AI coding agents are amazing. Until one deletes your database, or leaks your secrets. Antelog stops the disasters before they happen, and shows you everything your AI did: every command, every website, every bit of data it sent. Works with Claude Code, Cursor and Codex. Free.
In April, an AI agent deleted a company's entire production database in seconds. The backups went with it. The developer had only asked it to fix a small error.
That's when I realized: we're giving AI agents the keys to everything, with no brakes.
So I built Antelog.
🛑 It stops disasters. If your AI is about to: • delete your database or backups • wipe your files or overwrite your team's code • show or send your passwords and keys • send your data to a stranger because a web page tricked it
…Antelog blocks it, before it happens.
👀 It shows you everything. Every command your AI ran, every website it visited, every piece of data that left your computer. Written down, and impossible to secretly change.
🧠 Built on research. Antelog is built on LogAct, a research paper published by Meta, which records every AI action before it runs. We added the protection on top.
Works with Claude Code, Cursor, Codex and more. One install. Free.
What's the scariest thing your AI agent has ever tried to do? 👇
Blocking dangerous agent actions before execution is a useful safety feature. Can Antelog distinguish production from staging environments using actual connection details rather than relying on database names, especially when agents execute commands through remote MCP servers?
blocking the rm -rf moment before it happens is huge 🙏 any plans for team policys?
The part that matters most to me is what happens to the audit trail itself — Antelog sees every command, website, and secret passing through, so where does all of that logging actually live? Is it stored locally on the machine, or does any of it leave for your servers? And can the `antelog sent` audit be scoped per project, or is it one global log across everything the agent touches?
As a solo dev, the audit log is the part that interests me most — blocking a delete is great, but the scarier stuff is what an agent does quietly and I only notice a week later. Is the log something you can actually scan after a session to see what files changed and what left the machine, or is it more of a raw trail you dig through once something's already gone wrong?
does it catch stuff that goes thru mcp tools too or only shell commands? half the time our agent hits the db via an mcp server not psql so thats where id actually worry
scariest one for us wasn't even a delete. an agent did git add -A and pushed another session's half done work straight to main lol. we ended up writing our own hook rules for stuff like that, can you add project specific rules in antelog or is the list fixed?
cool launch!! how often does it block stuff i actually wanted, like wiping a local test db on purpose
the april story where a small fix ended with prod and the backups gone is the exact thing that keeps people from giving agents real access
when Antelog blocks a command mid task, does the agent get told why so it can try a safer route??? or does the session jsut stop there???
About Antelog on Product Hunt
“Stops AI coding agents from leaking or destroying your data”
Antelog launched on Product Hunt on November 14th, 2026 and earned 94 upvotes and 24 comments, placing #9 on the daily leaderboard. AI coding agents are amazing. Until one deletes your database, or leaks your secrets. Antelog stops the disasters before they happen, and shows you everything your AI did: every command, every website, every bit of data it sent. Works with Claude Code, Cursor and Codex. Free.
Antelog was featured in Developer Tools (523.3k followers), Artificial Intelligence (484k followers) and Security (3k followers) on Product Hunt. Together, these topics include over 240.8k products, making this a competitive space to launch in.
Who hunted Antelog?
Antelog was hunted by Yash Sarwaiya. 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.
Want to see how Antelog stacked up against nearby launches in real time? Check out the live launch dashboard for upvote speed charts, proximity comparisons, and more analytics.
📌 Hey Product Hunt! I'm Yash, founder of Antelog.
In April, an AI agent deleted a company's entire production database in seconds. The backups went with it. The developer had only asked it to fix a small error.
That's when I realized: we're giving AI agents the keys to everything, with no brakes.
So I built Antelog.
🛑 It stops disasters. If your AI is about to:
• delete your database or backups
• wipe your files or overwrite your team's code
• show or send your passwords and keys
• send your data to a stranger because a web page tricked it
…Antelog blocks it, before it happens.
👀 It shows you everything. Every command your AI ran, every website it visited, every piece of data that left your computer. Written down, and impossible to secretly change.
🧠 Built on research. Antelog is built on LogAct, a research paper published by Meta, which records every AI action before it runs. We added the protection on top.
Works with Claude Code, Cursor, Codex and more. One install. Free.
What's the scariest thing your AI agent has ever tried to do? 👇
I'll be in the comments all day!