KaiAI tutor for anyone

Kai's tool library

Curated, opinionated, tiered. S-tier is what I'd tell a friend to use. A-tier is worth your time. B-tier works but probably isn't the best option.

Marketing · 4

Agents · 23

Perplexity Personal Computer
A
Perplexity's desktop AI agent that automatically decides whether your task runs on your machine or in the cloud — no toggle required.
Included with Perplexity Max ($200/mo); Windows waitlist open
Microsoft Scout
A
Microsoft's always-on 'Autopilot' agent that lives inside your Microsoft 365 stack and keeps working even when you're not prompting it.
Requires GitHub Copilot subscription + Microsoft Frontier enrollment
Hermes Desktop
A
Nous Research's self-improving autonomous agent finally gets a no-terminal GUI — same persistent memory, skills, and multi-platform reach, now wrapped in a native desktop app.
Free (MIT open-source) + Nous Portal paid tiers (Plus/Super/Ultra, pricing undisclosed)
Meta Business Agent
A
Meta's AI agent for WhatsApp, Instagram, and Messenger that handles customer support, product recommendations, and sales so small businesses can punch above their weight 24/7.
Free to start; paid tiers via WhatsApp Business Premium + token-based pricing for enterprises
SIA (Self-Improving AI)
A
An open-source agent framework that closes the self-improvement loop by autonomously rewriting both its own scaffold and model weights — no human tuning required between cycles.
Free (MIT open source)
Adobe Firefly AI Assistant
A
Adobe's conversational creative agent that talks to Photoshop, Premiere, and Illustrator so you don't have to click through all of them yourself.
Requires paid plan — Firefly plans from $9.99/mo; CC Pro required for full access
Hermes Agent
A
A self-improving, model-agnostic CLI agent from Nous Research that now solves MCP's context-bloat problem with BM25-powered Tool Search.
Free (MIT open-source) + Nous Portal subscription for bundled models & tools
Gemini Spark
A
Google's always-on cloud agent that handles multi-step tasks across Gmail, Docs, and third-party apps 24/7 — even when your laptop is shut.
$99.99/mo (Google AI Ultra only)
Robinhood Agentic Trading
A
Connect any third-party AI agent to a sandboxed Robinhood account and let it autonomously trade stocks on your behalf — for better or worse.
Free (requires Robinhood account; Agentic Credit Card requires Robinhood Gold at $5/mo)
TencentDB Agent Memory
A
An open-source, fully local hierarchical memory system for AI agents that cuts token bloat and survives long-horizon sessions — no external API required.
Free (MIT open source)
Webwright
A
Microsoft Research's open-source web agent framework that turns your coding model into a browser-automating power user — by giving it a terminal and Playwright instead of a clicky GUI.
Free (open-source)
LiteLLM Agent Platform
A
Self-hosted Kubernetes infrastructure for running coding agents like Claude Code and Codex in isolated, persistent sandboxes — built for teams who want managed agent infra without giving up data control.
Free (open source, MIT)
Osaurus
A
A native, open-source macOS harness that lets you swap local and cloud AI models freely while keeping your memory, history, and tools locked on your own hardware.
Free (open source, MIT license)
OpenAI Daybreak
A
OpenAI's enterprise cybersecurity platform that uses Codex Security and GPT-5.5 to find, validate, and patch software vulnerabilities before attackers do.
Free first month (ChatGPT Enterprise/Business/Edu via Codex Security); broader Daybreak access requires contacting OpenAI
Claude for Legal
A
Anthropic's legal layer for Claude — 12 practice-area plugins and 20+ MCP connectors that turn the chatbot into a domain-aware legal assistant for law firms and in-house teams.
Included with paid Claude plans (Pro/Team/Enterprise)
Microsoft Legal Agent
A
A Word-native AI agent that does the clause-by-clause contract grunt work so lawyers can focus on actual lawyering.
Included with Microsoft 365 Copilot (enterprise license required)
Stripe Link
A
A digital wallet that lets AI agents spend on your behalf — without ever seeing your actual card number.
Free for consumers; standard Stripe per-transaction fees for merchants
Symphony
A
OpenAI's open-source daemon that turns your Linear board into an always-on coding agent factory — tickets go in, pull requests come out.
Free (open-source)
Skye
A
An agentic iPhone home screen that replaces your static icon grid with AI widgets that proactively surface health, calendar, finance, and local context — without you having to open a single app.
Waitlist / Beta (pricing not yet disclosed)
Manus
S
Autonomous AI agent that actually finishes tasks.
Free tier + $39-$199/mo
Devin
A
Cognition Labs' autonomous coding engineer.
$500/mo
ChatGPT Operator
B
OpenAI's browser agent. Clicks and types on websites for you.
Included with ChatGPT Pro $200/mo
Claude Agent SDK
S
Anthropic's SDK for building your own agents on Claude.
API usage + SDK is free

Writing · 4

Coding · 13

Kimi Code CLI
A
Moonshot AI's open-source terminal coding agent that edits code, runs commands, and dispatches parallel subagents — Claude Code's scrappier, cheaper Chinese rival.
Free (MIT open source) + Kimi Code membership for model access (~$19/mo)
Zero
A
A systems programming language built from the ground up so AI agents can read compiler output, repair errors, and ship native programs — no human translation required.
Free (Open Source, Apache-2.0)
Codex Security
A
OpenAI's agentic AppSec researcher that builds a codebase-specific threat model, validates vulnerabilities in sandboxed environments, and proposes patches — all without drowning you in false positives.
Free first month for ChatGPT Pro/Enterprise/Business/Edu; broader pricing undisclosed
OpenAI Codex
A
OpenAI's cloud-based coding agent that writes, reviews, and ships code in parallel sandboxes—now finding surprising fans in finance teams automating reporting workflows.
Included with ChatGPT Plus ($20/mo) and up; Pay-as-you-go API also available
GitNexus
A
An open-source, MCP-native knowledge graph engine that gives AI coding agents (Cursor, Claude Code, Windsurf) genuine structural awareness of your codebase before they touch a single line.
Free (MIT open source)
Cursor
S
VS Code fork that made AI coding actually work.
Free + $20/mo Pro + $40/mo Business
Claude Code
S
Anthropic's CLI agent. Opus-powered, operates on your repo directly.
Part of Claude Pro/Max/Team plans
Windsurf
A
Codeium's agentic IDE. Cascade agent + strong free tier.
Free + $15/mo Pro
GitHub Copilot
B
Microsoft/GitHub's autocomplete. Deep VS Code + JetBrains integration.
Free (limited) + $10/mo Pro + $19/mo Business
Aider
A
Terminal-based AI pair programmer. Git-aware, model-flexible.
Free (open source) + whatever API you use
Cline
A
Open-source VS Code agent. Reads + writes + runs.
Free (open source) + your API costs
Bolt.new (StackBlitz)
A
Prompt to deployed full-stack app in the browser.
Free + $20-$200/mo
Replit Agent
A
Replit's AI that builds + deploys full apps on their platform.
$10-$25/mo Core/Teams

Voice · 10

Chatbots · 8

Dev Platform · 15

Google Colab CLI
A
Run Python on remote Colab GPUs and TPUs straight from your terminal — no browser, no notebook babysitting required.
Free (CLI is open source) + Colab Pro $11.99/mo or Pro+ $49.99/mo for premium GPUs
Agent Control Specification (ACS)
A
Microsoft's open-source SDK that lets you define portable, auditable policy files controlling exactly what your AI agents can and can't do — across any framework.
Free (MIT open-source)
Microsoft ASSERT
A
Turn plain-English AI behavior specs into a full scored test suite — no hand-coded test cases required.
Free (MIT open source)
Genesis World 1.0
A
Open-source robotics simulation stack that compresses 200+ hours of real-world policy evaluation down to ~30 minutes using GPU-parallelized physics and photorealistic rendering.
Free (Apache 2.0 open source)
Bumblebee
A
A read-only, open-source CLI scanner that tells your security team exactly which developer laptops are sitting on a ticking supply-chain bomb — without triggering it.
Free (open source, Apache 2.0)
Cline SDK
A
The open-source TypeScript agent runtime pulled out of Cline's own guts — now yours to embed in any app, CI pipeline, or platform you want.
Free (Open Source, Apache 2.0)
Qwen-Scope
A
Open-source sparse autoencoder suite that cracks open Qwen LLMs so you can see—and steer—exactly what's happening inside.
Free (open-source)
DeepInfra
A
Blazing-fast, pay-as-you-go inference API for open-source LLMs and multimodal models, now plugged directly into the Hugging Face ecosystem.
Free $5 credit on signup, then pay-as-you-go from $0.06/M tokens
FlashQLA
A
Qwen's open-source GPU kernel library that squeezes 2–3× more speed out of linear attention on NVIDIA Hopper hardware — if you're lucky enough to own one.
Free (MIT License, open-source)
Cursor TypeScript SDK
A
Wire Cursor's full coding-agent runtime into your own apps, scripts, and CI/CD pipelines with a few lines of TypeScript.
Token-based; requires Cursor plan (Pro from $20/mo). Composer 2 at $0.50/$2.50 per M tokens (in/out); fast variant $1.50/$7.50 per M tokens.
OpenRouter
S
One API, every model. Pay-as-you-go, no subscriptions.
Pay per token — model-dependent
Replicate
S
Run any open-source AI model with an API call.
Pay per second of compute
Groq
S
The fastest AI inference in the world. Crazy low latency.
Free tier + pay-as-you-go API
Hugging Face
S
The GitHub of AI. Models, datasets, spaces — all in one.
Free + $9-$20/mo + enterprise
Ollama
S
Run LLMs locally. One-line install, GUI optional.
Free + open source

Other · 2

Productivity · 9

Audio · 8

Research · 9

Data · 4

Education · 4

Video · 10

Image · 7

Meetings · 4

Design · 5