Agentmash is an open-source multiplayer AI for teams' coding agents, a shared context layer that tells every agent which files a teammate's agent is changing, so the agents talk to each other and work on their own without overwriting anyone's code. You can switch between tasks running on different models, @mention a teammate, your own agent or a teammate's agent like in Slack, and keep skills, chats and automations in sync. Connect Claude Code, Codex, Antigravity or your own open-source models
We built agentmash so a team can run coding agents on one repo at the same time, with every agent knowing what a teammate's agent is changing and the agents sorting it out between themselves.
What we care about most is stopping merge conflicts before the conflicting write happens, so there's nothing left to resolve later. In our benchmarks on the same team, models and tasks, agents caught 98.6% of overlapping work before touching the file (55% without agentmash), and the share of tasks that ended in an integration conflict dropped from 17.5% to 4.7%. Each developer also got 17.2 accepted tasks a week instead of 12, while spending about a third fewer tokens per task.
We'd love to hear where your agents still get in each other's way.
I run a few agent sessions at once on one repo and they don't talk to each other, one main session collects their questions and brings them to me as one list. When agentmash agents settle an overlap between themselves, does the owner see what they agreed on, or just the end result?
congrats on the launch! 🚀🚀
mine are in separate worktrees, one branch each, so two agents never write the same file at the same moment. the collision just shows up later when the branches meet, which is worse because nobody is watching by then.
does it see across branches or only inside one checkout??
I run a few agent sessions at once on one repo and they don't talk to each other, one main session collects their questions and brings them to me as one list. When agentmash agents settle an overlap between themselves, does the owner see what they agreed on, or just the end result?
congrats on the launch damir. 55% to 98.6% is a big jump. in my case most fights between agents are not the same file but the same idea, two of them fixing one bug in diffrent places ) could claims work on a task level too, not only on names?
The claim-before-you-edit part is what sells this for me — most setups only tell you at merge time, when it's already a mess. When I run two agents on the same repo, the painful case is a shared type changing under the other agent, so the name-level warnings for JS/TS sound right. Curious what happens to a claim if an agent dies mid-task or just wanders off — does it expire on its own, or does a teammate have to clear it?
Love the idea! Having multiple AI agents working together sounds exciting until they start stepping on each other's changes. Solving this at the coordination level is a really smart approach. @iskakov
Hey, great project! One question - do I have to buy subscriptions separately (ex: directly from Claude) or it is already included in your plan?
question for everyone here, which level do you ship with day to day? and if you run more than one agent at a time, what breaks first for you
the easiest way we've found to explain who agentmash is for is splitting ai coding into three levels. level 1 is ai helping you write code (cursor, antigravity), level 2 is where you don't write it but still read and run it (claude code, codex), and level 3 is where you never see the code at all (lovable, bolt). agentmash is for level 2, the moment you start running several agents on one repo, so each agent sees which files the others are changing and gets a warning before it touches one of them
About agentmash on Product Hunt
“open-source multiplayer AI for teams' coding agents”
agentmash launched on Product Hunt on November 1st, 2026 and earned 142 upvotes and 19 comments, placing #6 on the daily leaderboard. Agentmash is an open-source multiplayer AI for teams' coding agents, a shared context layer that tells every agent which files a teammate's agent is changing, so the agents talk to each other and work on their own without overwriting anyone's code. You can switch between tasks running on different models, @mention a teammate, your own agent or a teammate's agent like in Slack, and keep skills, chats and automations in sync. Connect Claude Code, Codex, Antigravity or your own open-source models
agentmash was featured in Developer Tools (522.3k followers), Artificial Intelligence (482.7k followers), GitHub (41.5k followers) and Tech (635.9k followers) on Product Hunt. Together, these topics include over 430.8k products, making this a competitive space to launch in.
Who hunted agentmash?
agentmash was hunted by Damir Iskakov. 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 agentmash stacked up against nearby launches in real time? Check out the live launch dashboard for upvote speed charts, proximity comparisons, and more analytics.
Damir Iskakov
Hey Product Hunt, I'm Damir, CTO of agentmash.
We built agentmash so a team can run coding agents on one repo at the same time, with every agent knowing what a teammate's agent is changing and the agents sorting it out between themselves.
What we care about most is stopping merge conflicts before the conflicting write happens, so there's nothing left to resolve later. In our benchmarks on the same team, models and tasks, agents caught 98.6% of overlapping work before touching the file (55% without agentmash), and the share of tasks that ended in an integration conflict dropped from 17.5% to 4.7%. Each developer also got 17.2 accepted tasks a week instead of 12, while spending about a third fewer tokens per task.
We'd love to hear where your agents still get in each other's way.