Caw is a web terminal multiplexer for OpenCode, Claude Code, Codex, Copilot, Antigravity, and Pi. It makes it easy to monitor and interact with multiple agent sessions from anywhere, especially on mobile. Besides the terminal multiplexer itself, it includes: - Built-in file browser and editor - Kanban-like board showing all running agents - Push notifications whenever an agent finishes working or requests your input - Git worktrees on demand to parallelize work - Voice mode
The kanban-of-running-agents plus push-when-input-needed combo is exactly the missing supervision layer — running several coding agents, the cost isn't compute, it's ME polling terminals to see who's stuck. Question on the git-worktrees-on-demand: when two agents' worktrees both touch the same file and diverge, does Caw surface the conflict before merge time, or do I find out at the end? That's where parallel agent work usually bites. Congrats — starring the repo.
Push notifications whenever an agent finishes or needs input is the feature that would actually get me to install this, since that is the exact moment I usually miss because I have tabbed away. Curious how it decides an agent needs input versus just being between steps, since a lot of coding agents print a lot of ambiguous output, and a notification system that fires too often just gets muted like any other noisy app.
Also on the git worktrees on demand piece, when you spin up parallel work across multiple worktrees for the same repo, how does Caw handle it if two agents end up touching the same file in different worktrees and you eventually need to merge that work back together. Does it just leave that as a normal git conflict for you to resolve, or is there anything in the kanban view that flags the overlap before it becomes a merge headache.
Multiplexing terminal sessions specifically for AI agent workflows is a smart niche — curious how Caw handles session persistence when an agent's process crashes mid-task, does it auto-reattach or do you lose scrollback? Also wondering if it's local-only or if there's a relay involved, since that matters a lot for anyone running agents against sensitive codebases. Open source is the right call here given how much trust people need to hand a tool that sits between them and their terminal.
About Caw on Product Hunt
“ Open source web terminal multiplexer for AI agents”
Caw launched on Product Hunt on July 23rd, 2026 and earned 75 upvotes and 6 comments, placing #29 on the daily leaderboard. Caw is a web terminal multiplexer for OpenCode, Claude Code, Codex, Copilot, Antigravity, and Pi. It makes it easy to monitor and interact with multiple agent sessions from anywhere, especially on mobile. Besides the terminal multiplexer itself, it includes: - Built-in file browser and editor - Kanban-like board showing all running agents - Push notifications whenever an agent finishes working or requests your input - Git worktrees on demand to parallelize work - Voice mode
Caw was featured in Open Source (68.6k followers), Developer Tools (516.3k followers), GitHub (41.3k followers), Vibe coding (581 followers) and OpenAI Day (8 followers) on Product Hunt. Together, these topics include over 117.8k products, making this a competitive space to launch in.
Who hunted Caw?
Caw was hunted by Manuel Graña. 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 Caw stacked up against nearby launches in real time? Check out the live launch dashboard for upvote speed charts, proximity comparisons, and more analytics.
Manuel Graña
The kanban-of-running-agents plus push-when-input-needed combo is exactly the missing supervision layer — running several coding agents, the cost isn't compute, it's ME polling terminals to see who's stuck. Question on the git-worktrees-on-demand: when two agents' worktrees both touch the same file and diverge, does Caw surface the conflict before merge time, or do I find out at the end? That's where parallel agent work usually bites. Congrats — starring the repo.