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 Thumbnail

Run My Agents

Run many Claude Code sessions on one repo without clashes

Developer Tools
Artificial Intelligence
GitHub
Visit WebsiteSee on Product HuntGithub ⧉

Hunted byOleksandr DykyiOleksandr Dykyi

Run many Claude Code agents on one repo and stop them overwriting each other. When a session is about to edit a file another session changed in the last 10 minutes, it gets one warning and re-reads the file first. A warning, not a lock. Plus a local board with every Claude Code and Codex session as a card, per-session token limits that step down Opus → Sonnet → Haiku, and a Mac app. Free, MIT, open source. No server, no account, no keys.

Top comment

Hi Product Hunt! I run several Claude Code sessions on the same repo at once, and they kept quietly overwriting each other's edits. Run My Agents fixes that with one PreToolUse hook: before an edit, it checks whether another session on your machine touched that file in the last 10 minutes. If so, the agent gets a short note (which session, which branch, how long ago), re-reads the file and carries on. A second try always goes through, so it never blocks you.

Everything stays in ~/.run-my-agents on your computer: no server, no account, no keys.

It also ships a local board with every Claude Code and Codex session as a card, per-session token limits that step a session down from Opus to Sonnet to Haiku, and a Mac app.

Install in Claude Code:

/plugin marketplace add flisk-sh/run-my-agents

/plugin install run-my-agents@run-my-agents

How many agents do you run at once, and what breaks first?

Comment highlights

I usually have a couple of Claude Code sessions running on the same repo, and the silent overwrite is exactly the failure mode that's bitten me — I only find out when a diff looks wrong. I like that this warns and re-reads instead of locking, a lock would just stall everything. The local-only setup with no account is what sold me, going to try it with the Opus → Sonnet step-down on the background sessions.

About Run My Agents on Product Hunt

“Run many Claude Code sessions on one repo without clashes”

Run My Agents was submitted on Product Hunt and earned 3 upvotes and 3 comments, placing #87 on the daily leaderboard. Run many Claude Code agents on one repo and stop them overwriting each other. When a session is about to edit a file another session changed in the last 10 minutes, it gets one warning and re-reads the file first. A warning, not a lock. Plus a local board with every Claude Code and Codex session as a card, per-session token limits that step down Opus → Sonnet → Haiku, and a Mac app. Free, MIT, open source. No server, no account, no keys.

Run My Agents was featured in Developer Tools (523.1k followers), Artificial Intelligence (483.8k followers) and GitHub (41.5k followers) on Product Hunt. Together, these topics include over 266.6k products, making this a competitive space to launch in.

Who hunted Run My Agents?

Run My Agents was hunted by Oleksandr Dykyi. 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 Run My Agents stacked up against nearby launches in real time? Check out the live launch dashboard for upvote speed charts, proximity comparisons, and more analytics.