audrey 0.16.1 → 0.20.0

package/examples/healthcare-ops-demo.js

@@ -0,0 +1,67 @@
+import { Audrey } from '../dist/src/index.js';
+
+async function demo() {
+  console.log('=== Audrey Demo: Healthcare Operations ===\n');
+
+  const brain = new Audrey({
+    dataDir: './healthcare-demo-data',
+    agent: 'care-ops-agent',
+    embedding: { provider: 'mock', dimensions: 64 },
+  });
+
+  console.log('--- Encoding care-coordination observations ---');
+  await brain.encode({
+    content: 'Referral queue delays drop when missing imaging notes are requested before prior-authorization submission.',
+    source: 'direct-observation',
+    salience: 0.9,
+    tags: ['healthcare-ops', 'prior-auth', 'referrals'],
+    context: { domain: 'healthcare', workflow: 'prior-auth' },
+  });
+
+  await brain.encode({
+    content: 'Scheduling team reports the highest callback completion rate between 4pm and 6pm for discharge follow-up.',
+    source: 'tool-result',
+    salience: 0.8,
+    tags: ['healthcare-ops', 'follow-up', 'scheduling'],
+    context: { domain: 'healthcare', workflow: 'discharge-followup' },
+  });
+
+  await brain.encode({
+    content: 'Care coordinators want interpreter requirements captured in every handoff note before outreach starts.',
+    source: 'told-by-user',
+    salience: 0.7,
+    tags: ['healthcare-ops', 'handoff', 'interpreter'],
+    context: { domain: 'healthcare', workflow: 'care-coordination' },
+  });
+
+  console.log('\n--- Consolidating into a reusable workflow ---');
+  await brain.consolidate({
+    minClusterSize: 3,
+    similarityThreshold: -0.3,
+    extractPrinciple: () => ({
+      content: 'For care-coordination workflows, collect missing documentation and communication preferences before outreach or prior-auth submission.',
+      type: 'procedural',
+      conditions: ['prior-auth missing documentation', 'handoff note lacks outreach constraints'],
+    }),
+  });
+
+  console.log('\n--- Recalling during a care-coordination handoff ---');
+  const recalled = await brain.recall('care coordination handoff missing documentation', {
+    limit: 5,
+    context: { domain: 'healthcare', workflow: 'care-coordination' },
+  });
+
+  for (const memory of recalled) {
+    console.log(`[${memory.type}] ${memory.content}`);
+  }
+
+  brain.close();
+
+  const { rmSync } = await import('node:fs');
+  rmSync('./healthcare-demo-data', { recursive: true, force: true });
+}
+
+demo().catch(err => {
+  console.error(err);
+  process.exit(1);
+});

package/examples/stripe-demo.js

@@ -0,0 +1,105 @@
+// examples/stripe-demo.js
+// Proof-of-concept demo showing the full Audrey pipeline:
+//   encode episodic memories → consolidate into principles → recall proactively
+//
+// Run: node examples/stripe-demo.js
+// No external dependencies required (uses mock embeddings).
+
+import { Audrey } from '../dist/src/index.js';
+
+async function demo() {
+  console.log('=== Audrey Demo: Stripe Rate Limit Learning ===\n');
+
+  const brain = new Audrey({
+    dataDir: './demo-data',
+    agent: 'stripe-agent',
+    embedding: { provider: 'mock', dimensions: 64 },
+  });
+
+  brain.on('encode', ({ id, content }) => {
+    console.log(`  [ENCODE] ${id.slice(0, 8)}... "${content.slice(0, 60)}"`);
+  });
+
+  brain.on('consolidation', ({ principlesExtracted, clustersFound }) => {
+    console.log(`  [CONSOLIDATE] Found ${clustersFound} clusters, extracted ${principlesExtracted} principles`);
+  });
+
+  brain.on('reinforcement', ({ episodeId, similarity }) => {
+    console.log(`  [REINFORCE] Episode ${episodeId.slice(0, 8)}... reinforced existing knowledge (sim: ${similarity?.toFixed(2) || 'N/A'})`);
+  });
+
+  // --- Scenario: Agent encounters Stripe rate limits ---
+
+  console.log('--- Episode 1: First rate limit hit ---');
+  await brain.encode({
+    content: 'Stripe API returned HTTP 429 when batch-processing 150 payments per second',
+    source: 'direct-observation',
+    salience: 0.9,
+    causal: { trigger: 'batch-payment-job', consequence: 'payment-queue-stalled' },
+    tags: ['stripe', 'rate-limit', 'production'],
+  });
+
+  console.log('\n--- Episode 2: Second hit from different code path ---');
+  await brain.encode({
+    content: 'Stripe webhook verification endpoint returned 429 Too Many Requests during high traffic',
+    source: 'tool-result',
+    salience: 0.7,
+    causal: { trigger: 'webhook-flood', consequence: 'missed-webhook-events' },
+    tags: ['stripe', 'rate-limit', 'webhooks'],
+  });
+
+  console.log('\n--- Episode 3: Third observation from monitoring ---');
+  await brain.encode({
+    content: 'Stripe API rate limit triggered at approximately 100 requests per second threshold',
+    source: 'direct-observation',
+    salience: 0.8,
+    tags: ['stripe', 'rate-limit', 'monitoring'],
+  });
+
+  // --- Consolidation ---
+  console.log('\n--- Running consolidation ("sleep" cycle) ---');
+  await brain.consolidate({
+    minClusterSize: 3,
+    // Mock embeddings are hash-based (not semantic), so cosine similarity
+    // between related texts is near-random. In production with real embeddings
+    // (e.g. OpenAI text-embedding-3-small), a threshold of 0.80+ works well.
+    // We drop it here so the demo pipeline runs end-to-end.
+    similarityThreshold: -0.3,
+    extractPrinciple: (episodes) => ({
+      content: `Stripe enforces ~100 req/s rate limit across all endpoints. Exceeding this causes 429 errors that can stall payment queues and cause missed webhooks. Implement request throttling.`,
+      type: 'semantic',
+    }),
+  });
+
+  // --- Proactive recall ---
+  console.log('\n--- Agent encounters Stripe again, recalls proactively ---');
+  const memories = await brain.recall('stripe api request rate', {
+    minConfidence: 0.3,
+    limit: 5,
+  });
+
+  console.log(`\nRecalled ${memories.length} memories:`);
+  for (const mem of memories) {
+    console.log(`  [${mem.type.toUpperCase()}] (conf: ${mem.confidence.toFixed(2)}, score: ${mem.score.toFixed(3)}) ${mem.content.slice(0, 80)}${mem.content.length > 80 ? '...' : ''}`);
+  }
+
+  // --- Introspection ---
+  console.log('\n--- Brain stats ---');
+  const stats = brain.introspect();
+  console.log(`  Episodic memories:     ${stats.episodic}`);
+  console.log(`  Semantic principles:   ${stats.semantic}`);
+  console.log(`  Procedural workflows:  ${stats.procedural}`);
+  console.log(`  Causal links:          ${stats.causalLinks}`);
+  console.log(`  Consolidation runs:    ${stats.totalConsolidationRuns}`);
+  console.log(`  Dormant memories:      ${stats.dormant}`);
+
+  brain.close();
+
+  // Cleanup demo data
+  const { rmSync } = await import('node:fs');
+  rmSync('./demo-data', { recursive: true, force: true });
+
+  console.log('\n=== Demo complete ===');
+}
+
+demo().catch(console.error);

package/package.json

@@ -1,26 +1,57 @@
 {
   "name": "audrey",
-  "version": "0.16.1",
-  "description": "Biological memory architecture for AI agents — encode, consolidate, and recall memories with confidence decay, contradiction detection, and causal graphs",
+  "version": "0.20.0",
+  "description": "Biological memory architecture for AI agents - encode, consolidate, and recall memories with confidence decay, contradiction detection, and causal graphs",
   "type": "module",
-  "main": "src/index.js",
+  "main": "dist/src/index.js",
+  "types": "dist/src/index.d.ts",
   "exports": {
-    ".": "./src/index.js",
-    "./mcp": "./mcp-server/index.js"
+    ".": {
+      "types": "./dist/src/index.d.ts",
+      "default": "./dist/src/index.js"
+    },
+    "./mcp": {
+      "types": "./dist/mcp-server/index.d.ts",
+      "default": "./dist/mcp-server/index.js"
+    },
+    "./server": {
+      "types": "./dist/src/server.d.ts",
+      "default": "./dist/src/server.js"
+    }
   },
   "bin": {
-    "audrey": "mcp-server/index.js",
-    "audrey-mcp": "mcp-server/index.js"
+    "audrey": "dist/mcp-server/index.js",
+    "audrey-mcp": "dist/mcp-server/index.js"
   },
   "files": [
-    "src/",
-    "mcp-server/",
+    "dist/",
+    "docs/production-readiness.md",
+    "docs/benchmarking.md",
+    "docs/assets/benchmarks/",
+    "examples/",
     "README.md",
     "LICENSE"
   ],
   "scripts": {
+    "build": "tsc",
+    "prebuild": "node -e \"require('fs').rmSync('dist',{recursive:true,force:true})\"",
+    "pretest": "npm run build",
     "test": "vitest run",
-    "test:watch": "vitest"
+    "test:watch": "vitest",
+    "prepack": "npm run build",
+    "pack:check": "npm pack --dry-run",
+    "bench:memory": "node benchmarks/run.js",
+    "bench:memory:retrieval": "node benchmarks/run.js --suite retrieval",
+    "bench:memory:operations": "node benchmarks/run.js --suite operations",
+    "bench:memory:json": "node benchmarks/run.js --json",
+    "bench:memory:check": "node benchmarks/run.js --check",
+    "bench:memory:readme-assets": "node benchmarks/run.js --readme-assets-dir docs/assets/benchmarks",
+    "typecheck": "tsc --noEmit",
+    "serve": "node dist/mcp-server/index.js serve",
+    "docker:build": "docker build -t audrey:local .",
+    "docker:up": "docker compose up -d --build",
+    "docker:down": "docker compose down",
+    "docker:logs": "docker compose logs -f audrey"
   },
   "keywords": [
     "ai",
@@ -47,7 +78,11 @@
     "persistent-memory",
     "rag",
     "claude",
-    "agent-framework"
+    "agent-framework",
+    "rest-api",
+    "http-server",
+    "fintech",
+    "healthcare"
   ],
   "repository": {
     "type": "git",
@@ -57,20 +92,25 @@
   "bugs": {
     "url": "https://github.com/Evilander/Audrey/issues"
   },
-  "author": "Tyler Eveland <j.tyler.eveland@gmail.com>",
+  "author": "evilander",
   "engines": {
-    "node": ">=18"
+    "node": ">=20"
   },
   "license": "MIT",
   "dependencies": {
+    "@hono/node-server": "^1.19.13",
     "@huggingface/transformers": "^3.8.1",
     "@modelcontextprotocol/sdk": "^1.26.0",
     "better-sqlite3": "^12.6.2",
+    "hono": "^4.12.12",
     "sqlite-vec": "^0.1.7-alpha.2",
     "ulid": "^3.0.2",
     "zod": "^4.3.6"
   },
   "devDependencies": {
+    "@types/better-sqlite3": "^7.6.13",
+    "@types/node": "^25.6.0",
+    "typescript": "^6.0.2",
     "vitest": "^4.0.18"
   }
 }

package/mcp-server/config.js

@@ -1,80 +0,0 @@
-import { homedir } from 'node:os';
-import { join } from 'node:path';
-
-export const VERSION = '0.16.1';
-export const SERVER_NAME = 'audrey-memory';
-export const DEFAULT_DATA_DIR = join(homedir(), '.audrey', 'data');
-
-/**
- * Resolves which embedding provider to use.
- * Priority: explicit config -> gemini (if GOOGLE_API_KEY exists) -> local
- * OpenAI is NEVER auto-selected -- must be set explicitly via AUDREY_EMBEDDING_PROVIDER=openai.
- */
-export function resolveEmbeddingProvider(env, explicit) {
-  if (explicit && explicit !== 'auto') {
-    const dims = explicit === 'openai' ? 1536 : explicit === 'gemini' ? 3072 : 384;
-    const apiKey = explicit === 'gemini'
-      ? (env.GOOGLE_API_KEY || env.GEMINI_API_KEY)
-      : explicit === 'openai'
-        ? env.OPENAI_API_KEY
-        : undefined;
-    const result = { provider: explicit, apiKey, dimensions: dims };
-    if (explicit === 'local') result.device = env.AUDREY_DEVICE || 'gpu';
-    return result;
-  }
-  if (env.GOOGLE_API_KEY || env.GEMINI_API_KEY) {
-    return { provider: 'gemini', apiKey: env.GOOGLE_API_KEY || env.GEMINI_API_KEY, dimensions: 3072 };
-  }
-  return { provider: 'local', dimensions: 384, device: env.AUDREY_DEVICE || 'gpu' };
-}
-
-export function buildAudreyConfig() {
-  const dataDir = process.env.AUDREY_DATA_DIR || DEFAULT_DATA_DIR;
-  const agent = process.env.AUDREY_AGENT || 'claude-code';
-  const explicitProvider = process.env.AUDREY_EMBEDDING_PROVIDER;
-  const llmProvider = process.env.AUDREY_LLM_PROVIDER;
-
-  const embedding = resolveEmbeddingProvider(process.env, explicitProvider);
-
-  const config = { dataDir, agent, embedding };
-
-  if (llmProvider === 'anthropic') {
-    config.llm = { provider: 'anthropic', apiKey: process.env.ANTHROPIC_API_KEY };
-  } else if (llmProvider === 'openai') {
-    config.llm = { provider: 'openai', apiKey: process.env.OPENAI_API_KEY };
-  } else if (llmProvider === 'mock') {
-    config.llm = { provider: 'mock' };
-  }
-
-  return config;
-}
-
-export function buildInstallArgs(env = process.env) {
-  const envPairs = [`AUDREY_DATA_DIR=${DEFAULT_DATA_DIR}`];
-
-  const embedding = resolveEmbeddingProvider(env);
-  if (embedding.provider === 'gemini') {
-    envPairs.push('AUDREY_EMBEDDING_PROVIDER=gemini');
-    envPairs.push(`GOOGLE_API_KEY=${embedding.apiKey}`);
-  } else if (embedding.provider === 'openai') {
-    envPairs.push('AUDREY_EMBEDDING_PROVIDER=openai');
-    envPairs.push(`OPENAI_API_KEY=${env.OPENAI_API_KEY}`);
-  }
-
-  if (env.ANTHROPIC_API_KEY) {
-    envPairs.push('AUDREY_LLM_PROVIDER=anthropic');
-    envPairs.push(`ANTHROPIC_API_KEY=${env.ANTHROPIC_API_KEY}`);
-  }
-
-  const args = ['mcp', 'add', '-s', 'user', SERVER_NAME];
-  for (const pair of envPairs) {
-    args.push('-e', pair);
-  }
-  if (process.platform === 'win32') {
-    args.push('--', 'cmd', '/c', 'npx', 'audrey');
-  } else {
-    args.push('--', 'npx', 'audrey');
-  }
-
-  return args;
-}