This product was not featured by Product Hunt yet. It will not be visible on their landing page and won't be ranked (cannot win product of the day regardless of upvotes).
Product upvotes vs the next 3
Waiting for data. Loading
Product comments vs the next 3
Waiting for data. Loading
Product upvote speed vs the next 3
Waiting for data. Loading
Product upvotes and comments
Waiting for data. Loading
Product vs the next 3
Loading
Dear User
Performance reviews for your AI agent
Good working relationships have reviews and 1:1s. The one with our AI agent doesn't. Dear User reads and understands your Claude Code setup and suggests relevant improvements on how to better collaborate with your agent. Three skills: • /collab — performance review (working relationship) • /security — background check (12 credential types) • /health — wellbeing check (drift you can't see) Calibrated on 988 public setups. Open source. Local-first. MIT.
Hey Product Hunt 👋
I'm Jarl, solo founder of Dear User.
At work we have 1:1s and performance reviews with the people we work with. We take this for granted, but when it comes to the AI agent we spend so much time with, nothing similar exists.
This year you'll spend more hours with your AI agent than with most people in your life. I built Dear User to make those hours count and to have a great working relationship with my agent.
Dear User is an open-source MCP server that reads your full Claude Code setup — CLAUDE.md, AGENTS.md, hooks, skills, memory, scheduled tasks, MCP servers — and writes you a letter back. In your agent's voice. About how the two of you are actually working together.
Three skills, mapped to HR rituals you'll recognize:
• /collab — the performance review. Scores 7 categories (role clarity, communication, autonomy balance, quality standards, memory health, system maturity, coverage). Surfaces the corrections you keep making by hand that could just be a rule. Calibrated against 988 public Claude Code setups (median 32/100).
• /security — the background check. Scans for leaked credentials in 12 categories (OpenAI, Anthropic, GitHub, AWS, Stripe, Slack, Google, Supabase, Vercel, private keys, env secrets, bearer tokens). Pulls real CVEs from Dependabot, npm audit, Supabase RLS, Vercel.
• /health — the wellbeing check. Finds skills nothing calls, scheduled jobs writing to files nothing reads, contradictory rules that don't share keywords. The drift you can't see in the chat.
Everything runs locally. Your data never leaves your machine unless you explicitly share a Wrapped card. No telemetry, no cloud, no API keys required.
Install:
claude mcp add --scope user dearuser -- npx -y @poisedhq/dearuser-mcp@latest
Then run /collab, /security, or /health in any Claude Code session.
If you try it, run `dearuser feedback "..."` from your terminal — it lands in my inbox and I read every one.
Source: github.com/bleedmode/dearuser
About Dear User on Product Hunt
“Performance reviews for your AI agent”
Dear User was submitted on Product Hunt and earned 3 upvotes and 1 comments, placing #130 on the daily leaderboard. Good working relationships have reviews and 1:1s. The one with our AI agent doesn't. Dear User reads and understands your Claude Code setup and suggests relevant improvements on how to better collaborate with your agent. Three skills: • /collab — performance review (working relationship) • /security — background check (12 credential types) • /health — wellbeing check (drift you can't see) Calibrated on 988 public setups. Open source. Local-first. MIT.
On the analytics side, Dear User competes within Open Source, Developer Tools, GitHub and Vibe coding — topics that collectively have 621.7k followers on Product Hunt. The dashboard above tracks how Dear User performed against the three products that launched closest to it on the same day.
Who hunted Dear User?
Dear User was hunted by Jarl Rosenlykke. A “hunter” on Product Hunt is the community member who submits a product to the platform — uploading the images, the link, and tagging the makers behind it. Hunters typically write the first comment explaining why a product is worth attention, and their followers are notified the moment they post. Around 79% of featured launches on Product Hunt are self-hunted by their makers, but a well-known hunter still acts as a signal of quality to the rest of the community. See the full all-time top hunters leaderboard to discover who is shaping the Product Hunt ecosystem.
For a complete overview of Dear User including community comment highlights and product details, visit the product overview.
Jarl Rosenlykke