@everworker/oneringai

A unified AI agent library with multi-provider support for text generation, image/video generation, audio (TTS/STT), and agentic workflows.

Table of Contents

• Features
• Quick Start — Installation, basic usage, tools, vision, audio, images, video, search, scraping
• Supported Providers
• Key Features
  • 1. Agent with Plugins
  • 2. Dynamic Tool Management
  • 3. Tool Execution Plugins
  • 4. Session Persistence
  • Storage Registry
  • 5. Working Memory
  • 6. Research with Search Tools
  • 7. Context Management
  • 8. InContextMemory
  • 9. Persistent Instructions
  • 10. User Info
  • 10b. Self-Learning Memory — plugin + tools — MemoryPluginNextGen + MemoryWritePluginNextGen with 12 memory_* LLM tools (6 read incl. memory_search_documents + 6 write incl. memory_set_agent_rule); supersedes 9 & 10
  • 11. Direct LLM Access
  • 12. Audio Capabilities
  • Embeddings — Multi-vendor text embeddings with MRL dimension control
  • 13. Model Registry
  • 14. Streaming
  • 15. OAuth for External APIs
  • 16. Developer Tools
  • 17. Custom Tool Generation — Agents create, test, and persist their own tools
  • 18. Document Reader — PDF, DOCX, XLSX, PPTX, CSV, HTML, images
  • 19. Desktop Automation Tools — Screenshot, mouse, keyboard, window control for computer use agents
  • 20. Routine Execution — Multi-step workflows with task dependencies, validation, and memory bridging
  • 21. External API Integration — Scoped Registry, Vendor Templates, Tool Discovery
  • 22. Microsoft Graph Connector Tools — Email, calendar, meetings, and Teams transcripts
  • 23. Tool Catalog — Dynamic tool loading/unloading for agents with 100+ tools
  • 24. Async (Non-Blocking) Tools — Background tool execution with auto-continuation
  • 25. Long-Running Sessions (Suspend/Resume) — Suspend agent loops waiting for external input, resume days later
  • 26. Agent Registry — Global tracking, deep inspection, parent/child hierarchy, event fan-in, external control
  • 27. Agent Orchestrator — Multi-agent teams with shared workspace, delegation, and async execution
  • 28. Telegram Connector Tools — Bot API tools for messaging, updates, and webhooks
  • 29. Twilio Connector Tools — SMS and WhatsApp messaging tools
  • 30. Google Workspace Connector Tools — Gmail, Calendar, Meet, and Drive tools
  • 31. Zoom Connector Tools — Meeting management and transcripts
  • 32. Unified Calendar — Cross-provider meeting slot finder (Google + Microsoft)
  • 33. Multi-Account Connectors — Multiple accounts per vendor with automatic routing
  • 34. Integration Testing — Reusable test suites for connector tools
  • 36. Instruction Templates — {{DATE}}, {{AGENT_ID}}, custom {{COMMAND:arg}} with extensible registry
• MCP Integration
• Documentation
• Examples
• Development
• Architecture
• Troubleshooting
• Contributing
• License

Documentation

Start here if you're looking for detailed docs or the full API reference.

| Document | Description | |----------|-------------| | User Guide | Comprehensive guide covering every feature with examples — connectors, agents, context, plugins, audio, video, search, MCP, OAuth, and more | | API Reference | Auto-generated reference for all public exports — classes, interfaces, types, and functions with signatures | | CHANGELOG | Version history and migration notes |

Tutorial / Architecture Series

Part 0. One Lib to Rule Them All: Why We Built OneRingAI: introduction and architecture overview

Part 1. Your AI Agent Forgets Everything. Here’s How We Fixed It.: context management plugins

EVERWORKER DESKTOP APP

We realize that library alone in these times is not enough to get you excited, so we built a FREE FOREVER desktop app on top of this library to showcase its power! Check the Everworker Desktop repository for installation instructions. Or watch the video first:

Better to see once and then dig in the code! :)

YOUetal

Showcasing another amazing "built with oneringai": "no saas" agentic business team

Features

• ✨ Unified API - One interface for 12 AI providers (OpenAI, Anthropic, Google, Vertex, Groq, Together, Perplexity, Grok, DeepSeek, Mistral, Ollama, Custom)
• 🔑 Connector-First Architecture - Single auth system with support for multiple keys per vendor
• 📊 Model Registry - Complete metadata for 60+ latest (2026) models with pricing and features
• 🎤 Audio Capabilities - Text-to-Speech (TTS) and Speech-to-Text (STT) with OpenAI and Groq
• 🖼️ Image Generation - DALL-E 3, gpt-image-1, Google Imagen 4 with editing and variations
• 🎬 Video Generation - NEW: OpenAI Sora 2 and Google Veo 3 for AI video creation
• 🔢 Embeddings - NEW: Multi-vendor embedding generation with MRL dimension control (OpenAI, Google, Ollama, Mistral)
• 🔍 Web Search - Connector-based search with Serper, Brave, Tavily, and RapidAPI providers
• 🔌 NextGen Context - Clean, plugin-based context management with AgentContextNextGen
• 🎛️ Dynamic Tool Management - Enable/disable tools at runtime, namespaces, priority-based selection
• 🔌 Tool Execution Plugins - NEW: Pluggable pipeline for logging, analytics, UI updates, custom behavior
• 💾 Session Persistence - Save and resume conversations with full state restoration
• ⏸️ Long-Running Sessions - NEW: Suspend agent loops via SuspendSignal, resume hours/days later with Agent.hydrate()
• 👤 Multi-User Support - Set userId once, flows automatically to all tool executions and session metadata
• 🔒 Auth Identities - Restrict agents to specific connectors (and accounts), composable with access policies
• 🤖 Universal Agent - ⚠️ Deprecated - Use Agent with plugins instead
• 🤖 Task Agents - ⚠️ Deprecated - Use Agent with WorkingMemoryPluginNextGen
• 🔬 Research Agent - ⚠️ Deprecated - Use Agent with search tools
• 🎯 Context Management - Algorithmic compaction with tool-result-to-memory offloading
• 📌 InContextMemory - Live key-value storage directly in LLM context with optional UI display (showInUI)
• 📝 Persistent Instructions - ⚠️ Deprecated in favour of MemoryPluginNextGen (self-learning memory). Still works unchanged.
• 👤 User Info Plugin - ⚠️ Deprecated in favour of MemoryPluginNextGen. Still works unchanged.
• 🧠 Self-Learning Memory - NEW: MemoryPluginNextGen + MemoryWritePluginNextGen + 11 memory_* tools — brain-like entity/fact store with three-principal permissions, semantic search, graph queries, LLM-synthesised profiles that evolve from observations, user-driven behavior rules, optional background ingestion via SessionIngestorPluginNextGen
• 🛠️ Agentic Workflows - Built-in tool calling and multi-turn conversations
• 🔧 Developer Tools - NEW: Filesystem and shell tools for coding assistants (read, write, edit, grep, glob, bash)
• 🧰 Custom Tool Generation - NEW: Let agents create, test, and persist their own reusable tools at runtime — complete meta-tool system with VM sandbox
• 🖥️ Desktop Automation - NEW: OS-level computer use — screenshot, mouse, keyboard, and window control for vision-driven agent loops
• 📄 Document Reader - NEW: Universal file-to-text converter — PDF, DOCX, XLSX, PPTX, CSV, HTML, images auto-converted to markdown
• 🔌 MCP Integration - NEW: Model Context Protocol client for seamless tool discovery from local and remote servers
• 👁️ Vision Support - Analyze images with AI across all providers
• 📋 Clipboard Integration - Paste screenshots directly (like Claude Code!)
• 🔐 Scoped Connector Registry - NEW: Pluggable access control for multi-tenant connector isolation
• 💾 StorageRegistry - Centralized storage configuration — swap all backends (sessions, media, custom tools, etc.) with one configure() call
• 🔐 OAuth 2.0 - Full OAuth support for external APIs with encrypted token storage
• 📦 Vendor Templates - NEW: Pre-configured auth templates for 43+ services (GitHub, Slack, Stripe, etc.)
• 📧 Microsoft Graph Tools - NEW: Email, calendar, meetings, and Teams transcripts via Microsoft Graph API
• 🔁 Routine Execution - NEW: Multi-step workflows with task dependencies, LLM validation, retry logic, and memory bridging between tasks
• 📊 Execution Recording - NEW: Persist full routine execution history with createExecutionRecorder() — replaces manual hook wiring
• ⏰ Scheduling & Triggers - NEW: SimpleScheduler for interval/one-time schedules, EventEmitterTrigger for webhook/queue-driven execution
• 📦 Tool Catalog - NEW: Dynamic tool loading/unloading — agents discover and load only the categories they need at runtime
• Async Tools - NEW: Non-blocking tool execution — long-running tools run in background while the agent continues reasoning, with auto-continuation when results arrive
• 📡 Agent Registry - NEW: Global tracking of all active agents — deep inspection, parent/child hierarchy, event fan-in, external control
• 📱 Telegram Tools - NEW: 6 Telegram Bot API tools — send messages/photos, get updates, webhooks, chat info
• 📞 Twilio Tools - NEW: 4 Twilio tools — SMS, WhatsApp messaging, message listing and details
• 📧 Google Workspace Tools - NEW: 11 tools for Gmail, Calendar, Meet transcripts, and Drive (read, search, list files)
• 🎥 Zoom Tools - NEW: 3 Zoom tools — create/update meetings, get cloud recording transcripts
• 📅 Unified Calendar - NEW: Cross-provider meeting slot finder aggregating Google + Microsoft calendars
• 👥 Multi-Account Connectors - NEW: Multiple accounts per vendor (e.g., work + personal) with automatic routing
• 🧪 Integration Testing - NEW: Reusable test suite framework for connector tools with 10 built-in suites
• 📝 Instruction Templates - NEW: {{DATE}}, {{AGENT_ID}}, {{RANDOM:1:10}} and custom {{COMMAND:arg}} in agent instructions — extensible registry with async support
• 🔄 Streaming - Real-time responses with event streams
• 📝 TypeScript - Full type safety and IntelliSense support

v0.2.0 — Multi-User Support: Set userId once on an agent and it automatically flows to all tool executions, OAuth token retrieval, session metadata, and connector scoping. Combine with identities and access policies for complete multi-tenant isolation. See Multi-User Support and Auth Identities in the User Guide.

Quick Start

Installation

npm install @everworker/oneringai

Basic Usage

import { Connector, Agent, Vendor } from '@everworker/oneringai';

// 1. Create a connector (authentication)
Connector.create({
  name: 'openai',
  vendor: Vendor.OpenAI,
  auth: { type: 'api_key', apiKey: process.env.OPENAI_API_KEY! },
});

// 2. Create an agent
const agent = Agent.create({
  connector: 'openai',
  model: 'gpt-4.1',
});

// 3. Run
const response = await agent.run('What is the capital of France?');
console.log(response.output_text);
// Output: "The capital of France is Paris."

With Tools

import { ToolFunction } from '@everworker/oneringai';

const weatherTool: ToolFunction = {
  definition: {
    type: 'function',
    function: {
      name: 'get_weather',
      description: 'Get current weather',
      parameters: {
        type: 'object',
        properties: {
          location: { type: 'string' },
        },
        required: ['location'],
      },
    },
  },
  execute: async (args) => {
    return { temp: 72, location: args.location };
  },
};

const agent = Agent.create({
  connector: 'openai',
  model: 'gpt-4.1',
  tools: [weatherTool],
});

await agent.run('What is the weather in Paris?');

Vision

import { createMessageWithImages } from '@everworker/oneringai';

const agent = Agent.create({
  connector: 'openai',
  model: 'gpt-4o',
});

const response = await agent.run(
  createMessageWithImages('What is in this image?', ['./photo.jpg'])
);

Audio (NEW)

import { TextToSpeech, SpeechToText } from '@everworker/oneringai';

// Text-to-Speech — built-in voice
const tts = TextToSpeech.create({
  connector: 'openai',
  model: 'tts-1-hd',
  voice: 'nova', // alloy | ash | ballad | coral | echo | fable | onyx | nova | sage | shimmer | verse | marin | cedar
});

await tts.toFile('Hello, world!', './output.mp3');

// Text-to-Speech — custom voice (OpenAI). Pass the `voice_…` id you got
// when registering the voice in the OpenAI dashboard; the SDK call is
// handled automatically.
const customTts = TextToSpeech.create({
  connector: 'openai',
  model: 'gpt-4o-mini-tts',
  voice: 'voice_1234abcd',
});
await customTts.toFile('Spoken in your bespoke voice.', './brand.mp3');

// Speech-to-Text
const stt = SpeechToText.create({
  connector: 'openai',
  model: 'whisper-1',
});

const result = await stt.transcribeFile('./audio.mp3');
console.log(result.text);

Image Generation (NEW)

import { ImageGeneration } from '@everworker/oneringai';

// OpenAI DALL-E
const imageGen = ImageGeneration.create({ connector: 'openai' });

const result = await imageGen.generate({
  prompt: 'A futuristic city at sunset',
  model: 'dall-e-3',
  size: '1024x1024',
  quality: 'hd',
});

// Save to file
const buffer = Buffer.from(result.data[0].b64_json!, 'base64');
await fs.writeFile('./output.png', buffer);

// Google Imagen
const googleGen = ImageGeneration.create({ connector: 'google' });

const googleResult = await googleGen.generate({
  prompt: 'A colorful butterfly in a garden',
  model: 'imagen-4.0-generate-001',
});

Video Generation (NEW)

import { VideoGeneration } from '@everworker/oneringai';

// OpenAI Sora
const videoGen = VideoGeneration.create({ connector: 'openai' });

// Start video generation (async - returns a job)
const job = await videoGen.generate({
  prompt: 'A cinematic shot of a sunrise over mountains',
  model: 'sora-2',
  duration: 8,
  resolution: '1280x720',           // 720x1280 / 1280x720 / 1024x1792 / 1792x1024 (1.4× HD)
});

// Wait for completion
const result = await videoGen.waitForCompletion(job.jobId);

// Download the video
const videoBuffer = await videoGen.download(job.jobId);
await fs.writeFile('./output.mp4', videoBuffer);

// Google Veo
const googleVideo = VideoGeneration.create({ connector: 'google' });

const veoJob = await googleVideo.generate({
  prompt: 'A butterfly flying through a garden',
  model: 'veo-3.0-generate-001',
  duration: 8,
});

Sora: extend, remix, edit (OpenAI only)

The Videos API references completed clips by id — pass the jobId returned by generate(), not a buffer or URL.

// Extend — generate an additional segment after the source clip.
const extension = await videoGen.extend({
  model: 'sora-2',
  video: job.jobId,           // id of a completed video
  prompt: 'The camera pulls back to reveal a snow-covered valley',
  extendDuration: 8,          // length of the *new* segment, snapped to 4/8/12
});

// Remix — same length, prompt-steered re-generation.
const remix = await videoGen.remix({
  videoId: job.jobId,
  prompt: 'Same composition, but at golden hour',
});

// Edit — apply a prompt-described change to a completed clip.
const edited = await videoGen.edit({
  videoId: job.jobId,
  prompt: 'Add light snowfall throughout',
});

Sora: reusable characters (OpenAI only)

Upload a reference video to register a character; thread the returned id back through vendorOptions on a later generate().

const character = await videoGen.createCharacter({
  name: 'Hero',
  video: './reference-shot.mp4', // Buffer | local path | URL
});
// → { id: 'char_…', name: 'Hero' }

const scene = await videoGen.generate({
  prompt: 'Hero walks across a windswept beach at dusk',
  vendorOptions: { characterId: character.id },
});

// Look up later
const same = await videoGen.getCharacter(character.id);

Embeddings (NEW)

import { Embeddings } from '@everworker/oneringai';

// OpenAI embeddings
const embeddings = Embeddings.create({ connector: 'openai' });

const result = await embeddings.embed(['Hello world', 'How are you?'], {
  model: 'text-embedding-3-small',
  dimensions: 512,  // MRL: reduce dimensions for faster search
});

console.log(result.embeddings.length);     // 2
console.log(result.embeddings[0].length);  // 512

// Ollama (local, free)
const local = Embeddings.create({ connector: 'ollama-local' });
const localResult = await local.embed('search query');
// Uses qwen3-embedding (4096 dims, #1 on MTEB multilingual)

Document Reader (NEW)

Read any document format — agents automatically get markdown text from PDFs, Word docs, spreadsheets, and more:

import { Agent, developerTools } from '@everworker/oneringai';

const agent = Agent.create({
  connector: 'openai',
  model: 'gpt-4.1',
  tools: developerTools,
});

// read_file auto-converts binary documents to markdown
await agent.run('Read /path/to/report.pdf and summarize the key findings');
await agent.run('Read /path/to/data.xlsx and describe the trends');
await agent.run('Read /path/to/presentation.pptx and list all slides');

Programmatic usage:

import { DocumentReader, readDocumentAsContent } from '@everworker/oneringai';

// Read any file to markdown pieces
const reader = DocumentReader.create();
const result = await reader.read('/path/to/report.pdf');
console.log(result.pieces); // DocumentPiece[] (text + images)

// One-call conversion to LLM Content[] (for multimodal input)
const content = await readDocumentAsContent('/path/to/slides.pptx', {
  imageFilter: { minWidth: 100, minHeight: 100 },
  imageDetail: 'auto',
});

const response = await agent.run([
  { type: 'input_text', text: 'Analyze this document:' },
  ...content,
]);

Supported Formats:

• Office: DOCX, PPTX, ODT, ODP, ODS, RTF (via officeparser)
• Spreadsheets: XLSX, CSV (via exceljs)
• PDF (via unpdf)
• HTML (via Readability + Turndown)
• Text: TXT, MD, JSON, XML, YAML
• Images: PNG, JPG, GIF, WEBP, SVG (pass-through as base64)

Web Search

Connector-based web search with multiple providers:

import { Connector, SearchProvider, ConnectorTools, Services, Agent, tools } from '@everworker/oneringai';

// Create search connector
Connector.create({
  name: 'serper-main',
  serviceType: Services.Serper,
  auth: { type: 'api_key', apiKey: process.env.SERPER_API_KEY! },
  baseURL: 'https://google.serper.dev',
});

// Option 1: Use SearchProvider directly
const search = SearchProvider.create({ connector: 'serper-main' });
const results = await search.search('latest AI developments 2026', {
  numResults: 10,
  country: 'us',
  language: 'en',
});

// Option 2: Use with Agent via ConnectorTools
const searchTools = ConnectorTools.for('serper-main');

const agent = Agent.create({
  connector: 'openai',
  model: 'gpt-4.1',
  tools: [...searchTools, tools.webFetch],
});

await agent.run('Search for quantum computing news and summarize');

Supported Search Providers:

• Serper - Google search via Serper.dev (2,500 free queries)
• Brave - Independent search index (privacy-focused)
• Tavily - AI-optimized search with summaries
• RapidAPI - Real-time web search (various pricing)

Web Scraping

Enterprise web scraping with automatic fallback and bot protection bypass:

import { Connector, ScrapeProvider, ConnectorTools, Services, Agent, tools } from '@everworker/oneringai';

// Create ZenRows connector for bot-protected sites
Connector.create({
  name: 'zenrows',
  serviceType: Services.Zenrows,
  auth: { type: 'api_key', apiKey: process.env.ZENROWS_API_KEY! },
  baseURL: 'https://api.zenrows.com/v1',
});

// Option 1: Use ScrapeProvider directly
const scraper = ScrapeProvider.create({ connector: 'zenrows' });
const result = await scraper.scrape('https://protected-site.com', {
  includeMarkdown: true,
  vendorOptions: {
    jsRender: true,        // JavaScript rendering
    premiumProxy: true,    // Residential IPs
  },
});

// Option 2: Use web_scrape tool with Agent via ConnectorTools
const scrapeTools = ConnectorTools.for('zenrows');

const agent = Agent.create({
  connector: 'openai',
  model: 'gpt-4.1',
  tools: [...scrapeTools, tools.webFetch],
});

// web_scrape auto-falls back: native → API
await agent.run('Scrape https://example.com and summarize');

Supported Scrape Providers:

• ZenRows - Enterprise scraping with JS rendering, residential proxies, anti-bot bypass
• Jina Reader - Clean content extraction with AI-powered readability
• Firecrawl - Web scraping with JavaScript rendering
• ScrapingBee - Headless browser scraping with proxy rotation

Supported Providers

| Provider | Text | Vision | TTS | STT | Image | Video | Tools | Context | |----------|------|--------|-----|-----|-------|-------|-------|---------| | OpenAI | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | 128K | | Anthropic (Claude) | ✅ | ✅ | ❌ | ❌ | ❌ | ❌ | ✅ | 1M | | Google (Gemini) | ✅ | ✅ | ✅ | ❌ | ✅ | ✅ | ✅ | 1M | | Google Vertex AI | ✅ | ✅ | ❌ | ❌ | ❌ | ❌ | ✅ | 1M | | Grok (xAI) | ✅ | ✅ | ❌ | ❌ | ✅ | ✅ | ✅ | 128K | | Groq | ✅ | ❌ | ❌ | ✅ | ❌ | ❌ | ✅ | 128K | | Together AI | ✅ | Some | ❌ | ❌ | ❌ | ❌ | ✅ | 128K | | DeepSeek | ✅ | ❌ | ❌ | ❌ | ❌ | ❌ | ✅ | 64K | | Mistral | ✅ | ❌ | ❌ | ❌ | ❌ | ❌ | ✅ | 32K | | Perplexity | ✅ | ❌ | ❌ | ❌ | ❌ | ❌ | ✅ | 128K | | Ollama | ✅ | Varies | ❌ | ❌ | ❌ | ❌ | ✅ | Varies | | Custom | ✅ | Varies | ❌ | ❌ | ❌ | ❌ | ✅ | Varies |

Key Features

1. Agent with Plugins

The Agent class is the primary agent type, supporting all features through composable plugins:

import { Agent, createFileContextStorage } from '@everworker/oneringai';

// Create storage for session persistence
const storage = createFileContextStorage('my-assistant');

const agent = Agent.create({
  connector: 'openai',
  model: 'gpt-4.1',
  userId: 'user-123',            // Flows to all tool executions automatically
  identities: [                   // Only these connectors visible to tools
    { connector: 'github' },
    { connector: 'slack' },
  ],
  tools: [weatherTool, emailTool],
  context: {
    features: {
      workingMemory: true,      // Store/retrieve data across turns
      inContextMemory: true,    // Key-value pairs directly in context
      persistentInstructions: true,  // Agent instructions that persist to disk
    },
    agentId: 'my-assistant',
    storage,
  },
});

// Run the agent
const response = await agent.run('Check weather and email me the report');
console.log(response.output_text);

// Save session for later
await agent.context.save('session-001');

Features:

• 🔧 Plugin Architecture - Enable/disable features via context.features
• 💾 Session Persistence - Save/load full state with ctx.save() and ctx.load()
• 📝 Working Memory - Store findings with automatic eviction
• 📌 InContextMemory - Key-value pairs visible directly to LLM
• 🔄 Persistent Instructions - Agent instructions that persist across sessions

2. Dynamic Tool Management (NEW)

Control tools at runtime. AgentContextNextGen is the single source of truth - agent.tools and agent.context.tools are the same ToolManager instance:

import { Agent } from '@everworker/oneringai';

const agent = Agent.create({
  connector: 'openai',
  model: 'gpt-4.1',
  tools: [weatherTool, emailTool, databaseTool],
});

// Disable tool temporarily
agent.tools.disable('database_tool');

// Enable later
agent.tools.enable('database_tool');

// UNIFIED ACCESS: Both paths access the same ToolManager
console.log(agent.tools === agent.context.tools);  // true

// Changes via either path are immediately reflected
agent.context.tools.disable('email_tool');
console.log(agent.tools.listEnabled().includes('email_tool'));  // false

// Context-aware selection
const selected = agent.tools.selectForContext({
  mode: 'interactive',
  priority: 'high',
});

// Backward compatible
agent.addTool(newTool);        // Still works!
agent.removeTool('old_tool');  // Still works!

3. Tool Execution Plugins (NEW)

Extend tool execution with custom behavior through a pluggable pipeline architecture. Add logging, analytics, UI updates, permission prompts, or any custom logic:

import { Agent, LoggingPlugin, type IToolExecutionPlugin } from '@everworker/oneringai';

const agent = Agent.create({
  connector: 'openai',
  model: 'gpt-4.1',
  tools: [weatherTool],
});

// Add built-in logging plugin
agent.tools.executionPipeline.use(new LoggingPlugin());

// Create a custom plugin
const analyticsPlugin: IToolExecutionPlugin = {
  name: 'analytics',
  priority: 100,

  async beforeExecute(ctx) {
    console.log(`Starting ${ctx.toolName}`);
  },

  async afterExecute(ctx, result) {
    const duration = Date.now() - ctx.startTime;
    trackToolUsage(ctx.toolName, duration);
    return result; // Must return result (can transform it)
  },

  async onError(ctx, error) {
    reportError(ctx.toolName, error);
    return undefined; // Let error propagate (or return value to recover)
  },
};

agent.tools.executionPipeline.use(analyticsPlugin);

Plugin Lifecycle:

1. beforeExecute - Modify args, abort execution, or pass through
2. Tool execution
3. afterExecute - Transform results (runs in reverse priority order)
4. onError - Handle/recover from errors

Plugin Context (PluginExecutionContext):

interface PluginExecutionContext {
  toolName: string;           // Name of the tool being executed
  args: unknown;              // Original arguments (read-only)
  mutableArgs: unknown;       // Modifiable arguments
  metadata: Map<string, unknown>; // Share data between plugins
  startTime: number;          // Execution start timestamp
  tool: ToolFunction;         // The tool being executed
  executionId: string;        // Unique ID for this execution
}

Built-in Plugins:

• LoggingPlugin - Logs tool execution with timing and result summaries

Pipeline Management:

// Add plugin
agent.tools.executionPipeline.use(myPlugin);

// Remove plugin
agent.tools.executionPipeline.remove('plugin-name');

// Check if registered
agent.tools.executionPipeline.has('plugin-name');

// Get plugin
const plugin = agent.tools.executionPipeline.get('plugin-name');

// List all plugins
const plugins = agent.tools.executionPipeline.list();

4. Tool Permissions (NEW)

Policy-based permission system with per-user rules, argument inspection, and pluggable storage. Permissions are enforced at the ToolManager pipeline level -- all tool execution paths are gated.

Zero-Config (Backward Compatible)

Existing code works unchanged. Safe tools (read-only, memory, catalog) are auto-allowed; all others default to prompting:

const agent = Agent.create({ connector: 'openai', model: 'gpt-4.1', tools: [readFile, bash] });

// read_file executes immediately (in DEFAULT_ALLOWLIST)
// bash triggers approval flow (write/shell tools require approval by default)

Per-User Permission Rules

User rules have the highest priority -- they override all built-in policies. Rules support argument inspection with conditions:

import { PermissionPolicyManager } from '@everworker/oneringai';

const manager = new PermissionPolicyManager({
  userRules: [
    // Allow bash, but only in the project directory
    {
      id: '1', toolName: 'bash', action: 'allow', enabled: true,
      createdBy: 'user', createdAt: new Date().toISOString(), updatedAt: new Date().toISOString(),
      conditions: [{ argName: 'command', operator: 'not_contains', value: 'rm -rf' }],
    },
    // Block all web tools unconditionally
    {
      id: '2', toolName: 'web_fetch', action: 'deny', enabled: true, unconditional: true,
      createdBy: 'admin', createdAt: new Date().toISOString(), updatedAt: new Date().toISOString(),
    },
  ],
});

Condition operators: starts_with, not_starts_with, contains, not_contains, equals, not_equals, matches (regex), not_matches.

Built-in Policies

Eight composable policies evaluated in priority order (deny short-circuits):

| Policy | Description | |--------|-------------| | AllowlistPolicy | Auto-allow tools in the allowlist (read-only, memory, catalog) | | BlocklistPolicy | Hard-block tools in the blocklist (no approval possible) | | SessionApprovalPolicy | Cache approvals per-session with optional argument-scoped keys | | PathRestrictionPolicy | Restrict file tools to allowed directory roots | | BashFilterPolicy | Block/flag dangerous shell commands by pattern | | UrlAllowlistPolicy | Restrict web tools to allowed URL domains | | RolePolicy | Role-based access control (map user roles to tool permissions) | | RateLimitPolicy | Limit tool invocations per time window |

import { PathRestrictionPolicy, BashFilterPolicy } from '@everworker/oneringai';

const agent = Agent.create({
  connector: 'openai', model: 'gpt-4.1',
  permissions: {
    policies: [
      new PathRestrictionPolicy({ allowedPaths: ['/workspace'] }),
      new BashFilterPolicy({ blockedPatterns: ['rm -rf', 'sudo'] }),
    ],
  },
});

Approval Dialog Integration

When a tool needs approval, the onApprovalRequired callback fires. Return a createRule to persist the decision:

const agent = Agent.create({
  connector: 'openai', model: 'gpt-4.1',
  permissions: {
    onApprovalRequired: async (ctx) => {
      const userChoice = await showApprovalDialog(ctx.toolName, ctx.args);

      return {
        approved: userChoice.allow,
        // Persist as a user rule so it won't ask again
        createRule: userChoice.remember ? {
          description: `Auto-allow ${ctx.toolName}`,
          conditions: [{ argName: 'path', operator: 'starts_with', value: '/workspace' }],
        } : undefined,
      };
    },
  },
});

Tool Self-Declaration

Tool authors declare permission defaults on the tool definition. App developers can override at registration:

const myTool: ToolFunction = {
  definition: { type: 'function', function: { name: 'deploy', description: '...', parameters: {...} } },
  execute: async (args) => { /* ... */ },
  // Author-declared defaults
  permission: {
    scope: 'once',
    riskLevel: 'high',
    approvalMessage: 'This will deploy to production',
    sensitiveArgs: ['environment', 'version'],
  },
};

// App developer can override at registration
agent.tools.register(myTool, {
  permission: { scope: 'session' },  // Relax to session-level approval
});

For complete documentation, see the User Guide.

5. Session Persistence

Save and resume full context state including conversation history and plugin states:

import { AgentContextNextGen, createFileContextStorage } from '@everworker/oneringai';

// Create storage for the agent
const storage = createFileContextStorage('my-assistant');

// Create context with storage
const ctx = AgentContextNextGen.create({
  model: 'gpt-4.1',
  features: { workingMemory: true },
  storage,
});

// Build up state
ctx.addUserMessage('Remember: my favorite color is blue');
await ctx.memory?.store('user_color', 'User favorite color', 'blue');

// Save session with metadata
await ctx.save('session-001', { title: 'User Preferences' });

// Later... load session
const ctx2 = AgentContextNextGen.create({ model: 'gpt-4.1', storage });
const loaded = await ctx2.load('session-001');

if (loaded) {
  // Full state restored: conversation, plugin states, etc.
  const color = await ctx2.memory?.retrieve('user_color');
  console.log(color); // 'blue'
}

What's Persisted:

• Complete conversation history
• All plugin states (WorkingMemory entries, InContextMemory, etc.)
• System prompt

Storage Location: ~/.oneringai/agents/<agentId>/sessions/<sessionId>.json

Storage Registry

Swap all storage backends (sessions, media, custom tools, OAuth tokens, etc.) with a single configure() call at init time. No breaking changes — all existing APIs continue to work.

import { StorageRegistry } from '@everworker/oneringai';

StorageRegistry.configure({
  media: new S3MediaStorage(),
  oauthTokens: new EncryptedFileTokenStorage(),
  // Context-aware factories — optional StorageContext for multi-tenant partitioning
  customTools: (ctx) => new MongoCustomToolStorage(ctx?.userId),
  sessions: (agentId, ctx) => new RedisContextStorage(agentId, ctx?.tenantId),
  persistentInstructions: (agentId, ctx) => new DBInstructionsStorage(agentId, ctx?.userId),
  workingMemory: (ctx) => new RedisMemoryStorage(ctx?.tenantId),
  routineDefinitions: (ctx) => new MongoRoutineStorage(ctx?.userId),
});

// All agents and tools automatically use these backends
const agent = Agent.create({ connector: 'openai', model: 'gpt-4.1' });

Resolution order: explicit constructor param > StorageRegistry > file-based default.

Multi-tenant: Factories receive an optional StorageContext (opaque, like ConnectorAccessContext). Set via StorageRegistry.setContext({ userId, tenantId }) — auto-forwarded to all factory calls for per-user/per-tenant storage partitioning.

See the User Guide for full documentation.

6. Working Memory

Use the WorkingMemoryPluginNextGen for agents that need to store and retrieve data:

import { Agent } from '@everworker/oneringai';

const agent = Agent.create({
  connector: 'openai',
  model: 'gpt-4.1',
  tools: [weatherTool, emailTool],
  context: {
    features: { workingMemory: true },
  },
});

// Agent now has unified store_get, store_set, store_delete, store_list, store_action tools
await agent.run('Check weather for SF and remember the result');

Features:

• 📝 Working Memory - Store and retrieve data with priority-based eviction
• 🏗️ Hierarchical Memory - Raw → Summary → Findings tiers for research tasks
• 🧠 Context Management - Automatic handling of context limits
• 💾 Session Persistence - Save/load via ctx.save() and ctx.load()

7. Research with Search Tools

Use Agent with search tools and WorkingMemoryPluginNextGen for research workflows:

import { Agent, ConnectorTools, Connector, Services, tools } from '@everworker/oneringai';

// Setup search connector
Connector.create({
  name: 'serper-main',
  serviceType: Services.Serper,
  auth: { type: 'api_key', apiKey: process.env.SERPER_API_KEY! },
  baseURL: 'https://google.serper.dev',
});

// Create agent with search and memory
const searchTools = ConnectorTools.for('serper-main');

const agent = Agent.create({
  connector: 'openai',
  model: 'gpt-4.1',
  tools: [...searchTools, tools.webFetch],
  context: {
    features: { workingMemory: true },
  },
});

// Agent can search and store findings in memory
await agent.run('Research AI developments in 2026 and store key findings');

Features:

• 🔍 Web Search - SearchProvider with Serper, Brave, Tavily, RapidAPI
• 📝 Working Memory - Store findings with priority-based eviction
• 🏗️ Tiered Memory - Raw → Summary → Findings pattern

8. Context Management

AgentContextNextGen is the modern, plugin-based context manager. It provides clean separation of concerns with composable plugins:

import { Agent, AgentContextNextGen } from '@everworker/oneringai';

// Option 1: Use AgentContextNextGen directly (standalone)
const ctx = AgentContextNextGen.create({
  model: 'gpt-4.1',
  systemPrompt: 'You are a helpful assistant.',
  features: { workingMemory: true, inContextMemory: true },
});

ctx.addUserMessage('What is the weather in Paris?');
const { input, budget } = await ctx.prepare(); // Ready for LLM call

// Option 2: Via Agent.create
const agent = Agent.create({
  connector: 'openai',
  model: 'gpt-4.1',
  context: {
    features: { workingMemory: true },
  },
});

// Agent uses AgentContextNextGen internally
await agent.run('Check the weather');

Feature Configuration

Enable/disable features independently. Disabled features = no associated tools registered:

// Minimal stateless agent (no memory)
const agent = Agent.create({
  connector: 'openai',
  model: 'gpt-4.1',
  context: {
    features: { workingMemory: false }
  }
});

// Full-featured agent with all plugins
const agent = Agent.create({
  connector: 'openai',
  model: 'gpt-4.1',
  context: {
    features: {
      workingMemory: true,
      inContextMemory: true,
      persistentInstructions: true
    },
    agentId: 'my-assistant',  // Required for persistentInstructions
  }
});

Available Features: | Feature | Default | Plugin | Associated Tools | |---------|---------|--------|------------------| | workingMemory | true | WorkingMemoryPluginNextGen | Unified store_* tools (store="memory"). Actions: cleanup_raw, query | | inContextMemory | true | InContextMemoryPluginNextGen | Unified store_* tools (store="context") | | persistentInstructions | false | PersistentInstructionsPluginNextGen | Unified store_* tools (store="instructions"). Actions: clear | | userInfo | false | UserInfoPluginNextGen | Unified store_* tools (store="user_info") + todo_add/update/remove | | toolCatalog | false | ToolCatalogPluginNextGen | tool_catalog_search/load/unload | | sharedWorkspace | false | SharedWorkspacePluginNextGen | Unified store_* tools (store="workspace"). Actions: log, history, archive, clear | | memory | false | MemoryPluginNextGen | 6 read tools: memory_recall, memory_graph, memory_search, memory_search_documents, memory_find_entity, memory_list_facts. Requires plugins.memory.memory: MemorySystem. | | memoryWrite | false | MemoryWritePluginNextGen | 6 write tools: memory_remember, memory_link, memory_upsert_entity, memory_forget, memory_restore, memory_set_agent_rule. Requires memory: true. |

AgentContextNextGen architecture:

• Plugin-first design - All features are composable plugins
• ToolManager - Tool registration, execution, circuit breakers
• Single system message - All context components combined
• Smart compaction - Happens once, right before LLM call

Compaction strategy:

• algorithmic (default) - Moves large tool results to Working Memory, limits tool pairs, applies rolling window. Triggers at 75% context usage.

Context preparation:

const { input, budget, compacted, compactionLog } = await ctx.prepare();

console.log(budget.totalUsed);           // Total tokens used
console.log(budget.available);           // Remaining tokens
console.log(budget.utilizationPercent);  // Usage percentage

9. InContextMemory

Store key-value pairs directly in context for instant LLM access without retrieval calls:

import { AgentContextNextGen } from '@everworker/oneringai';

const ctx = AgentContextNextGen.create({
  model: 'gpt-4.1',
  features: { inContextMemory: true },
  plugins: {
    inContextMemory: { maxEntries: 20 },
  },
});

// Access the plugin
const plugin = ctx.getPlugin('in_context_memory');

// Store data - immediately visible to LLM
plugin.set('current_state', 'Task processing state', { step: 2, status: 'active' });
plugin.set('user_prefs', 'User preferences', { verbose: true }, 'high');

// Store data with UI display - shown in the host app's sidebar panel
plugin.set('dashboard', 'Progress dashboard', '## Progress\n- [x] Step 1\n- [ ] Step 2', 'normal', true);

// LLM uses unified store tools: store_set("whiteboard", ...), store_get("whiteboard", ...), etc.
// Or access directly via plugin API
const state = plugin.get('current_state');  // { step: 2, status: 'active' }

Key Difference from WorkingMemory:

• WorkingMemory: External storage + index → requires store_get("notes", key) for values
• InContextMemory: Full values in context → instant access, no retrieval needed

UI Display (showInUI): Entries with showInUI: true are displayed in the host application's sidebar panel with full markdown rendering (code blocks, tables, charts, diagrams, etc.). The LLM sets this via store_set("whiteboard", key, { ..., showInUI: true }). Users can also pin specific entries to always display them regardless of the agent's setting. See the User Guide for details.

Use cases: Session state, user preferences, counters, flags, small accumulated results, live dashboards.

10. Persistent Instructions

Store agent-level custom instructions that persist across sessions on disk:

import { Agent } from '@everworker/oneringai';

const agent = Agent.create({
  connector: 'openai',
  model: 'gpt-4.1',
  context: {
    agentId: 'my-assistant',  // Required for storage path
    features: {
      persistentInstructions: true,
    },
  },
});

// LLM uses unified store tools: store_set("instructions", ...), store_delete("instructions", ...), etc.
// Instructions persist to ~/.oneringai/agents/my-assistant/custom_instructions.json

Key Features:

• 📁 Disk Persistence - Instructions survive process restarts and sessions
• 🔧 LLM-Modifiable - Agent can update its own instructions during execution
• 🔄 Auto-Load - Instructions loaded automatically on agent start
• 🛡️ Never Compacted - Critical instructions always preserved in context

Store Tools (via unified store_* interface):

• store_set("instructions", key, { content }) - Add or update a single instruction by key
• store_delete("instructions", key) - Remove a single instruction by key
• store_list("instructions") - List all instructions with keys and content
• store_action("instructions", "clear", { confirm: true }) - Remove all instructions

Use cases: Agent personality/behavior, user preferences, learned rules, tool usage patterns.

11. User Info

Store user-specific preferences and context that are automatically injected into the LLM system message:

import { Agent } from '@everworker/oneringai';

const agent = Agent.create({
  connector: 'openai',
  model: 'gpt-4.1',
  userId: 'alice',  // Optional — defaults to 'default' user
  context: {
    features: {
      userInfo: true,
    },
  },
});

// LLM uses unified store tools: store_set("user_info", ...), store_get("user_info", ...), etc.
// Data persists to ~/.oneringai/users/alice/user_info.json
// All entries are automatically shown in context — no need to call store_get each turn

Key Features:

• 📁 Disk Persistence - User info survives process restarts and sessions
• 🔄 Auto-Inject - Entries rendered as markdown and included in the system message automatically
• 👥 User-Scoped - Data is per-user, not per-agent — different agents share the same user data
• 🔧 LLM-Modifiable - Agent can update user info during execution

Store Tools (via unified store_* interface):

• store_set("user_info", key, { value, description? }) - Store/update user information
• store_get("user_info", key?) - Retrieve one entry or all entries
• store_delete("user_info", key) - Remove a specific entry
• store_action("user_info", "clear", { confirm: true }) - Clear all entries

TODO Tools (built into the same plugin):

• todo_add - Create a TODO (title, description?, people?, dueDate?, tags?)
• todo_update - Update a TODO (id, plus any fields to change including status: 'done')
• todo_remove - Delete a TODO by id

TODOs are stored alongside user info and rendered in a separate "Current TODOs" checklist in context. The agent proactively suggests creating TODOs when conversation implies action items, reminds about due/overdue items once per day, and auto-cleans completed TODOs after 48 hours.

Use cases: User preferences (theme, language, timezone), user context (role, location), accumulated knowledge about the user, task/TODO tracking with deadlines and people.

⚠️ Deprecated in favour of the Self-Learning Memory plugin below. UserInfoPluginNextGen + PersistentInstructionsPluginNextGen keep working unchanged for existing integrations — no breaking change — but new code should prefer MemoryPluginNextGen.

10b. Self-Learning Memory — plugin + tools

A brain-like, queryable knowledge store built on the memory layer. Two cooperating context plugins + 11 LLM-callable tools turn the agent into a learning system: it bootstraps a person entity for the user (and optionally an organization entity for their group), injects the evolving user profile + any user-given behavior rules into the system message every turn, and exposes memory_* tools so the LLM can read or write the knowledge graph mid-conversation. Observations flow in via memory_remember (LLM-driven) or SessionIngestorPluginNextGen (passive); incremental profile regeneration synthesises them; the next turn sees the updated profile. No manual prompt engineering for user/agent preferences.

import { Agent, createMemorySystemWithConnectors, InMemoryAdapter } from '@everworker/oneringai';

const memory = createMemorySystemWithConnectors({
  store: new InMemoryAdapter(),                 // or MongoMemoryAdapter for production
  connectors: {
    embedding: { connector: 'openai', model: 'text-embedding-3-small', dimensions: 1536 },
    profile:   { connector: 'anthropic', model: 'claude-sonnet-4-6' },
  },
});

const agent = Agent.create({
  connector: 'anthropic',
  model: 'claude-sonnet-4-6',
  userId: 'alice',                              // REQUIRED — memory's owner invariant
  context: {
    agentId: 'my-assistant',
    features: {
      memory: true,                             // reads: profile injection + 5 retrieval tools
      memoryWrite: true,                        // writes: 6 mutation tools (omit for retrieval-only)
    },
    plugins: {
      memory: {
        memory,
        // groupId: 'team-A',                   // trusted, from your auth layer
        // userProfileInjection: { topFacts: 20, relatedTasks: true },
        // groupBootstrap: { displayName: 'Acme', identifiers: [{ kind: 'domain', value: 'acme.com' }] },
      },
    },
  },
});

await agent.run('Remember I prefer concise answers');
// Agent calls memory_remember({subject:"me", predicate:"prefers", value:"concise answers"})
// Fact stored → profile regen fires in background → next turn sees it in the user profile

Key Features:

• 🧠 Self-learning — profiles synthesised from facts via incremental regeneration (prior profile + new facts + invalidated IDs → evolved profile)
• 🔐 Three-principal permissions — owner / group / world, enforced at the adapter
• 📊 Ranked recall — profile + top facts by confidence × recency × predicateWeight × importance
• 🕸️ Graph queries — Mongo native $graphLookup when available, iterative BFS fallback
• 🔍 Semantic search — over embedded facts (with Atlas Vector Search at scale)
• 🧬 Multi-ID entities — lookup by email / slack_id / github_login / domain / any identifier; upsert auto-merges
• 📜 Supersession history — corrections archive predecessors; audit chain preserved via archivedOnly: true
• 🪧 User-driven behavior rules — memory_set_agent_rule records "be terse" / "reply in Russian" / "your name is Jason" directives, rendered back into the system message every turn (per-user-per-agent scoped)
• 🏢 Optional org bootstrap — when groupBootstrap is set, an organization entity is upserted and rendered as a separate "Your Organization Profile" block alongside the user profile
• 🛡️ LLM-safe — groupId fixed by host app (never from tool args); ghost-write protection; contextIds auto-downgrade; numeric limits clamped

12 LLM tools (memory_*), split into two opt-in bundles:

Read (via MemoryPluginNextGen, feature flag memory):

• memory_recall(subject, include?) — profile + top facts + optional tiers (documents / semantic / neighbors)
• memory_graph(start, direction, maxDepth, predicates?) — N-hop traversal
• memory_search(query, topK?, filter?) — semantic text search across facts
• memory_search_documents(query, mode?, attachedTo?, role?, limit?) — search long-form documents (type='document') by content. Semantic mode matches contentEmbedding; keyword mode is case-insensitive substring over body + title.
• memory_find_entity(by, action? ∈ {find, list}) — lookup or list (read-only)
• memory_list_facts(subject, predicate?, archivedOnly?) — structured enumeration

Write (via MemoryWritePluginNextGen, feature flag memoryWrite, requires memory: true):

• memory_remember(subject, predicate, value?/objectId?/details?, visibility?) — write a fact (atomic or document)
• memory_link(from, predicate, to) — write a relational fact
• memory_upsert_entity(type, displayName, identifiers, ...) — create or merge an entity by identifier
• memory_forget(factId, replaceWith?) — archive or supersede (rate-limited 10/60s/user)
• memory_restore(factId) — un-archive (undo for memory_forget)
• memory_set_agent_rule(rule, replaces?) — record a user-specific behavior rule for THIS agent

Enable memory: true alone for retrieval-only agents (and pair with SessionIngestorPluginNextGen for passive background learning); enable both flags for agents that write memory deliberately.

Flexible SubjectRef — every tool accepts any of: entity id, "me", "this_agent", {id}, {identifier: {kind, value}}, {surface: "..."}.

Storage backends: InMemoryAdapter (zero deps, dev/tests), MongoMemoryAdapter + RawMongoCollection (production servers — supports native $graphLookup + Atlas Vector Search via ensureVectorSearchIndexes()), MongoMemoryAdapter + MeteorMongoCollection (Meteor apps — reactive publications). Custom adapters implement IMemoryStore.

See the USER_GUIDE Self-Learning Memory section for the user-guide-level walkthrough, docs/MEMORY_GUIDE.md for the full conceptual model + adapter setup + signal ingestion, docs/MEMORY_API.md for the MemorySystem API reference, and docs/MEMORY_PERMISSIONS.md for the permission model.

12. Direct LLM Access

Bypass all context management for simple, stateless LLM calls:

const agent = Agent.create({ connector: 'openai', model: 'gpt-4.1' });

// Direct call - no history tracking, no memory, no context preparation
const response = await agent.runDirect('What is 2 + 2?');
console.log(response.output_text);  // "4"

// With options
const response = await agent.runDirect('Summarize this', {
  instructions: 'Be concise',
  temperature: 0.5,
  maxOutputTokens: 100,
});

// Multimodal (text + image)
const response = await agent.runDirect([
  { type: 'message', role: 'user', content: [
    { type: 'input_text', text: 'What is in this image?' },
    { type: 'input_image', image_url: 'https://example.com/image.png' }
  ]}
]);

// Streaming
for await (const event of agent.streamDirect('Tell me a story')) {
  if (event.type === 'output_text_delta') {
    process.stdout.write(event.delta);
  }
}

Comparison:

| Aspect | run() | runDirect() | |--------|-------------------|---------------| | History tracking | ✅ | ❌ | | Memory/Cache | ✅ | ❌ | | Context preparation | ✅ | ❌ | | Agentic loop (tool execution) | ✅ | ❌ | | Overhead | Full context management | Minimal |

Use cases: Quick one-off queries, embeddings-like simplicity, testing, hybrid workflows.

Thinking / Reasoning (Per-Call)

Control reasoning effort per call — vendor-agnostic API that maps to OpenAI's reasoning_effort, Anthropic's budget_tokens, and Google's thinkingBudget:

const agent = Agent.create({ connector: 'anthropic', model: 'claude-sonnet-4-6' });

// Set reasoning at agent level (applies to all calls)
const agent2 = Agent.create({
  connector: 'openai', model: 'o3-mini',
  thinking: { enabled: true, effort: 'medium' },
});

// Override per call via RunOptions
const deep = await agent.run('Prove this theorem', {
  thinking: { enabled: true, budgetTokens: 16384 },
});

const quick = await agent.run('What is 2+2?', {
  thinking: { enabled: true, effort: 'low' },
});

// Streaming with reasoning
for await (const event of agent.stream('Analyze this code', {
  thinking: { enabled: true, effort: 'high' },
})) { /* ... */ }

// Also works with runDirect()
const resp = await agent.runDirect('Quick question', {
  thinking: { enabled: true, effort: 'medium' },
});

RunOptions (for run() / stream()): thinking, temperature, vendorOptions — override agent-level config for a single call.

13. Audio Capabilities

Text-to-Speech and Speech-to-Text with multiple providers:

import { TextToSpeech, SpeechToText } from '@everworker/oneringai';

// === Text-to-Speech ===
const tts = TextToSpeech.create({
  connector: 'openai',
  model: 'tts-1-hd',       // or 'gpt-4o-mini-tts' for instruction steering
  voice: 'nova',
});

// Synthesize to file
await tts.toFile('Hello, world!', './output.mp3');

// Synthesize with options
const audio = await tts.synthesize('Speak slowly', {
  format: 'wav',
  speed: 0.75,
});

// Introspection
const voices = await tts.listVoices();
const models = tts.listAvailableModels();

// === Speech-to-Text ===
const stt = SpeechToText.create({
  connector: 'openai',
  model: 'whisper-1',      // or 'gpt-4o-transcribe'
});

// Transcribe
const result = await stt.transcribeFile('./audio.mp3');
console.log(result.text);

// With timestamps
const detailed = await stt.transcribeWithTimestamps(audioBuffer, 'word');
console.log(detailed.words);  // [{ word, start, end }, ...]

// Translation
const english = await stt.translate(frenchAudio);

Streaming TTS — for real-time voice applications:

// Stream audio chunks as they arrive from the API
for await (const chunk of tts.synthesizeStream('Hello!', { format: 'pcm' })) {
  if (chunk.audio.length > 0) playPCMChunk(chunk.audio);  // 24kHz 16-bit LE mono
  if (chunk.isFinal) break;
}

// VoiceStream wraps agent text streams with interleaved audio events
const voice = VoiceStream.create({
  ttsConnector: 'openai', ttsModel: 'tts-1-hd', voice: 'nova',
});
for await (const event of voice.wrap(agent.stream('Tell me a story'))) { ... }

Available Models:

• TTS: OpenAI (tts-1, tts-1-hd, gpt-4o-mini-tts), Google (gemini-tts)
• STT: OpenAI (whisper-1, gpt-4o-transcribe), Groq (whisper-large-v3 - 12x cheaper!)

Embeddings (NEW)

Generate text embeddings across multiple vendors with a unified API. Supports Matryoshka Representation Learning (MRL) for flexible output dimensions.

import { Embeddings, Connector, Vendor } from '@everworker/oneringai';

// Setup
Connector.create({
  name: 'openai',
  vendor: Vendor.OpenAI,
  auth: { type: 'api_key', apiKey: process.env.OPENAI_API_KEY! },
});

const embeddings = Embeddings.create({ connector: 'openai' });

// Single text
const result = await embeddings.embed('Hello world');
console.log(result.embeddings[0].length);  // 1536 (default for text-embedding-3-small)

// Batch with custom dimensions (MRL)
const batch = await embeddings.embed(
  ['search query', 'document chunk 1', 'document chunk 2'],
  { dimensions: 512 }
);
console.log(batch.embeddings.length);     // 3
console.log(batch.embeddings[0].length);  // 512

// Local with Ollama (free, no API key)
Connector.create({
  name: 'ollama-local',
  vendor: Vendor.Ollama,
  auth: { type: 'none' },
  baseURL: 'http://localhost:11434/v1',
});

const local = Embeddings.create({ connector: 'ollama-local' });
const localResult = await local.embed('semantic search query');
// Uses qwen3-embedding by default (4096 dims, #1 on MTEB multilingual)

Model introspection and cost estimation:

import {
  getEmbeddingModelInfo,
  getEmbeddingModelsByVendor,
  calculateEmbeddingCost,
  EMBEDDING_MODELS,
  Vendor,
} from '@everworker/oneringai';

// Model details
const info = getEmbeddingModelInfo('text-embedding-3-small');
console.log(info.capabilities.maxDimensions);       // 1536
console.log(info.capabilities.features.matryoshka);  // true (supports MRL)
console.log(info.capabilities.maxTokens);            // 8191

// Cost estimation
const cost = calculateEmbeddingCost('text-embedding-3-small', 1_000_000);
console.log(`$${cost} per 1M tokens`);  // $0.02

// Browse models by vendor
const ollamaModels = getEmbeddingModelsByVendor(Vendor.Ollama);
console.log(ollamaModels.map(m => `${m.name} (${m.capabilities.defaultDimensions}d)`));
// ['qwen3-embedding (4096d)', 'qwen3-embedding:4b (4096d)', 'qwen3-embedding:0.6b (1024d)', ...]

Available Embedding Models:

| Vendor | Model | Dims | MRL | Tokens | Price/1M | |--------|-------|------|-----|--------|----------| | OpenAI | text-embedding-3-small | 1536 | yes | 8191 | $0.02 | | OpenAI | text-embedding-3-large | 3072 | yes | 8191 | $0.13 | | Google | text-embedding-004 | 768 | yes | 2048 | Free | | Mistral | mistral-embed | 1024 | no | 8192 | $0.10 | | Ollama | qwen3-embedding (8B) | 4096 | yes | 8192 | Free (local) | | Ollama | qwen3-embedding:0.6b | 1024 | yes | 8192 | Free (local) | | Ollama | nomic-embed-text | 768 | yes | 8192 | Free (local) |

14. Model Registry

Complete metadata for 60+ models with pricing, context windows, and feature flags:

import { getModelInfo, calculateCost, LLM_MODELS, Vendor } from '@everworker/oneringai';

// Get model information
const model = getModelInfo('gpt-5.2');
console.log(model.features.input.tokens);  // 400000
console.log(model.features.input.cpm);     // 1.75 (cost per million)

// Calculate costs
const cost = calculateCost('gpt-5.2', 50_000, 2_000);
console.log(`Cost: $${cost}`);  // $0.1155

// With caching
const cachedCost = calculateCost('gpt-5.2', 50_000, 2_000, {
  useCachedInput: true
});
console.log(`Cached: $${cachedCost}`);  // $0.0293 (90% discount)

Available Models:

• OpenAI (40+): GPT-5.5 (flagship), GPT-5.4 (+ pro / mini / nano), GPT-5.3, GPT-5.2, GPT-5.1, GPT-5, GPT-4.1, GPT-4o, o3, o4-mini, o1, Deep Research, Audio, Realtime, Open-Source
• Anthropic (9): Claude 4.6 (Opus, Sonnet), Claude 4.5, Claude 4.1, Claude 4, Claude 3.7 Sonnet, Haiku 4.5
• Google (10): Gemini 3.1, Gemini 3, Gemini 2.5
• Grok (5): Grok 4.20 (reasoning, non-reasoning, multi-agent), Grok 4.1 Fast

15. Streaming

Real-time responses:

import { StreamHelpers } from '@everworker/oneringai';

for await (const text of StreamHelpers.textOnly(agent.stream('Hello'))) {
  process.stdout.write(text);
}

16. OAuth for External APIs

import { OAuthManager, FileStorage } from '@everworker/oneringai';

const oauth = new OAuthManager({
  flow: 'authorization_code',
  clientId: process.env.GITHUB_CLIENT_ID!,
  clientSecret: process.env.GITHUB_CLIENT_SECRET!,
  authorizationUrl: 'https://github.com/login/oauth/authorize',
  tokenUrl: 'https://github.com/login/oauth/access_token',
  storage: new FileStorage({ directory: './tokens' }),
});

const authUrl = await oauth.startAuthFlow('user123');

17. Developer Tools

File system and shell tools for building coding assistants:

import { developerTools } from '@everworker/oneringai';

const agent = Agent.create({
  connector: 'openai',
  model: 'gpt-4.1',
  tools: developerTools, // Includes all 11 tools
});

// Agent can now:
// - Read files (read_file)
// - Write files (write_file)
// - Edit files with surgical precision (edit_file)
// - Search files by pattern (glob)
// - Search content with regex (grep)
// - List directories (list_directory)
// - Execute shell commands (bash)
// - Start dev servers (dev_server)
// - Manage background processes (bg_process_output, bg_process_list, bg_process_kill)

await agent.run('Read package.json and tell me the dependencies');
await agent.run('Find all TODO comments in the src directory');
await agent.run('Run npm test and report any failures');

Available Tools:

• read_file - Read file contents with line numbers
• write_file - Create/overwrite files
• edit_file - Surgical find/replace edits
• glob - Find files by pattern (**/*.ts)
• grep - Search content with regex
• list_directory - List directory contents
• bash - Execute shell commands with safety guards
• dev_server - Start a development server in the background
• bg_process_output - Read output from a background process
• bg_process_list - List running background processes
• bg_process_kill - Stop a background process

Safety Features:

• Blocked dangerous commands (rm -rf /, fork bombs)
• Configurable blocked directories (node_modules, .git)
• Timeout protection (default 2 min)
• Output truncation for large outputs

18. Custom Tool Generation (NEW)

Let agents create their own tools at runtime — draft, test, iterate, save, and reuse. The agent writes JavaScript code, validates it, tests it in the VM sandbox, and persists it for future use. All 6 meta-tools are auto-registered and visible in Everworker Desktop.

import { createCustomToolMetaTools, hydrateCustomTool } from '@everworker/oneringai';

// Give an agent the ability to create tools
const agent = Agent.create({
  connector: 'openai',
  model: 'gpt-4.1',
  tools: [...createCustomToolMetaTools()],
});

// The agent can now: draft → test → save tools autonomously
await agent.run('Create a tool that fetches weather data from the OpenWeather API');

// Later: load and use a saved tool
import { createFileCustomToolStorage } from '@everworker/oneringai';
const storage = createFileCustomToolStorage();
const definition = await storage.load(undefined, 'fetch_weather'); // undefined = default user
const weatherTool = hydrateCustomTool(definition!);

// Register on any agent
agent.tools.register(weatherTool, { source: 'custom', tags: ['weather', 'api'] });

Meta-Tools: custom_tool_draft (validate), custom_tool_test (execute in sandbox), custom_tool_save (persist), custom_tool_list (search), custom_tool_load (retrieve), custom_tool_delete (remove)

Dynamic Descriptions: Draft and test tools use descriptionFactory to show all available connectors and the full sandbox API — automatically updated when connectors are added or removed.

Pluggable Storage: Default FileCustomToolStorage saves to ~/.oneringai/users/<userId>/custom-tools/ (defaults to ~/.oneringai/users/default/custom-tools/ when no userId). Implement ICustomToolStorage for MongoDB, S3, or any backend.

See the User Guide for the complete workflow, sandbox API reference, and examples.

19. Desktop Automation Tools (NEW)

OS-level desktop automation for building "computer use" agents — screenshot the screen, send to a vision model, receive tool calls (click, type, etc.), execute them, r