Free forever tier. GDPR, EU servers. No model lock-in —
leave anytime and take your data: `npx @cachly-dev/mcp-server@latest export` writes
every lesson to `lessons.md` (to read) and `lessons.jsonl` (to reuse). Code excerpts
are stored only if you call `index_project` yourself — and only on your own EU
instance.

---

## What changes the moment you turn it on

| The moment | Without cachly | With cachly |
|-----------|----------------|-------------|
| Session start | *"What's your architecture again?"* | *"Ready. 23 lessons. Last session: deployed API."* |
| A known bug returns | Re-researches from scratch | *"You fixed this March 12 — here's the exact command."* |
| You open an unfamiliar file | Cold start | *"Carol fixed 3 bugs here. Related: `fix:stripe-retry`."* |
| A teammate leaves | Their knowledge leaves too | Their lessons stay, attributed, searchable |
| New hire, day one | Weeks to onboard | `setup` → full team context instantly |
| Pre-deploy | Hope nothing breaks | Brain predicts failure risks from past patterns |

This is the transformation: from the engineer who **re-explains everything every
morning** → to the team whose **collective brain never forgets and gets sharper with
every commit.**

---

## cachly vs. Claude's built-in memory

Anthropic now ships memory for Claude — and it's genuinely good for **one developer,
using only Claude, alone.** That's not the game we're playing. Here's the honest map:

| | **cachly** | **Claude built-in memory** |
|--|------------|----------------------------|
| Works across **teams** | ✅ one engineer's fix → everyone's reflex | ❌ per-user / per-agent only |
| Works across **models & tools** | ✅ MCP — Claude, Cursor, Copilot, Windsurf, Zed… | ❌ Claude + Anthropic API only |
| **Structured** knowledge | ✅ topic · outcome · severity · causal graph | ⚠️ flat text files, read linearly |
| **Causal root-cause** (`causal_trace`) | ✅ problem → chain → proven fix | ❌ |
| **Provable recall quality** | ✅ +33.3 % Precision@1 vs. BM25 ([benchmark](./BENCH.md)) | ❌ no public metric |
| **Governance** (review, attribution, audit) | ✅ `team_confirm`, roles, audit trail | ❌ |
| **Self-hosting / BYOK / VPC** | ✅ data stays in your infra | ❌ Anthropic-hosted |
| Survives a **model switch** | ✅ your brain is yours | ❌ memory is gone or fragmented |
| Zero-setup for one solo user | ⚠️ ~1 command | ✅ built in |

**The honest takeaway:** if you're a solo dev who only ever uses Claude, the built-in
memory is great — use it. If you work on a **team**, switch tools, care about **proof**,
or need **governance and data residency**, that's a gap Anthropic structurally can't
close without breaking its own lock-in. **That gap is where cachly wins.**
*(Full strategic analysis: [STRATEGY.md](./STRATEGY.md).)*

---

## vs. other memory tools

| | cachly | mem0 | MemGPT / Letta | Plain CLAUDE.md |
|--|--------|------|----------------|-----------------|
| Persistent memory | ✅ | ✅ | ✅ | Manual |
| MCP server (no code changes) | ✅ | ✅ | ❌ | ✅ |
| Causal root cause analysis | ✅ | ❌ | ❌ | ❌ |
| Fully automatic (no explicit calls) | ✅ | ❌ | ❌ | ❌ |
| Team knowledge graph + attribution | ✅ | Paid | ❌ | ❌ |
| Provable recall lift (published) | ✅ | ❌ | ❌ | ❌ |
| Git-ambient learning | ✅ | ❌ | ❌ | ❌ |
| GDPR / EU servers | ✅ | ❌ | ❌ | ✅ |
| Free tier forever | ✅ | Limited | ❌ | ✅ |

---

## The standout moves

| Capability | What it does |
|------