ai

A privacy-focused AI assistant that can use local or optional cloud AI providers for scheduling, meeting analysis, and email summaries.

In plain words
What is it for?
Use it to schedule meetings in natural language, find times across working hours and time zones, resolve conflicts, protect focus time, and summarize email.
Why use it?
It can help with planning and inbox work while allowing the default AI processing to stay on the user’s machine.

Command

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add commands/nylas/cli/ai
Clone the repo
git clone --depth 1 https://github.com/nylas/cli
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,337 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.01337
Opus 5 $0.00000 $0.00668
Sonnet 5 $0.00000 $0.00267
Haiku 4.5 $0.00000 $0.00134

Measured 2d ago against content hash 45e13eab9d9a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ai scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

docs/commands/ai.md · 217 lines

How it starts

The opening of the file, as written. The whole thing — 217 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AI-Powered Features

Privacy-first AI assistant with multi-provider support

Quick Reference: COMMANDS.md | Related: Calendar | Email


Overview

AI assistant features:

  • Natural language scheduling: "Schedule 30-min call with John next Tuesday"
  • Find optimal meeting times: Analyze timezones and working hours
  • Conflict resolution: Auto-suggest rescheduling
  • Focus time protection: AI-adaptive deep work blocks
  • Meeting analytics: Pattern analysis and insights
  • Email analysis: Inbox summary, categorization, and action items

Time saved: 7.6 hours/week average | Errors reduced: 80%


Privacy-First Design

Local AI (Ollama) - Default

  • All data stays on your machine
  • No external API calls
  • GDPR/HIPAA compliant
  • Works offline
  • Zero cost (completely free)

Cloud AI - Opt-In

  • Requires explicit consent
  • Data sent to third-party API
  • Advanced reasoning
  • Faster processing

Quick Start

1. Install Local AI (Recommended)

# Install Ollama (free, private, offline)
brew install ollama
ollama serve
ollama pull llama3.2

2. Configure

nylas ai config
# Select: Ollama (default)
# Model: llama3.2

3. Use AI Features

# Natural language scheduling
nylas calendar schedule ai "coffee with Alice next Monday 2pm"

# AI analytics
nylas calendar analyze

# Find best meeting time
nylas calendar find-time --participants [email protected],[email protected] --duration 1h

Providers

Provider Privacy Cost Best For
Ollama Local Free Privacy, offline, zero cost
Claude Cloud $$ Advanced reasoning
OpenAI Cloud $$ Fast processing
Groq Cloud $ Low latency

Default: Ollama (local, private, free)


Calendar AI Features

Natural Language Scheduling

nylas calendar schedule ai "team standup every Monday at 10am"
nylas calendar schedule ai "lunch with Bob next week"
nylas calendar schedule ai "30-min 1:1 with Sarah on Thursday"

Read the full file on GitHub · 217 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 217 lines · 0 tokens per session scan A 45e13eab9d9a

Subscribe to this mod's changes

ai is a command published in the GitHub repository nylas/cli (68 stars, last pushed 14d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,337 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.