Show HN: AI Boost – an MCP for accessing your everyday patterns

Your expertise layer for LLM agents.

Capture what took years to learn. Inject it in seconds. Share it when you're ready.

Get ConnectedRead our Manifesto

Works with

⚡

Claude Code

◎

Cursor

◈

Any MCP Client

Our Commitment

The rules of expertise need to change in the age of AI

Experts are being asked to hand more and more of their knowledge to tools they do not control. We think that trust has to be earned, not assumed. These are not terms of service. They are commitments from one developer to another.

Your context is yours. Forever.

Private boosters are never indexed, sold, surfaced to others, or used to train any model. What you save stays entirely in your account.

Delete anything, any time.

You can remove any booster, any version, or your entire account at any point. Deletion is permanent and immediate. There is no archive.

Transparent internal process.

Pricing changes, policy updates, and platform decisions are announced in advance. We will not change the rules without giving you time to act.

The em-dash

We believe the em-dash is a valid — and useful — punctuation mark, and we will continue to use it regardless of what anyone else says.

Your Personal Library

Your expertise. Captured once. Available everywhere.

Private boosters are yours alone. Capture your expertise from any session. AI Boost embeds it for instant retrieval. Your agent surfaces it the moment context matches.

01

Capture any expertise

Tell your agent what you want to save. It reads your current context, proposes metadata, and creates a private booster in seconds.

02

Indexed and embedded

AI Boost processes the booster for keyword and semantic search so it can be retrieved accurately across all your future sessions.

03

Suggested automatically

When you start a task that matches a saved pattern, your agent surfaces the booster before it begins. You approve, it injects.

See it in action

Save once, available for every future session

Tell your agent what to save. It handles the rest — including reminding you next time.

Step 1 — Saving a pattern

AI Boost Agent

Save our custom auth middleware pattern as a private booster

Thought for 2s

Let me read the current auth middleware file to extract the pattern.

Ran Read file in filesystem

Got it. Based on the file, here are my suggested booster details:

Name: Custom Auth Middleware Pattern

Description: JWT validation, role-based guards, request context injection

Tags:

auth

middleware

jwt

express

typescript

Visibility will be set to private. Confirm to save, or let me know what to change.

NameCustom Auth Middleware Pattern

DescriptionJWT validation, role-based guards, and request context injection for Express services

Tags

auth

middleware

jwt

express

typescript

Version1.0.0

Visibility

Private

Price0 credits (personal use)

Confirmed

Thought for 1s

Ran create_booster in ai-boost

Booster IDa3f2c901-7b44-4d1e-bc82-19e047f6a312

Slugcustom-auth-middleware-pattern

Status

Saved to your library

Your Custom Auth Middleware Pattern booster has been saved to your private library under custom-auth-middleware-pattern. It is only visible to you and will be suggested automatically in future sessions.

Step 2 — Auto-suggested in a new session

AI Boost Agent — New session

Add protected routes to the new payments service

Thought for 2s

Before I start, let me check if there are any relevant boosters in your library.

Ran search_boosters in ai-boost

Found in your library

Custom Auth Middleware Pattern

auth

middleware

jwt

express

typescript

I found your saved auth middleware booster. Would you like me to inject it before I begin?

Yes, inject it

Thought for 1s

Ran get_booster in ai-boost

Booster injected into context

Your auth middleware conventions are loaded. I will follow your JWT validation and role-based guard patterns throughout this task.

The Problem

Every session starts blank

Memory systems capture history, but they cannot curate it. The expertise your agent needs (your conventions, your gotchas, lessons that took years to learn) has nowhere to live between sessions.

Every session starts from scratch

Patterns you use every day — your auth flow, your infra conventions, your API design rules — live in human memory. Your agent has no access to them.

Memory is not curation

Memory plugins record everything, which means they retrieve everything. The signal-to-noise ratio makes them unreliable for injecting the specific, structured knowledge your agent actually needs.

No way to share structured expertise

Domain experts have invaluable knowledge. There is currently no mechanism to package, distribute, and inject that expertise into an LLM at the moment it is needed.

How It Works

How a booster works

01

Save

Tell your agent about a convention, pattern, or workflow. AI Boost packages it as a booster and indexes it using keywords and semantic embeddings.

Private by default; publish when you are ready

→

02

Suggest

On your next session, your agent queries AI Boost automatically before starting a task. If a relevant booster exists (yours or from the community) it is surfaced for your approval.

Proactive, not passive

→

03

Inject

You approve. The full context payload flows directly into the agent's context window. Conventions, patterns, examples: available immediately. No copy-paste, no setup.

Re-injectable at any point in a session

Get Connected

Connect in minutes

AI Boost is an MCP server. Add it to your agent client once and it will be available across every project automatically.

1

Open your Cursor MCP config

Create or edit .cursor/mcp.json in your home directory or project root.

2

Add the AI Boost server entry

{ "mcpServers": { "ai-boost": { "url": "https://mcp.ai-boost.io/mcp", "transport": "streamable-http" } } }

3

Authenticate with GitHub OAuth

On first use Cursor will open a browser tab. Sign in with GitHub, grant access, and you will be redirected back automatically.

4

Top up credits and start using boosters

Visit app.ai-boost.io/billing to add credits, then ask Cursor to search for a booster relevant to your task.

See it in action

Watch the full flow

See it in action

Three messages to go live

Just tell the agent what you want to publish. It handles the rest.

AI Boost Agent

I would like to publish this repo as a booster

Thought for 3s

I'll help you publish this as a booster on the AI Boost Marketplace. Let me start with the first step of the submission flow.

Answer

How would you like to submit the booster content?

Link to a public GitHub repository

Thought for 2s

Let me check the GitHub remote URL for this repo.

Ran Check git remote URL in git

origin [email protected]:AI-Boost-IO/stripe-payment-integration-guide.git (fetch)

origin [email protected]:AI-Boost-IO/stripe-payment-integration-guide.git (push)

Thought for 1s

The repo is AI-Boost-IO/stripe-payment-integration-guide. Let me fetch the GitHub API to auto-suggest details.

Based on the GitHub repo, here are my suggestions — let me know if you'd like to change any of them:

Name: Stripe Payment Integration Guide

Description: A quick-setup guide for Stripe payments

Version: 1.0.0 (no releases found, defaulting)

Branch:

main

Tags:

stripe

payments

python

webhook

subscription

billing

Now for the remaining details:

Answers

What price (in credits) would you like to set for this booster?

0 credits (free)

How should the booster be delivered?

Whole repository

Thought for 2s

Here's a full summary of the booster submission — please confirm before I proceed:

NameStripe Payment Integration Guide

DescriptionA quick-setup guide for Stripe payments

Tags

stripe

payments

python

webhook

subscription

billing

Version1.0.0

Branchmain

Repo URLgithub.com/AI-Boost-IO/stripe-payment-integration-guide

DeliveryWhole repository

Price0 credits (free)

Does everything look correct? Reply "confirmed" to submit, or let me know what to change.

Confirmed

Thought for 1s

Let me check the submission tool schema first.

Ran Submit Booster From Repo in ai-boost

The booster was submitted and approved. Here's the summary:

Booster IDfd904501-cda7-4a9f-aca9-34f539b5fc5a

Version IDff6135a2-0432-4bca-8fc1-232c9f05d0d5

Slugstripe-payment-integration-guide

Status

Approved

The Stripe Payment Integration Guide booster is now live on the AI Boost Marketplace and discoverable under the slug stripe-payment-integration-guide.

Community

Expert human experience is hard to find in the age of AI

LLMs cannot learn from what they have never seen. Your hard-won patterns are exactly what other developers need. Make your private boosters public when you are ready. They surface automatically in every relevant session across the community.

Developers are increasingly surrounded by AI-generated knowledge. Boosters backed by real human experience are a different category entirely. When you share one, you are contributing something the models genuinely cannot replicate.

What sharing looks like

01

Your private booster already exists in your library. You just flip the visibility to public.

02

It goes through automated LLM adversarial review and human approval to ensure quality.

03

It becomes searchable across the community. Any developer whose agent matches it can inject it.

04

You earn AI Boost credits for every injection of your booster — a direct measure of your contribution to the community.

Most Popular Boosters

What the community is using

Browse after connecting

Django on AWS EC2 with Terraform

0 credits

A setup guide for deploying a Dockerised Django app on AWS EC2 using Terraform-managed infrastructure (VPC, EC2, S3, IAM, EIP).

django

aws

terraform

by AI Boost IO

9

14

Django Channels + Celery + Next.js + Terraform/AWS

0 credits

Full-stack skeleton documenting the canonical patterns for a monorepo SaaS backend: Django 5.2 + Strawberry GraphQL + Django Channels 4 + Celery + Next.js 16 + Material UI v9 + Apollo Client 4 + Terraform on AWS EC2. Covers ASGI routing, WebSocket subscriptions with Redis pub/sub, Celery workers and Beat scheduler, Next.js App Router with RSC and Client Components, MUI v9 theming, GraphQL codegen, Docker Compose dev/prod split, and Vercel deployment for the frontend.

django

celery

nextjs

by AI Boost IO

13

Stripe Payment Integration Guide

0 credits

A quick-setup guide for Stripe payments

stripe

payments

python

by AI Boost IO

1

3

Next.js App Router — NextAuth GitHub OAuth

0 credits

Wire NextAuth.js v4 GitHub OAuth into a Next.js 15 App Router project and exchange the GitHub token for a Django API token during sign-in. Includes lib/auth.ts, a thin route handler, TypeScript session augmentation, and implementation docs.

nextjs

nextauth

github-oauth

by AI Boost IO

NextJS Monorepo with Bun and Biome

0 credits

A lightweight monorepo pattern for two independent Next.js 15 apps (public marketing site and authenticated dashboard) managed with Bun, linted and formatted with Biome, and deployed to separate Vercel projects from the same git repository.

nextjs

monorepo

bun

by AI Boost IO

Features

Built for serious agent workflows

Every design decision optimises for two things: the agent gets the right context instantly, and the user stays in control.

Proactive Discovery

Your agent calls the marketplace autonomously before starting any implementation task. No prompting required — it just works, like a reflex.

Semantic + Keyword Search

Boosters are ranked by relevance using embeddings and full-text search. The right booster surfaces based on what your agent is actually trying to do.

Review Pipeline + Signing

Every booster passes automated LLM adversarial review and human approval before going live. Cryptographic signing ensures content integrity at inject time.

Open Knowledge Commons

Share your expertise with the community. Your boosters surface proactively in relevant sessions across every member's workspace — kno

[truncated for AI cost control]