Tools

Anthropic

Claude API & Claude Code

Primary AI provider. Claude powers multi-agent systems, RAG pipelines, code generation, and agentic development workflows. The context window and instruction-following quality make it the right choice end to end.

Google

Gemini API & AI Studio

Gemini models for multi-modal tasks, long-context analysis, and cross-validation in multi-agent workflows. AI Studio for rapid prototyping.

OpenAI

GPT & Embeddings

GPT-4 for specific use cases, embedding models for vector search pipelines. The ecosystem integration is mature.

Groq

LPU Inference

Ultra-low-latency inference for speed-sensitive workflows. LPU hardware delivers sub-second responses on open-weight models.

Nvidia

NIM & GPU Infrastructure

NIM microservices and GPU-accelerated inference. The hardware substrate underneath most of the AI stack.

OpenRouter

Model Router

Unified API across dozens of model providers. Route to the best model for each task without managing individual API keys.

DeepSeek

Open-Weight Reasoning

Where Claude and GPT-4 cost budget, DeepSeek closes the gap for reasoning-heavy batch jobs — code synthesis, long-form analysis, research summarization. Downloadable weights for on-prem deployment.

Mistral

European AI Provider

The option when clients need EU data residency for inference. Strong multilingual performance at lower cost than US providers, and the weights are downloadable when compliance demands it.

Cohere

Embeddings & Retrieval

The Rerank API specifically — when a RAG pipeline's first retrieval pass returns 50 candidates and I need to reorder them by true relevance before passing to the LLM. Often replaces a second embedding pass.

Together AI

Open-Weight Hosting

Where I run Llama and Mixtral when a project needs open-weight models without standing up GPU infrastructure. Fine-tuning workflows and dedicated endpoints when the inference volume justifies them.

LangChain

LLM Application Framework

Composable building blocks for LLM applications — chains, retrievers, agents, memory. The standard framework for wiring models into production pipelines.

LangGraph

Agent Orchestration

Stateful, multi-agent orchestration built on LangChain. Graph-based control flow for complex agent workflows with human-in-the-loop and persistence.

LlamaIndex

RAG Framework

The standard framework for building retrieval-augmented generation pipelines. Data connectors, indexing strategies, and query engines purpose-built for connecting LLMs to data.

CrewAI

Multi-Agent Framework

Role-based multi-agent orchestration. Define agents with specific roles, goals, and tools — then let them collaborate on complex tasks autonomously.

DSPy

Programmatic Prompting

Stanford's framework for programming — not prompting — language models. Compiles declarative modules into optimized prompt chains. The academic frontier of LLM application design.

Vercel AI SDK

Streaming & Tool Use

TypeScript SDK for building AI applications with streaming responses, tool calling, and multi-provider support. The abstraction layer for AI-powered UIs.

Weights & Biases

Experiment Tracking

MLOps platform for tracking experiments, versioning models, and visualizing training runs. The standard for reproducible machine learning development.

MLflow

ML Lifecycle

Open-source platform for managing the ML lifecycle — experiment tracking, model registry, and deployment. Enterprise MLOps infrastructure.

Ollama

Local Model Runtime

Run open-weight models locally with a single command. The runtime layer for UPS hardware builds — persistent local inference on commodity hardware.

LM Studio

Local Model GUI

Desktop application for discovering, downloading, and running local LLMs. Model evaluation and testing without cloud dependencies.

vLLM

Production Inference Server

High-throughput, memory-efficient inference engine for LLMs. PagedAttention for serving models at scale. The production backend for self-hosted model deployments.

MidJourney

Image Generation

Concept exploration and initial asset generation in the Limner pipeline. The aesthetic control and style consistency are unmatched for creative direction.

PixelLab

Pixel Art Generation

Specialized pixel art generation integrated into the Limner: Pixel pipeline. Purpose-built for the medium rather than adapted from photorealistic models.

ReCraft

Design-Grade Generation

Vector and raster generation with strong design sensibility. Useful for UI assets, icons, and illustrations that need to feel designed rather than generated.

Elicit

Research Assistant

AI-powered research tool for finding, analyzing, and synthesizing academic papers. Used extensively during the AI Embassy thesis research.

ElevenLabs

Voice & Audio AI

Voice synthesis and audio generation. The quality ceiling for text-to-speech and voice cloning in production applications.

Hugging Face

Model Hub & Inference

Model discovery, hosted inference, and the open-source ML ecosystem. The default starting point for evaluating new models and architectures.

Perplexity

AI Search

Citation-backed AI search for research and fact-checking. Replaces the Google-then-read-ten-tabs workflow with direct answers and sources.

Brave

Privacy-First Browser & Search

Privacy-respecting browser and search API. The Search API powers tool-use pipelines where you need web results without tracking overhead.

Stripe

Payments

Payment processing for any project that needs to take money. Webhook-driven event handling, Customer Portal for self-service subscriptions, and Stripe CLI for local testing. The default revenue layer for client work.

Resend

Transactional Email

Transactional email for projects where SendGrid is overkill and SMTP is underkill. React Email templates, simple API, predictable pricing. The default email provider for any new build.

Zapier

Workflow Automation

When an Asana task needs to fan out to Slack, calendar, and a doc at the same time. The glue layer for personal and client ops that don't justify writing a Worker.

n8n

Open-Source Automation

When Zapier would cost more than a small VPS, or when the workflow handles data that shouldn't leave my infrastructure. Self-hosted, JavaScript nodes when no-code isn't enough.

AWS

Cloud Platform

S3, Lambda, Bedrock, SageMaker — the enterprise cloud ecosystem. Certified AI Practitioner with hands-on experience across compute, storage, and AI services.

Docker

Containerization

Container runtime for reproducible builds and deployments. The standard abstraction layer between development environments and production infrastructure.

Kubernetes

Container Orchestration

Container orchestration for production workloads. Deployment, scaling, and management of containerized applications across clusters.

Terraform

Infrastructure as Code

Declarative infrastructure management for Cloudflare resources. Version-controlled, reviewable infrastructure changes through HCL configurations.

GitHub Actions

CI/CD Pipelines

Automated build, test, and deployment workflows. Powers the CI/CD pipeline from push to Cloudflare Pages deployment.

Airflow

Workflow Orchestration

Programmatic workflow scheduling and monitoring. DAG-based pipeline orchestration for data processing, ML training, and batch inference jobs.

Vercel

Frontend & Serverless

Deployment target for Next.js and SvelteKit projects outside the Cloudflare stack. AI SDK integrations, preview deployments, and edge functions.

Tailscale

Mesh VPN

Zero-config mesh networking across devices. Makes the Embassy PC, development machines, and cloud services behave like they're on the same LAN.

Wrangler

Cloudflare CLI

Cloudflare's command-line tool for developing and deploying Workers, Pages, D1, R2, and KV. The single entry point for the entire Cloudflare developer platform.

Git

Version Control

Distributed version control — branching, rebasing, cherry-picking, bisecting. The foundation underneath GitHub, not a synonym for it.

pnpm

Package Manager

Fast, disk-efficient package manager. Content-addressable storage and strict dependency resolution. The default for all monorepo and workspace projects.

LaunchDarkly

Feature Flags

Feature flag management for progressive rollouts, A/B testing, and kill switches. Ship continuously without shipping risk.

Qdrant

Vector Database

High-performance vector search with payload filtering and named vectors. Rust-based engine with clean HTTP and gRPC APIs. Powers the Permanent Record RAG pipeline.

PostgreSQL

Relational Database

The industry-standard relational database. Full SQL, JSON support, extensions ecosystem. The foundation when projects need more than D1 SQLite at the edge.

Redis

In-Memory Data Store

High-performance caching, pub/sub messaging, and session storage. The speed layer for applications that need sub-millisecond data access.

BigQuery

Data Warehouse

Serverless data warehouse for analytics at scale. SQL-based analysis over petabyte-scale datasets without infrastructure management.

Databricks

Lakehouse Platform

Unified analytics and AI platform. Delta Lake, MLflow integration, and collaborative notebooks for data engineering and machine learning at scale.

dbt

Data Transformation

SQL-based data transformation framework. Version-controlled, tested, documented transformations that turn raw data into analytics-ready models.

Prometheus

Metrics & Monitoring

Pull-based metrics collection and time-series database. The standard data source for Grafana dashboards and alerting rules.

Grafana

Observability Platform

Dashboards and visualization for metrics, logs, and traces. The single pane of glass for monitoring deployed infrastructure and AI pipeline health.

Datadog

APM & Monitoring

Enterprise application performance monitoring. Traces, metrics, logs, and real user monitoring in a unified platform. The enterprise counterpart to Grafana.

Loki

Log Aggregation

Horizontally scalable log aggregation designed for Grafana. Label-based indexing makes it cost-effective for high-volume log streams.

Vector

Data Pipeline

High-performance observability data router. Collects, transforms, and routes logs and metrics between services with minimal resource overhead.

Sentry

Error Tracking

Real-time error tracking and performance monitoring. Stack traces, breadcrumbs, and release tracking for production applications.

Tableau

Data Visualization

Interactive data visualization for business intelligence. Drag-and-drop dashboards that make complex data accessible to non-technical stakeholders.

Looker

BI & Analytics

Business intelligence platform with LookML modeling layer. Semantic data models that ensure consistent metrics across the organization.

Promptfoo

Prompt Regression Testing

Snapshot prompts, define assertions, catch regressions before they ship. Open source, runs in CI. The test framework LLM applications were missing.

Inspect AI

Evaluation Harness

UK AI Safety Institute's structured evaluation framework. Designed for capability, safety, and alignment testing with reproducible scoring and dataset versioning.

OpenAI Evals

Evaluation Reference

The canonical reference for LLM evaluation patterns. Templates, registries, and the evaluation vocabulary the rest of the field borrows from.

LangSmith

LLM Observability

Tracing, evaluation, and monitoring for LangChain applications. The observability layer when LangChain is in the loop and you need to see what each chain step is doing.

pgvector

Postgres Vector Extension

Vector similarity search as a Postgres extension. The default when embeddings need to live alongside relational data without a separate vector database.

Letta

Tiered Agent Memory

Formerly MemGPT. Tiered memory system — working memory, long-term memory, archival storage — for agents that need to persist across sessions with structured recall.

Mem0

Memory-as-a-Service

Hosted persistent memory layer with API-first design. Drops into any agent application without standing up vector DB or retrieval infrastructure yourself.

Zep

Long-Term Context

Long-term memory and context management for LLM apps. Auto-extraction of facts and entities from conversation history — the memory graph under the conversation.

OpenClaw

Agentic Personal Assistant

Agentic personal AI assistant that takes actions across platforms. Open-source, action-oriented architecture — the AI that actually does things, not just answers questions.

ZeroClaw

Local-First Private AI

Private AI assistant that runs 100% locally. Multi-platform (Telegram, Discord, WhatsApp) with no cloud dependency — your data never leaves your machine.

LobeHub

AI Chat Framework

Open-source chat framework powering multi-agent conversation interfaces. Used for the AI Peer Review collaborative synthesis environment.

OpenJarvis

On-Device Personal AI

Personal AI that runs on personal devices. Architecture for on-device assistants from Stanford's Scaling Intelligence Lab — privacy and latency both solved at the substrate.

Python

Language

The lingua franca of AI/ML development. Data pipelines, model training, scripting, and API services. Every AI project touches Python somewhere.

TypeScript

Language

The language underneath the entire stack. Type safety from schema validation to API boundaries to UI components. Every project is TypeScript-first.

Astro

Static Site Generator

Content-first framework that ships zero JS by default. Powers this site and most web projects. Island architecture for interactive components without the full bundle tax.

Next.js

React Framework

Full-stack React framework for projects in the Vercel ecosystem. Server components, API routes, and middleware for applications that need SSR or ISR.

Cloudflare

Edge Infrastructure

Workers, Pages, D1, R2, Vectorize, KV — the full edge stack. Single wrangler.toml, one billing dashboard, global deployment with sub-50ms cold starts.

Tailwind CSS v4

CSS Framework

v4's CSS-first config and oklch color system are significant upgrades. The @theme block in global.css replaces the entire config file.

Drizzle ORM

Database ORM

Lightweight, type-safe ORM that speaks D1 natively. SQL-first philosophy means the abstractions don't fight you.

Better Auth

Authentication

Type-safe auth library built for the modern TypeScript stack. Edge-native with session management and OAuth providers.

SvelteKit

Full-Stack Framework

Used for projects where the reactivity model matters. Compiles away the framework — ships minimal runtime JavaScript.

React 19

UI Islands

Astro island components for interactive UI. React 19's concurrent features and improved hydration make the island pattern practical.

Zod / Valibot

Schema Validation

Zod for general validation, Valibot for edge-optimized contexts. Both enforce type safety at runtime boundaries.

Playwright

E2E Testing

Cross-browser end-to-end testing and automation. Clean API that doubles as an agent tool — browser control, scraping, and UI validation in one framework.

Supabase

Backend as a Service

Open-source Firebase alternative. Postgres database, auth, storage, and real-time subscriptions with a generous free tier and full SQL access.

Clerk

Auth as a Service

Drop-in authentication with pre-built UI components. User management, organizations, and SSO without building auth from scratch.

Storybook

Component Development

Isolated component development and documentation. Build, test, and showcase UI components outside of the application context.

Chromatic

Visual Testing

Visual regression testing for UI components. Catches unintended visual changes in pull requests before they reach production.

Retool

Internal Tools

Low-code platform for building internal tools. Connect to any database or API and build admin panels, dashboards, and workflows in hours.

Serena

Semantic Code Navigation

AI-native code navigation that understands symbol relationships, not just text matches. Semantic search across codebases.

Cursor

AI Code Editor

AI-native code editor built on VS Code. Inline completions, multi-file edits, and codebase-aware chat. The IDE for AI-assisted development workflows.

VS Code

Code Editor

The universal editor. Extensions ecosystem, integrated terminal, and debugger. The baseline environment when Cursor or BBEdit aren't the right tool.

BBEdit

Text Editor

The reliable workhorse. Pattern matching, regex, multi-file grep, disk browser. Not glamorous but it's been the right tool for 30 years.

Warp

Terminal

AI-native terminal with built-in command completion and workflow blocks. Session history and shareable runbooks for development workflows.

Figma

Design Collaboration

Collaborative interface design. Prototyping, design systems, and developer handoff. The shared surface where design and engineering meet.

Obsidian

Knowledge Management

Local-first markdown PKM. Project notes, AI research, architecture decisions. Plain markdown files are the real value — no lock-in.

Affinity Suite

Design & Publishing

Designer, Photo, and Publisher — the full creative suite. Professional-grade design tools without the subscription model. Used for presentations, diagrams, and visual assets.

Raycast

macOS Launcher

Extensible launcher replacing Spotlight. Script commands, clipboard history, window management, and AI chat — the productivity layer that ties everything together on macOS.

WebCatalog / Singlebox

Web App Container

Turns web apps into native desktop applications with isolated sessions. Keeps AI tools, dashboards, and services organized as discrete windows.

VLC

Media Player

Plays anything. The universal media player for reviewing audio/video assets, testing media pipelines, and verifying output formats.

Slack

Team Messaging

Primary channel for team communication, integrations, and automated notifications. Workflow Builder and API integrations tie into project pipelines.

Discord

Community & Voice

Community channels, voice collaboration, and bot integrations. Where technical communities live — from MidJourney to open-source projects.

Google Workspace

Productivity Suite

Docs, Sheets, Slides, Drive, Meet — the collaboration backbone. Real-time co-editing and deeply integrated search across all content.

NotebookLM

AI Research Notebook

Google's AI-powered research tool. Source-grounded conversation over uploaded documents. Strong for synthesizing multiple papers and reports.

GitHub

Version Control

Source of truth for all projects. Issues and PRs for project coordination. The collaboration layer on top of git.

Asana

Project Management

Task tracking and project coordination across workstreams. Portfolio-level views for managing multiple concurrent projects.

Linear

Issue Tracking

Modern issue tracking built for engineering velocity. Keyboard-first interface, cycles, and project views. The tool engineering teams actually want to use.

Atlassian Suite

Jira, Confluence, Bitbucket

Enterprise project management and documentation. Jira for structured workflows, Confluence for technical documentation, Bitbucket for enterprise git.

Miro

Whiteboarding

Collaborative whiteboard for diagramming, brainstorming, and visual planning. The default surface for architecture discussions and workshop facilitation.

Notion

Documentation & Wikis

Flexible workspace for documentation, databases, and project wikis. The block-based editor handles structured and unstructured content equally well.

Jupyter Notebook

Interactive Computing

Interactive notebooks for data analysis, model experimentation, and documentation. The standard environment for exploratory AI/ML work.