@nxuss/lemma 0.3.1 → 0.3.3

package/README.md

@@ -1,75 +1,64 @@
-# Lemma v0.3.0
+# Lemma v0.3.2
 > **The Universal AI Cache Proxy + Agent Orchestration Layer.**
 
 Lemma is the open-core gateway for AI development. It sits between your tools (Cursor, VS Code, CLI Agents) and your models (OpenAI, Claude, Gemini, Ollama), providing a **shared semantic memory** that saves you 40-70% in API costs and makes your AI tools instant.
 
-### 🚀 Why Lemma?
+⚡ **Why Lemma?**
 - 💰 **Stop paying twice**: Lemma caches redundant queries semantically. "Fix this bug" and "Solve this error" return the same cached answer.
 - ⚡ **Instant responses**: 3ms cache hits vs 2000ms LLM calls.
 - 🤖 **Universal Gateway**: One endpoint for OpenAI, Anthropic, and Gemini.
 - 🐝 **Agent Swarms**: Orchestrate multiple agents with shared memory.
 
----
-
-## ⚡ Quick Start (IDE Proxy)
+⚡ **Quick Start (IDE Proxy)**
 
 Install and launch the proxy to start saving on your API bills immediately.
 
 ```bash
 npm install -g @nxuss/lemma
-lemma-proxy start
+lemma start
+
+# Or to launch the full development stack (Proxy + Dashboard + Hub + Chroma):
+lemma start --stack
 ```
 
 **Configure your IDE:**
+
 - **Base URL:** `http://localhost:8080/v1`
 - **Gemini Base:** `http://localhost:8080/v1beta`
 
-- 🆓 **Free Tier**: 300 queries/month + Exact Matching.
-- 💎 **Pro**: Unlimited queries + **Semantic Caching** ($12/mo or $120/yr).
-- ☁️ **Cloud**: Managed infrastructure (Coming Soon).
+🆓 **Free Tier:** 300 queries/month + Exact Matching.
+💎 **Pro:** Unlimited queries + Semantic Caching ($12/mo or $120/yr).
+☁️ **Cloud:** Managed infrastructure (Coming Soon).
 
-👉 **[Get Lemma Pro](https://lemma.nxus.studio/upgrade)**
+👉 [Get Lemma Pro](https://lemma.nxus.studio/upgrade)
 
 ### Option 2: Multi-Agent System
-
 For building coordinated AI agent systems:
 
 ```bash
 npm install @nxuss/lemma
 ```
-
-👉 **[Multi-Agent Guide](#quick-start)**
+👉 [Multi-Agent Guide](https://lemma.nxus.studio/docs/multi-agent)
 
 ---
 
 ## The problem with AI development costs
-
 When you use AI assistants for development, you pay for every prompt — even when asking similar questions:
 
-```
-"How to implement JWT in Express?"
-"Explain JWT authentication in Node.js"  ← Same answer, paid twice
-"Show me JWT example for Express"       ← Same answer, paid three times
-```
-
-**Lemma Proxy** intercepts these calls and returns cached responses for similar prompts in 3ms instead of 600ms, saving you money and time.
+1. *"How to implement JWT in Express?"*
+2. *"Explain JWT authentication in Node.js"*  ← **Same answer, paid twice**
+3. *"Show me JWT example for Express"*       ← **Same answer, paid three times**
 
----
+Lemma Proxy intercepts these calls and returns cached responses for similar prompts in **3ms instead of 600ms**, saving you money and time.
 
 ## The problem with multi-agent systems
-
 When you run multiple AI agents in parallel, they don't share context. Agent A solves a problem. Agent B gets the same problem 10 minutes later and solves it again. You pay twice, wait twice, and get the same answer.
 
 At scale this compounds fast:
-
-```
-10 agents × 500 tasks/day × 70% overlap = 3,500 redundant LLM calls/day
-```
+**10 agents × 500 tasks/day × 70% overlap = 3,500 redundant LLM calls/day**
 
 Lemma puts a shared semantic brain between your agents. When any agent solves something, every other agent gets that answer for free — even if they phrase the question differently.
 
----
-
 ## How it works
 
 ```
@@ -82,16 +71,15 @@ Agent C ──┘         │
 1. Agents connect via WebSocket and register their capabilities
 2. Every task request hits the semantic cache first
 3. On a miss, the hub routes to a capable agent and stores the result
-4. On a hit, the response returns in ~20ms — no agent invoked, no LLM called
+4. On a hit, the response returns in **~20ms** — no agent invoked, no LLM called
 
-The cache is semantic, not exact. "fibonacci up to n=10" and "compute fibonacci(10)" resolve to the same cached answer.
+The cache is **semantic**, not exact. *"fibonacci up to n=10"* and *"compute fibonacci(10)"* resolve to the same cached answer.
 
 ---
 
 ## Quick start
 
 ### 1. Install and setup dependencies
-
 ```bash
 npm install @nxuss/lemma
 
@@ -109,7 +97,6 @@ ollama pull nomic-embed-text
 ### 2. Choose your mode
 
 #### Option A: Semantic Mode (Recommended) ⚡
-
 Zero external dependencies, true semantic matching:
 
 ```typescript
@@ -130,7 +117,6 @@ await cachedLLM('San Francisco temperature');  // Cache HIT! ⚡
 ```
 
 #### Option B: Memory Mode (Fastest)
-
 Exact matching, zero dependencies:
 
 ```typescript
@@ -140,9 +126,6 @@ const lemma = await Lemma.create({
 ```
 
 #### Option C: Server Mode (Multi-Agent)
-
-#### Option C: Server Mode (Multi-Agent)
-
 For multi-agent orchestration:
 
 ```typescript
@@ -157,7 +140,6 @@ console.log('WebSocket hub listening on ws://localhost:8080');
 ```
 
 ### 3. Connect agents (Server Mode)
-
 ```typescript
 import WebSocket from 'ws';
 
@@ -217,7 +199,6 @@ ws.on('message', (data) => {
 ```
 
 ### 4. See it in action
-
 When multiple agents request similar tasks, you'll see the cache working:
 
 ```
@@ -225,15 +206,13 @@ When multiple agents request similar tasks, you'll see the cache working:
 [agent-002] ⚡ CACHE HIT - compute the 10th fibonacci... (20ms)
 [agent-003] ⚡ CACHE HIT - fibonacci sequence up to n=10... (22ms)
 ```
-
-**Result:** 100% cache hit rate after first computation. ~20ms responses. Zero duplicate LLM calls.
+**Result: 100% cache hit rate after first computation. ~20ms responses. Zero duplicate LLM calls.**
 
 ---
 
 ## What's inside
 
 ### Embedded Mode — Zero-config semantic cache
-
 The simplest way to add semantic caching to any project:
 
 ```typescript
@@ -256,11 +235,11 @@ console.log(result.fromCache); // true on cache hit
 ```
 
 **Features:**
-- **Semantic matching** with lightweight embeddings (transformers.js)
-- **Automatic TTL cleanup** prevents memory leaks
-- **Circuit breaker** with automatic fallbacks (Cloud → Chroma → Memory)
-- **Health monitoring** with detailed metrics
-- **Graceful shutdown** with `lemma.stop()`
+- Semantic matching with lightweight embeddings (transformers.js)
+- Automatic TTL cleanup prevents memory leaks
+- Circuit breaker with automatic fallbacks (Cloud → Chroma → Memory)
+- Health monitoring with detailed metrics
+- Graceful shutdown with `lemma.stop()`
 
 **Storage options:**
 - `memory`: Exact match, zero dependencies, fastest
@@ -269,7 +248,6 @@ console.log(result.fromCache); // true on cache hit
 - `cloud`: Managed cache (requires API key)
 
 ### SubconsciousHub — the orchestration layer
-
 The core of Lemma. A WebSocket server that manages agent connections, routes tasks by capability, and maintains the shared semantic cache.
 
 ```typescript
@@ -281,26 +259,22 @@ await hub.start();
 
 **What it handles:**
 - Agent registration and capability discovery
-- Semantic cache lookup before every task (ChromaDB + `nomic-embed-text` embeddings)
+- Semantic cache lookup before every task (ChromaDB + nomic-embed-text embeddings)
 - Task routing to capable agents on cache miss
 - Response storage for future cache hits
 - WebSocket heartbeat and connection lifecycle
 - Rate limiting and message sanitization
 
 ### Semantic cache — the shared memory
-
 Built on ChromaDB with Ollama embeddings. Catches paraphrases, not just exact matches.
 
-```
-"fibonacci up to n=10"          ──► cache hit (similarity: 0.97)
-"compute the 10th fibonacci"    ──► cache hit (similarity: 0.91)
-"fib sequence, first 10 terms"  ──► cache hit (similarity: 0.88)
-```
+- *"fibonacci up to n=10"*          ──► **cache hit** (similarity: 0.97)
+- *"compute the 10th fibonacci"*    ──► **cache hit** (similarity: 0.91)
+- *"fib sequence, first 10 terms"*  ──► **cache hit** (similarity: 0.88)
 
 Threshold is configurable (`SEMANTIC_THRESHOLD=0.85` by default).
 
 ### Consensus engine — multi-model voting
-
 For high-stakes decisions, route a query through multiple models and only return when they agree.
 
 ```typescript
@@ -318,7 +292,6 @@ const result = await consensus.requestConsensus({
 });
 // Returns only when 3 models agree ≥90%
 ```
-
 Supports Ollama (local), OpenAI, Anthropic, and Google models simultaneously.
 
 ---
@@ -326,9 +299,7 @@ Supports Ollama (local), OpenAI, Anthropic, and Google models simultaneously.
 ## New in v0.2.0 🎉
 
 ### 1. Semantic Memory Backend
-
 True semantic caching without external dependencies:
-
 ```typescript
 const lemma = await Lemma.create({
   storage: 'semantic',
@@ -342,120 +313,42 @@ await lemma.run('SF temperature forecast', fetchWeather); // HIT!
 ```
 
 ### 2. Automatic TTL Cleanup
-
 No more memory leaks from expired entries:
-
 ```typescript
 const lemma = await Lemma.create({
   ttl: 3600000,          // 1 hour expiry
   cleanupInterval: 60000, // Check every minute
 });
-
-// Expired entries are automatically removed
-// No manual cleanup needed!
 ```
 
 ### 3. Circuit Breaker & Fallbacks
-
 Automatic resilience when backends fail:
-
 ```typescript
 const lemma = await Lemma.create({
   storage: 'cloud',
-  enableFallback: true,  // Auto-fallback on failure
+  enableFallback: true,
   maxRetries: 3,
   retryDelay: 1000,
 });
-
-// If cloud fails → falls back to chroma
-// If chroma fails → falls back to memory
-// Automatic recovery when backend comes back
-
-lemma.on('backend-degraded', ({ from, to }) => {
-  console.log(`Degraded: ${from} → ${to}`);
-});
-
-lemma.on('backend-recovered', ({ backend }) => {
-  console.log(`Recovered: ${backend}`);
-});
 ```
 
 ### 4. Enhanced Metrics & Health Monitoring
-
 ```typescript
 const metrics = lemma.getMetrics();
-console.log(metrics);
-// {
-//   hits: 150,
-//   misses: 50,
-//   hitRate: 0.75,
-//   backendHealth: 'healthy',
-//   failureCount: 0,
-//   evictedCount: 23,
-//   lastCleanupAt: 1234567890
-// }
-
-const health = lemma.getBackendHealth();
-console.log(health);
-// {
-//   state: 'CLOSED',
-//   currentBackend: 'semantic',
-//   failureCount: 0,
-//   totalFailures: 0
-// }
+// { hits: 150, misses: 50, hitRate: 0.75, ... }
 ```
 
 ### 5. Dual Module Support (ESM + CJS)
-
-```typescript
-// ESM
-import { Lemma } from '@nxuss/lemma/embed';
-import { ConsensusEngine } from '@nxuss/lemma/consensus';
-import { SpeculativeEngine } from '@nxuss/lemma/speculative';
-
-// CJS
-const { Lemma } = require('@nxuss/lemma/embed');
-const { ConsensusEngine } = require('@nxuss/lemma/consensus');
-```
-
-**New exports:**
-- `@nxuss/lemma/consensus` - Multi-model consensus
-- `@nxuss/lemma/speculative` - Speculative execution
-- `@nxuss/lemma/security` - Security utilities
-- `@nxuss/lemma/protocol` - IAP protocol
-- `@nxuss/lemma/langchain` - LangChain SDK
-- `@nxuss/lemma/crewai` - CrewAI SDK
-
-See [MIGRATION_GUIDE.md](docs/MIGRATION_GUIDE.md) for upgrade instructions.
+Full support for both modern and legacy Node.js projects.
 
 ---
 
 ## Install
-
 ```bash
 npm install @nxuss/lemma
 ```
 
-**Optional dependencies (install as needed):**
-
-```bash
-# For semantic mode (lightweight embeddings)
-npm install @xenova/transformers
-
-# For persistent storage with ChromaDB
-pip install chromadb
-chroma run --path ./chroma_data --port 8000
-
-# For ChromaDB embeddings
-ollama pull nomic-embed-text
-```
-
-**Zero dependencies required** for basic memory mode!
-
----
-
 ## Configuration
-
 ```bash
 # .env
 WS_PORT=8080
@@ -463,60 +356,11 @@ CHROMA_HOST=http://localhost
 CHROMA_PORT=8000
 OLLAMA_HOST=http://localhost:11434
 OLLAMA_MODEL=nomic-embed-text
-SEMANTIC_THRESHOLD=0.85   # similarity cutoff (0–1)
-ENABLE_CACHING=true
-AUTH_ENABLED=false        # set true in production
+SEMANTIC_THRESHOLD=0.85
 ```
 
----
-
-## Examples & Documentation
-
-For complete examples including:
-- Single agent setup
-- Multi-agent swarms
-- Consensus voting
-- Security & authentication
-- LangChain/CrewAI integration
-
-Visit [lemma.nxus.studio/docs](https://lemma.nxus.studio/docs)
-
----
-
-## Who this is for
-
-- Teams running **LangChain, CrewAI, or custom agent frameworks** who need shared memory across agents
-- Systems where **multiple agents handle overlapping queries** — support bots, research pipelines, code assistants
-- Anyone whose **LLM bill scales with agent count** rather than unique queries
-
-Lemma is designed for multi-agent systems where coordination and shared memory provide immediate value.
-
----
-
-## Production deployment
-
-Lemma can be deployed to any Node.js hosting environment. For production setup guides including:
-- Docker deployment
-- API key management
-- Security configuration
-- Monitoring & observability
-
-Visit [lemma.nxus.studio/docs/deployment](https://lemma.nxus.studio/docs/deployment)
-
----
-
-## Cloud hosting (coming soon)
-
-Managed Lemma instances with zero infrastructure setup. Check pricing and availability at [lemma.nxus.studio](https://lemma.nxus.studio)
-
----
-
 ## Contributing
-
-Contributions are welcome! For development setup and guidelines, visit [lemma.nxus.studio](https://lemma.nxus.studio)
-
----
+Contributions are welcome! Visit [lemma.nxus.studio](https://lemma.nxus.studio)
 
 ## License
-
-MIT © [Nxus Studio](https://nxus.studio)
+MIT © Nxus Studio

package/lemma-proxy.cjs

@@ -1,7 +1,7 @@
 #!/usr/bin/env node
 'use strict';
 /**
- * Lemma Proxy v0.3.1 — Universal AI Cache CLI
+ * Lemma Proxy v0.3.2 — Universal AI Cache CLI
  * Commands: start, stop, stats, status, activate <key>
  */
 
@@ -79,7 +79,7 @@ async function validateKeyRemote(key) {
     const body = JSON.stringify({ key });
     const u = new URL(VALIDATE_URL);
     const req = https.request({ hostname: u.hostname, port: 443, path: u.pathname, method: 'POST',
-      headers: { 'Content-Type': 'application/json', 'Content-Length': Buffer.byteLength(body), 'User-Agent': 'lemma-proxy/0.3.1' }
+      headers: { 'Content-Type': 'application/json', 'Content-Length': Buffer.byteLength(body), 'User-Agent': 'lemma-proxy/0.3.2' }
     }, res => {
       let d = '';
       res.on('data', c => d += c);
@@ -413,14 +413,14 @@ class LemmaServer {
     server.listen(this.port, () => {
       fs.writeFileSync(PID_FILE, String(process.pid));
       fs.writeFileSync(PORT_FILE, String(this.port));
-      console.log(`\n🚀 Lemma Proxy v0.3.1\n📁 Project : ${this.projectName}\n🔌 Port    : ${this.port}\n`);
+      console.log(`\n🚀 Lemma Proxy v0.3.2\n📁 Project : ${this.projectName}\n🔌 Port    : ${this.port}\n`);
     });
     process.on('SIGTERM', () => server.close());
   }
 }
 
 // ── CLI ────────────────────────────────────────────────────────────────────────
-program.name('lemma').description('Lemma Proxy CLI').version('0.3.1');
+program.name('lemma').description('Lemma Proxy CLI').version('0.3.2');
 
 program.command('start')
   .description('Start the proxy server')

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@nxuss/lemma",
-  "version": "0.3.1",
+  "version": "0.3.3",
   "description": "Semantic cache for AI apps — stop paying for the same LLM call twice",
   "main": "./dist/cjs/index.js",
   "module": "./dist/esm/index.js",
@@ -68,6 +68,14 @@
         "types": "./dist/cjs/protocol/index.d.ts",
         "default": "./dist/cjs/protocol/index.js"
       }
+    },
+    "./langchain": {
+      "types": "./sdks/langchain/dist/index.d.ts",
+      "default": "./sdks/langchain/dist/index.js"
+    },
+    "./crewai": {
+      "types": "./sdks/crewai/dist/index.d.ts",
+      "default": "./sdks/crewai/dist/index.js"
     }
   },
   "files": [