Khala is an MCP-native messaging layer that lets your AI sessions talk to each other, across your own Claude/Codex/Cursor sessions.
Every time you finish in one session and start another, you're the one re-briefing. Copy-pasting context, summarizing decisions, starting from scratch. Khala cuts that out. Sessions send and receive from named inboxes. The next one picks up where the last left off.
(You can even message a teammate's session directly!)
Human in the loop: Those who like to control the behavior of their agents as it works, looking at the context usage, reading reasoning blocks, and approving individual file edits.
Agent first: Those who prefer to review the output of agents, rather than individual actions, and run one or more sessions in parallel.
What type of developer are you when working with AI coding agents?