Skip to content

Fix my prompt, then keep what works.

Fix your prompt. Then make your AI remember what worked.

Free, 3 checks a day, no signup.

Or start a 7-day free trial for memories

Pro is $19 a month after a 7-day free trial. The trial needs a card. A free plan is there too.

Score it, then fix itExample, for illustration

Before

Fix the failing tests in the payments service.

31

Checked as: agent taskNo folder, no command to run, and no way to tell when it is done.

After

In services/payments, run npm test and fix the failing tests without changing what the code does. Only edit a test if the test itself is wrong, and say why. Done when every test passes and npm run lint is clean. List each file you changed.

86

How it works

You decide what is worth keeping. FixMyPrompt keeps it in a shape your AI can follow later.

Tell it to save once it works

When the AI finally gets something right, say "save how you fixed that to memory". The secret check runs first, then it saves the steps, the commands, how to check the result and what to avoid, not just the prompt you typed.

  • Filed for you. Memories go into a project named after the folder you are working in.Pro
  • Secret check first. Keys and passwords are caught before anything is saved.
  • Versions, with one in use. Save a better way and it becomes a new version. Switch back any time.

Ask for it in plain words

"Use fmp to find how we deploy the staging site." Ask in plain words in any connected tool and your AI reads back the memory that fits. You can also open the Memories page in the app.

  • Search by meaning. Finds the memory even when you word it differently.Pro. The free plan searches exact words.
  • Similar memories. Spot two memories that cover the same job.Pro
  • Projects kept apart. Each working folder has its own memories, so one repo's steps don't leak into another.Pro

Run it like a command

Your AI follows the saved steps. Give a memory a short name and it shows up as a slash command in Claude Code. Anything that changes between runs is a blank it asks you to fill each time.

  • Fill-in blanks. Branch, environment, file name: asked at run time.
  • Tighten. Trims a long saved prompt down to what the AI needs. Works on saved prompts, not saved steps.
  • Merge and undo. Fold two memories into one on the Memories page, and undo it if you change your mind.Pro

How memories work

Works inside Claude Code

Add it with one command, then sign in.

Your link is in Settings in the app. It connects over MCP.

Claude Code

Add FixMyPrompt once and sign in. Your memories become tools and slash commands.

$ claude mcp add --transport http fmp <your link>

Plans

Pro is for people who work with an AI tool every day. Start with a 7-day free trial.

Free

$0

Try FixMyPrompt in one AI tool, free.

Create free account
  • Connect one AI tool (Claude Code, Codex and Cursor)
  • 25 memories and 25 session notes
  • 300 memory reads a month
  • 5 GitHub checks a month
  • Prompt check and fix, paid with credits

1 project, 25 memories, 25 session notes, 300 memory reads a month. Kept 60 days after you last use them.

Pro

$19a month

or $228 a year, 2 months free your first year

For people who use an AI tool every day and are tired of re-explaining.

Start free trial
  • One memory across every AI tool (Claude Code, Codex and Cursor)
  • Checks and fixes system prompts, agent tasks and workflows
  • Tighten cuts the tokens your saved prompts use
  • Versions with undo and an in-use mark

5 app projects plus folder projects, 5,000 memories. Kept 6 months after you last use them. 20,000 credits every month for prompt checks and Tighten. 7 days free, then $19 a month. Monthly credits start with your first paid month. They pause while your own key is on.

Biz

$25a seat a month, 2-seat minimum

or $300 a seat a year, $250 your first year

For a company that wants everyone's AI to reuse what one person already worked out.

Start free trial
  • Everything in Pro
  • Shared across the company, so one person's fix helps everyone
  • Admins approve changes to shared memories
  • Credits pooled across seats

Per seat: 10 app projects plus folder projects, 10,000 memories, pooled across the company. Kept 12 months after you last use them. 20,000 credits a month per seat, shared by the company. 7 days free, then $25 a seat a month.

Enterprise

Custom

From 200 seats. Talk to us.

Talk to us
  • Everything in Biz
  • Project leads for each team's memories
  • Custom seats and limits
  • Talk to us about your setup

From 200 seats. We set it up with you.

Any plan, Free included, can use your own OpenRouter key. AI runs on your key cost no credits. On Pro, the monthly credits pause while a key is on, and the price stays the same.

Need more checks?

One-time credits that never expire. Works on any plan. New here? 3 free prompt checks a day, no account needed.

Checking a single prompt?

The prompt check scores it from 0 to 100 and flags the weak spots. Free, 3 checks a day, no signup.

Questions

Short answers. More on the pricing page.

What is a memory?

Something your AI worked out that you never want it to work out again: the steps, the commands, how to check it worked and what to avoid. You tell it to save one when it finally gets something right.

Isn't that just a prompt library?

A prompt is what you asked. A memory is what the AI learned while answering. It holds the working steps and the check, so the next session can follow them instead of guessing again.

Does the AI look up memories on its own?

Not yet. Today you ask for one ("use fmp to find how we deploy staging"), or run it as a slash command in Claude Code when it has a short name.

Which AI tools work with it?

Claude Code. The free plan connects one tool. Pro connects as many as you use.

What are credits for?

Credits pay for the AI work FixMyPrompt runs for you, such as Tighten and prompt checks beyond the free ones. Pro includes 20,000 every month, starting with your first paid month, and packs top you up without expiring.

Can my team share memories?

Yes, on Biz, at $25 a seat a month, from 2 seats. What one person saves is there for their teammates in their own AI tools and the app. Admins decide what is shared and whether changes need approval. Enterprise, from 200 seats, adds project leads and one page to review it all.