@cachly-dev/mcp-server 0.6.0 → 0.7.0

package/README.md

@@ -1,12 +1,11 @@
-# cachly — The World's First Cognitive Cache
+# 🧠 cachly AI Brain — MCP Server
 
-> **A cache that thinks.**  
-> Not just managed Redis. The universal AI memory layer — persistent, self-managing, cross-model.  
-> One command. Your AI never forgets again.
+> **Persistent memory for Claude Code, Cursor, GitHub Copilot, Windsurf, Cline & Zed.**  
+> Your AI remembers every lesson, every fix, every architecture decision — forever.
 
 <p align="center">
-  <a href="https://github.com/cachly-dev/cachly-mcp/stargazers">
-    <img src="https://img.shields.io/github/stars/cachly-dev/cachly-mcp?style=social" alt="GitHub Stars" />
+  <a href="https://github.com/cachly-dev/mcp-server/stargazers">
+    <img src="https://img.shields.io/github/stars/cachly-dev/mcp-server?style=social" alt="GitHub Stars" />
   </a>
   &nbsp;
   <a href="https://www.npmjs.com/package/@cachly-dev/mcp-server">
@@ -24,256 +23,278 @@
   <a href="https://cachly.dev/legal">
     <img src="https://img.shields.io/badge/GDPR-EU%20only-green" alt="GDPR: EU only" />
   </a>
+  &nbsp;
+  <img src="https://img.shields.io/badge/License-Apache--2.0-yellow" alt="License: Apache-2.0" />
 </p>
 
 ---
 
-## What is a Cognitive Cache?
-
-Every cache stores data. cachly stores **meaning**.
-
-Five capabilities no other cache — or AI memory tool — has ever had:
-
-| Capability | What it does |
-|-----------|-------------|
-| **`memory_consolidate`** | Distill the entire knowledge base: detect contradictions, merge duplicates, prune stale memories — like garbage collection for your AI's brain |
-| **`brain_diff`** | Git-style diff for AI knowledge — shows exactly what was learned, forgotten, or updated across sessions |
-| **`causal_trace`** | Root cause analysis through memory — given a problem, traces backwards through the knowledge graph to find what caused it |
-| **`knowledge_decay`** | Temporal confidence scoring — every memory gets a freshness score that decays with time and rebounds with each recall |
-| **`autopilot`** | Zero-config AI memory — generates a CLAUDE.md that makes any AI manage its own brain automatically, forever |
+## 🆕 v0.6 — Cognitive Cache: Your AI Brain now *thinks* about what it knows
 
-This is not a tool you use. This is infrastructure that makes AI genuinely intelligent over time.
+> Redis stores bytes. LangChain stores text. **cachly v0.6 reasons over knowledge.**
 
----
+### The 5 tools no other memory system has:
 
-## One command. Permanent memory. No copy-paste.
+| Tool | What it does | Why it's different |
+|---|---|---|
+| `memory_consolidate` | Weekly garbage collector — detects contradictions, merges duplicates, expires stale | Like `git gc` for knowledge |
+| `brain_diff` | `git log` for your AI Brain — what changed this week? | See your AI's learning velocity |
+| `causal_trace` | Root Cause Analysis through memory: problem → chain → solution | **No other system can do this** |
+| `knowledge_decay` | Confidence score per lesson: `████░░░░ 40%` | Old knowledge rots. Now you know which |
+| `autopilot` | Generates CLAUDE.md that makes any AI self-managing, forever | Zero manual calls. One command. Done. |
 
-```bash
-npx @cachly-dev/mcp-server@latest setup
+**The `causal_trace` moment:**
 ```
+causal_trace(problem="auth breaks after restart")
 
-Browser opens → sign in → Brain provisioned → every editor configured automatically.  
-No dashboard visit. No API keys to copy. No instance IDs to manage.
+→ Root: k8s:namespace-terminating
+→ Via:  keycloak:jwks-race  
+→ Fix:  PollUntilContextTimeout 3min  ← used this March 12, worked
+```
+*30 minutes of git blame + log archaeology. In one call.*
 
 ---
 
-## What it looks like
+## The Problem
 
-Every session starts with this instead of a blank slate:
+Every morning, you open your AI coding assistant. It doesn't remember yesterday.  
+You explain your architecture. You explain the deployment process. You explain the bug you fixed last week.
 
-```
-🧠 Session Briefing
+**The average developer wastes 45 minutes/day re-establishing context.** That's €15,000+ in lost productivity per engineer per year.
 
-📅 Last session (2h ago): Fixed auth redirect loop in Next.js middleware
-   Duration: 47 min · Files: middleware.ts, auth.config.ts, .env.local
+## The Fix — One Command
 
-📊 Brain: 23 lessons · 5 context entries · 38 recalls · ~9.5h saved
+```bash
+npx @cachly-dev/mcp-server@latest setup
+```
 
-🎯 Relevant for "auth":
-  ✅ next:middleware-auth — matcher must exclude /_next/static paths (negative lookahead)
-  ✅ keycloak:refresh-token — use httpOnly cookie, not localStorage — Safari blocks third-party
-  ❌ oauth:pkce — PKCE + CORS broken in Safari 16.3, still unresolved
+The interactive wizard:
+1. Signs you in (free, no credit card required)
+2. Picks or creates your AI Brain instance
+3. **Auto-detects** Cursor, Windsurf, VS Code, Claude Code, Continue.dev, **Cline & Zed**
+4. Writes the correct MCP config for every detected editor
+5. Creates `CLAUDE.md` with memory rules pre-filled
+6. Shows your Brain Health snapshot right in the terminal
 
-🕐 Recent lessons:
-  ✅ redis:pipeline-batching — pipeline() for N writes, 10× faster than sequential
-  ✅ deploy:healthcheck — readinessProbe.failureThreshold must be ≥ 10 on cold starts
-  ✅ typescript:strictNullChecks — enable in tsconfig, catches 30% of runtime errors at compile time
+**Index your project** into the Brain for instant semantic search:
+```bash
+npx @cachly-dev/mcp-server@latest index .
 ```
 
-Your AI arrives pre-briefed. No repeating yourself. No re-explaining the architecture.
+**Result:** Your AI remembers everything. Always.
 
 ---
 
-## The Cognitive Cache in Action
-
-### Root Cause Analysis Through Memory
-
-```
-causal_trace(problem="auth fails after namespace restart")
+## Quick Start (Manual)
 
-🔍 Causal Trace — "auth fails after namespace restart"
+**Step 1 — Get your free credentials** at [cachly.dev](https://cachly.dev) (25 MB free, forever, no credit card).
 
-Found 7 related memories (3 failures · 1 partial · 2 fixes)
+**Step 2 — Add to your editor's MCP config:**
 
-❌ Root causes / similar failures:
-  1. [12.03.2025] 🔴 `k8s:namespace-terminating` (relevance 9/10)
-     ↳ Cannot create resources in Terminating namespace — must wait for full deletion
-  2. [08.02.2025] 🟡 `keycloak:jwks-cache-race` (relevance 6/10)
-     ↳ Concurrent JWKS map access panics under load — needs RWMutex
+<details>
+<summary><b>Claude Code</b> (<code>~/.claude/mcp.json</code> or <code>.mcp.json</code>)</summary>
 
-✅ What solved similar problems:
-  • `k8s:namespace-wait` — PollUntilContextTimeout 3min loop until NotFound
-  • `auth:jwks-singleton` — double-checked locking pattern, init once on startup
+```json
+{
+  "mcpServers": {
+    "cachly": {
+      "type": "stdio",
+      "command": "npx",
+      "args": ["-y", "@cachly-dev/mcp-server@latest"],
+      "env": {
+        "CACHLY_JWT": "your-jwt-token",
+        "CACHLY_INSTANCE_ID": "your-instance-id"
 
-🧩 Likely causal chain:
-  `k8s:namespace-terminating`
-    ↓ led to `keycloak:jwks-cache-race`
-    ↓ current symptom: auth fails after namespace restart
+Every morning, you open your AI coding assistant. It doesn't remember yesterday.  
+You explain your architecture. You explain the deployment process. You explain the bug you fixed last week.
 
-🎯 Recommended fix: apply `k8s:namespace-wait` solution
-```
+**The average developer wastes 45 minutes/day re-establishing context.** That's €15,000+ in lost productivity per engineer per year.
 
-### Knowledge Decay — Trust What's Still True
+## The Fix — One Command
 
+```bash
+npx @cachly-dev/mcp-server@latest setup
 ```
-knowledge_decay(threshold_days=30)
 
-⏱️ Knowledge Decay Analysis
+The interactive wizard:
+1. Signs you in (free, no credit card required)
+2. Picks or creates your AI Brain instance
+3. **Auto-detects** Cursor, Windsurf, VS Code, Claude Code, Continue.dev, **Cline & Zed**
+4. Writes the correct MCP config for every detected editor
+5. Creates `CLAUDE.md` with memory rules pre-filled
+6. Shows your Brain Health snapshot right in the terminal
 
-🧠 31 total memories · 24 healthy (avg 88% confidence) · 7 decaying
-
-⚠️ 7 memories need re-verification:
-
-  ██████████ 100% — `auth:jwt-refresh` (3d old · recalled 5×)
-  ████████░░  80% 🟡 `k8s:resource-limits` (45d old · recalled 1×)
-  █████░░░░░  52%    `deploy:docker-compose` (78d old · recalled 0×)
-  ███░░░░░░░  31% 🔴 `stripe:webhook-secret` (112d old · recalled 0×)
-  ██░░░░░░░░  22%    `react:concurrent-mode` (140d old · recalled 0×)
-
-💡 Re-validate top decaying memories before critical tasks.
+**Index your project** into the Brain for instant semantic search:
+```bash
+npx @cachly-dev/mcp-server@latest index .
 ```
 
-### Brain Diff — See What You've Learned
+**Result:** Your AI remembers everything. Always.
 
-```
-brain_diff(since_sessions=5)
+---
 
-📊 Brain Diff — knowledge delta over last 5 sessions
+## Quick Start (Manual)
 
-🧠 Total: 31 lessons · +12 new · 19 pre-existing
+**Step 1 — Get your free credentials** at [cachly.dev](https://cachly.dev) (25 MB free, forever, no credit card).
 
-📅 Sessions covered:
-  • 04.05.2026 (23m) — Fixed auth redirect loop + pushed to main
-  • 03.05.2026 (61m) — K8s provisioner: namespace termination wait
-  • 02.05.2026 (34m) — Token refresh + JWKS race condition
+**Step 2 — Add to your editor's MCP config:**
 
-➕ 12 new lessons learned:
-  ✅ 🔴 `auth:token-refresh` — Store refresh token in JWT callback, refresh at <60s TTL
-  ✅ 🟡 `k8s:namespace-terminating` — Wait 3min via PollUntilContextTimeout before recreate
-  ✅ 🟡 `api:status-codes` — Always 201 for paid tier; checkout_url in body is the signal
-  ❌    `stripe:402-redirect` — 402 blocks fetch(), use 201 + JSON body for checkout flow
-  …and 8 more
+<details>
+<summary><b>Claude Code</b> (<code>~/.claude/mcp.json</code> or <code>.mcp.json</code>)</summary>
 
-📚 19 lessons unchanged (stable knowledge base)
+```json
+{
+  "mcpServers": {
+    "cachly": {
+      "type": "stdio",
+      "command": "npx",
+      "args": ["-y", "@cachly-dev/mcp-server@latest"],
+      "env": {
+        "CACHLY_JWT": "your-jwt-token",
+        "CACHLY_INSTANCE_ID": "your-instance-id"
+      }
+    }
+  }
+}
 ```
+</details>
 
-### Autopilot — Zero-Config Forever Memory
+<details>
+<summary><b>Cursor / Windsurf / VS Code</b> (<code>.cursor/mcp.json</code> / <code>.mcp.json</code>)</summary>
 
+```json
+{
+  "servers": {
+    "cachly": {
+      "type": "stdio",
+      "command": "npx",
+      "args": ["-y", "@cachly-dev/mcp-server@latest"],
+      "env": {
+        "CACHLY_JWT": "your-jwt-token",
+        "CACHLY_INSTANCE_ID": "your-instance-id"
+      }
+    }
+  }
+}
 ```
-autopilot(instance_id="...", project_dir="/home/you/myproject", write=true)
-
-🤖 cachly Autopilot — zero-config AI memory for myproject
-
-Brain: 31 lessons stored · Instance: `a1b2c3d4…`
+</details>
 
-✅ Written to:
-   • /home/you/myproject/CLAUDE.md
-   • /home/you/myproject/.github/copilot-instructions.md
+**Step 3 — Add to `CLAUDE.md` / `.github/copilot-instructions.md`:**
 
-🎯 Autopilot is live. This AI — and any other AI on this project —
-   will now manage memory automatically.
+```markdown
+## AI Brain Rules (cachly)
+- Call session_start BEFORE reading any files or making changes
+- Call learn_from_attempts AFTER every fix, deploy, or discovery
+- Call session_end when closing the window
 ```
 
-From that point on: no manual `session_start`, no manual `learn_from_attempts`, no manual `session_end`. The AI does it all, every time, forever.
-
 ---
 
-## Before vs. After
+## With vs. Without cachly
 
 | Situation | Without cachly | With cachly |
 |-----------|----------------|-------------|
-| Session start | "What's your architecture?" | Briefed in 2s — lessons, last session, open failures |
-| Bug hits again | Re-researches from scratch (20–40 min) | "You fixed this on March 12, exact command: `kubectl rollout restart`" |
-| "Why is X broken?" | Manual investigation from scratch | `causal_trace` traces root cause through memory in seconds |
-| "Can I trust this lesson?" | No way to know | `knowledge_decay` shows confidence % per memory |
-| After holiday | Context completely dead | Full context restored, team lessons visible |
-| New team member | Weeks to onboard | `session_start` gives full codebase context instantly |
-| Model switch | Start over with new AI | Brain is model-agnostic — Claude, GPT-4, Gemini, all share one brain |
-| Context limit | Lose everything | `compact_recover` restores checkpoint + lessons in one call |
+| Session start | "What's your architecture?" | "Ready. 23 lessons, last session: deployed API." |
+| Known bug hits again | Re-researches from scratch | "You fixed this on March 12, here's the exact command" |
+| After holiday / team handoff | Context dead | Fully briefed in < 10 seconds |
+| Repeated LLM patterns | Pays for each re-discovery | Cached by meaning, ~1,200 tokens saved per hit |
+| New team member | Weeks to onboard | `session_start` gives full context instantly |
 
 ---
 
-## Bootstrap from Git History
-
-```bash
-npx @cachly-dev/mcp-server@latest learn
-```
+## 51 MCP Tools
 
-**One command. 2 years of team knowledge. 30 seconds.**
+### 🧠 Session & Memory (most used)
 
-`brain_from_git` reads your git log and extracts lessons automatically:
+| Tool | What it does |
+|------|-------------|
+| **`session_start`** | Full briefing: last session summary, open failures, recent lessons, brain health |
+| **`session_end`** | Save what you built, auto-extract lessons from summary + ambient git log |
+| **`session_handoff`** | Hand off remaining tasks to next window, with context |
+| **`auto_learn_session`** | Batch-learn from a list of observations |
+| **`sync_file_changes`** | Sync changed files into brain index |
+| **`learn_from_attempts`** | Store structured lessons after any fix, deploy, or discovery |
+| **`recall_best_solution`** | Best known solution for a topic — with success/failure history |
+| **`recall_at`** | Recall a lesson at a specific point in time |
+| **`remember_context`** | Cache architecture findings, decisions, file summaries |
+| **`recall_context`** | Get exact context by key (supports glob) |
+| **`list_remembered`** | See all cached context entries |
+| **`forget_context`** | Remove stale context |
+| **`smart_recall`** | BM25+ full-text search across all brain data — multilingual: EN, DE, FR, ES, IT, PT, ZH, JA, KO, **AR, HE** |
+| **`setup_ai_memory`** | Interactive wizard to configure AI memory |
+
+### 🌍 Multilingual Brain — Search in Any Language
+
+The Brain's search engine understands **11 languages natively** — no configuration required.
+
+| Script | Languages | Tokenization |
+|--------|-----------|-------------|
+| Latin | EN, DE, FR, ES, IT, PT | Whitespace + stopwords |
+| CJK | Chinese (ZH), Japanese (JA), Korean (KO) | Character bigrams |
+| RTL | Arabic (AR), Hebrew (HE) | Word tokenization + light stemming |
+
+**Romanization matching** — store lessons in Japanese, search in romaji:
+```
+smart_recall("kontena") → finds コンテナ docs
+smart_recall("depuroi") → finds デプロイ docs
+```
 
+**Cross-language retrieval** — 130+ tech term synonyms EN↔JA↔ZH↔KO↔AR↔HE:
 ```
-🧠 Brain bootstrapped from git history
-
-📊 Scanned: 342 commits over last 180 days
-✅ Success lessons: 28  ❌ Failure/revert lessons: 9
-📁 Hotspot files tracked: 12
-💾 Total stored: 31 new lessons
-
-Top lessons extracted:
-  ✅🟡 `auth:jwt-refresh-token` — Use httpOnly cookie, not localStorage — Safari blocks third-party
-  ❌🔴 `deploy:docker-compose-detach` — Reverted: "docker compose up without -d blocks SSH terminal"
-  ✅🟡 `redis:connection-pool-timeout` — connectTimeout:5000 + retryStrategy:null prevents hangs
-  ❌🔴 `auth:pkce-safari-16` — PKCE flow broken Safari 16.3, still unresolved
+smart_recall("deploy")    → finds デプロイ, 部署, 배포, نشر, פריסה
+smart_recall("デプロイ")  → finds "deploy", "deployment"
+smart_recall("خطأ")       → finds "error", エラー, 错误
 ```
 
----
+### 💡 Legendary Brain Features
 
-## Full Tool Reference
+| Feature | How it works |
+|---------|-------------|
+| **Team Telepathy** | Multi-dev Brain: the `author` param on `learn_from_attempts` shares fixes across the whole team. Every `session_start` shows colleagues' lessons. |
+| **Ambient Git Learning** | Pass `workspace_path` to `session_end` — it auto-reads `git log`, stores recent commits as Brain lessons. Zero extra calls. |
+| **Memory Crystals** | `memory_crystalize` distills all lessons into a compact Crystal injected at every `session_start`. AI arrives pre-loaded with team knowledge. |
+| **IQ Boost** | `brain_doctor` reports `iq_boost_pct` — how much smarter your AI gets vs. baseline from cached lessons. |
 
-### Cognitive Cache (v0.6 — new)
+### ⚙️ Instance Management
 
 | Tool | What it does |
 |------|-------------|
-| **`memory_consolidate`** | Distill knowledge base: detect contradictions, merge duplicates, prune stale. Knowledge health score 0–100. |
-| **`brain_diff`** | Git-style diff for AI knowledge — what was learned, updated, or went stale since N sessions |
-| **`causal_trace`** | Root cause analysis: given a problem, traces backwards through memory to find cause + recommended fix |
-| **`knowledge_decay`** | Temporal confidence per memory — decay by age, recover by recall frequency |
-| **`autopilot`** | Generates and optionally writes CLAUDE.md that makes any AI fully self-managing |
+| `list_instances` | List all your cache instances |
+| `create_instance` | Spin up a new instance (free or paid) |
+| `get_connection_string` | Get the `redis://` URL for your app |
+| `delete_instance` | Remove an instance |
+| `get_real_time_stats` | Memory, hit rate, ops/sec |
 
-### Session & Memory
+### 🗄️ Cache Operations
 
 | Tool | What it does |
 |------|-------------|
-| **`session_start`** | Full briefing: last session, open TODOs, checkpoint, lessons, brain stats |
-| **`session_end`** | Save session + auto-refresh CLAUDE.md with top lessons inline |
-| **`session_ping`** | Cross-provider checkpoint — switch Claude↔Copilot↔Cursor seamlessly |
-| **`compact_recover`** | One call after context compaction — restores checkpoint + TODOs + critical lessons |
-| **`brain_from_git`** | Bootstrap brain from git history — no manual lesson writing required |
-| **`learn_from_attempts`** | Store lessons after any fix, deploy, or discovery |
-| **`recall_best_solution`** | Best known fix for a topic — with full success/failure history |
-| **`smart_recall`** | Full-text search across all brain data (BM25+) |
-| **`todo_add`** / **`todo_done`** | Persistent TODOs — survive sessions, compaction, provider switches |
-| **`refresh_claude_md`** | Embed top lessons inline in CLAUDE.md — ambient brain without tool calls |
-| **`remember_context`** / **`recall_context`** | Save/restore architecture findings, file summaries, ADRs |
-| **`auto_learn_session`** | Batch-store multiple observations at session end |
-| **`sync_file_changes`** | Track file change history, surface related lessons per file |
-
-### Team Brain
+| `cache_get` / `cache_set` / `cache_delete` | Standard cache operations |
+| `cache_mget` / `cache_mset` | Bulk pipeline (single round-trip) |
+| `cache_lock_acquire` / `cache_lock_release` | Distributed Redlock-lite |
+| `cache_stream_set` / `cache_stream_get` | LLM token stream caching |
+
+### 🔍 Semantic Cache
 
 | Tool | What it does |
 |------|-------------|
-| **`team_learn`** / **`team_recall`** | Share lessons across the whole team on a shared instance |
-| **`invite_link`** | Generate `npx ... join <token>` — teammate connects in one command |
-| **`global_learn`** / **`global_recall`** | Cross-project global knowledge base |
-| **`publish_lesson`** / **`import_public_brain`** | Share knowledge with the community |
-| **`brain_stats`** | Dashboard: lessons, recalls, time saved, top topics, team authors |
-| **`export_brain`** | Full Markdown export — share, archive, or import |
-| **`brain_doctor`** | Health check: lesson quality, open failures, recommendations |
+| `semantic_search` | Find cached entries by meaning (pgvector HNSW, EU-hosted) |
+| `semantic_warmup` | Pre-warm cache with prompt/response pairs |
+| `detect_namespace` | Auto-classify prompt into code/qa/summary/translation/creative |
 
-### Cache & Infrastructure
+### 👥 Team Brain
 
 | Tool | What it does |
 |------|-------------|
-| `cache_get` / `cache_set` / `cache_delete` | Standard Redis/Valkey operations |
-| `cache_mget` / `cache_mset` | Bulk pipeline (single round-trip) |
-| `cache_stats` | Memory, hit rate, ops/sec, keyspace info |
-| `semantic_search` | Find cached entries by meaning (vector search, EU-hosted) |
-| `cache_warmup` | Pre-warm cache from file or URL list |
-| `cache_lock_acquire` / `cache_lock_release` | Distributed locking |
-| `cache_stream_set` / `cache_stream_get` | Cache streaming LLM responses in chunks |
-| `get_connection_string` | Get the `redis://` URL for your own app |
+| `team_learn` / `team_recall` | Share lessons across the team |
+| `team_synthesize` | Consolidate multiple lessons into one authoritative version |
+| `memory_crystalize` | Distill all lessons into a Crystal snapshot for instant team context |
+| `brain_doctor` | Health check: lesson count, IQ boost %, open failures, quality score |
+| `global_learn` / `global_recall` | Cross-project universal lessons |
+| `publish_lesson` / `import_public_brain` | Share/import community knowledge |
+| `trace_dependency` | Causal chain — find lessons affected by a dependency change |
+| `list_orgs` / `create_org` | Manage team organizations |
+| `invite_member` / `get_org_plan` | Invite a developer to your org by email |
 
 ---
 
@@ -281,82 +302,13 @@ Top lessons extracted:
 
 | Tier | RAM | Price | Best for |
 |------|-----|-------|----------|
-| **Free** | 25 MB | **€0/mo forever** | Side projects & solo devs |
+| **Free** | 25 MB | **€0/mo forever** | Dev & side projects |
 | **Dev** | 200 MB | €19/mo | Individual developers |
-| **Pro** | 900 MB | €49/mo | Teams (shared brain) |
-| **Speed** | 900 MB + Dragonfly + Semantic | €79/mo | AI-heavy workloads |
+| **Pro** | 900 MB | €49/mo | Teams |
+| **Speed** | 900 MB + Dragonfly + Semantic Cache | €79/mo | AI-heavy workloads |
 | **Business** | 7 GB | €199/mo | Scale-ups |
 
-✅ All plans: **German servers · GDPR-compliant · 99.9% SLA · no credit card for Free**
-
----
-
-## Manual Setup
-
-<details>
-<summary>Claude Code (<code>~/.claude/mcp.json</code> or <code>.mcp.json</code>)</summary>
-
-```json
-{
-  "mcpServers": {
-    "cachly": {
-      "type": "stdio",
-      "command": "npx",
-      "args": ["-y", "@cachly-dev/mcp-server@latest"],
-      "env": {
-        "CACHLY_JWT": "your-api-key",
-        "CACHLY_BRAIN_INSTANCE_ID": "your-instance-id"
-      }
-    }
-  }
-}
-```
-</details>
-
-<details>
-<summary>Cursor / Windsurf (<code>.cursor/mcp.json</code> or <code>.mcp.json</code>)</summary>
-
-```json
-{
-  "servers": {
-    "cachly": {
-      "type": "stdio",
-      "command": "npx",
-      "args": ["-y", "@cachly-dev/mcp-server@latest"],
-      "env": {
-        "CACHLY_JWT": "your-api-key",
-        "CACHLY_BRAIN_INSTANCE_ID": "your-instance-id"
-      }
-    }
-  }
-}
-```
-</details>
-
-<details>
-<summary>Autopilot CLAUDE.md (generated by <code>autopilot</code> tool)</summary>
-
-```markdown
-# My Project — cachly AI Brain (Autopilot)
-
-> Brain instance: `your-instance-id` · 31 lessons stored
-
-## Memory Protocol — follow these rules automatically, every session
-
-### SESSION START (before any work)
-mcp__cachly__compact_recover({"instance_id":"..."})
-mcp__cachly__smart_recall({"instance_id":"...","query":"<describe your task>"})
-
-### WHEN SOMETHING WORKS
-mcp__cachly__learn_from_attempts({"instance_id":"...","topic":"<topic>","outcome":"success","what_worked":"<solution>","severity":"major"})
-
-### ROOT CAUSE ANALYSIS
-mcp__cachly__causal_trace({"instance_id":"...","problem":"<symptom>"})
-
-### SESSION END (always)
-mcp__cachly__session_end({"instance_id":"...","summary":"<one sentence>","files_changed":["..."]})
-```
-</details>
+✅ All plans: **German servers · GDPR-compliant · 99.9% SLA · No credit card for Free tier**
 
 ---
 
@@ -364,27 +316,30 @@ mcp__cachly__session_end({"instance_id":"...","summary":"<one sentence>","files_
 
 | Variable | Default | Description |
 |----------|---------|-------------|
-| `CACHLY_JWT` | — | **Required.** API key or JWT from the setup wizard |
-| `CACHLY_BRAIN_INSTANCE_ID` | — | Default instance UUID — set once, works in all tools |
+| `CACHLY_JWT` | — | **Required.** Your API token from [cachly.dev](https://cachly.dev) |
+| `CACHLY_INSTANCE_ID` | — | Default instance UUID (optional if you pass per-call) |
 | `CACHLY_API_URL` | `https://api.cachly.dev` | Override for self-hosted |
-| `CACHLY_EMBED_PROVIDER` | auto-detect | `openai` \| `gemini` \| `mistral` \| `cohere` \| `ollama` \| `cachly` |
-| `CACHLY_NO_TELEMETRY` | unset | Set to `1` to opt out of anonymous usage pings |
+| `CACHLY_NO_TELEMETRY` | unset | Set to `1` to disable anonymous usage pings |
+| `CACHLY_NO_UPDATE_CHECK` | unset | Set to `1` to disable the version-check on startup |
 
 ---
 
-## Ecosystem
+## 🛠️ Ecosystem
 
 | Package | What it does |
 |---------|-------------|
-| **[`@cachly-dev/mcp-server`](https://www.npmjs.com/package/@cachly-dev/mcp-server)** | ← you are here — Cognitive Cache MCP for Claude, Cursor, Copilot, Windsurf |
-| **[`cachly-brain` (VS Code)](https://marketplace.visualstudio.com/items?itemName=cachly.cachly-brain)** | VS Code extension — status bar, CodeLens lessons, one-click setup |
-| **[`@cachly-dev/openclaw`](https://www.npmjs.com/package/@cachly-dev/openclaw)** | JS/TS SDK — cut LLM costs 60–90% with semantic cache in your own app |
-| **[`@cachly-dev/sdk`](https://www.npmjs.com/package/@cachly-dev/sdk)** | Node.js SDK — managed Redis, semantic cache & AI memory in your app |
+| **[`@cachly-dev/mcp-server`](https://www.npmjs.com/package/@cachly-dev/mcp-server)** | ← you are here — AI Brain MCP tools for Claude Code, Cursor, Copilot, Windsurf |
+| **[`@cachly-dev/openclaw`](https://www.npmjs.com/package/@cachly-dev/openclaw)** | JS/TS SDK — cut LLM costs 60–90% with semantic cache + BM25 in your own app, 3 lines of code |
+| **[`@cachly-dev/init`](https://www.npmjs.com/package/@cachly-dev/init)** | One-command setup wizard: auto-detects all your editors and writes the correct MCP config — `npx @cachly-dev/init` |
+| **[`@cachly-dev/cli`](https://www.npmjs.com/package/@cachly-dev/cli)** | Terminal CLI — manage instances, cache data, brain lessons: `npm i -g @cachly-dev/cli` |
+| **[`@cachly-dev/sdk`](https://www.npmjs.com/package/@cachly-dev/sdk)** | Node.js/TypeScript SDK — use managed Redis, semantic cache & AI memory directly in your app |
 
 ---
 
 ## Links
 
 - 🌐 [cachly.dev](https://cachly.dev) — Dashboard & free signup
-- 📖 [Docs](https://cachly.dev/docs/ai-memory) — Full documentation
-- 💬 [Issues](https://github.com/cachly-dev/cachly-mcp/issues) — Bug reports & feature requests
+- 📖 [AI Brain docs](https://cachly.dev/docs/ai-memory) — Full documentation
+- 💬 [GitHub Issues](https://github.com/cachly-dev/mcp-server/issues) — Bug reports & feature requests
+- ⭐ [Star on GitHub](https://github.com/cachly-dev/mcp-server) — If cachly saves you time, a star means a lot!
+- 📦 [npm](https://www.npmjs.com/package/@cachly-dev/mcp-server)

package/dist/__tests__/namespace.test.d.ts

@@ -0,0 +1 @@
+export {};