HN Showcase
Back to browse
Khala – let your AI sessions talk to each other, across any LLM

Khala – let your AI sessions talk to each other, across any LLM

by lanakim9410·Jun 23, 2026·1 point·0 comments
Visit ProjectView on HN

AI Analysis

●MidSolve My Problem

MCP handoff between Claude and Codex sessions, but orchestration tools already exist.

Strengths
  • •MCP integration means no code changes to existing AI tool workflows.
  • •Named inbox system provides clear session-to-session routing without manual intervention.
Weaknesses
  • •Invite-only access limits real-world testing and feedback from broader audience.
  • •MCP ecosystem still nascent; only works with tools that support the protocol.
Category
AI/ML
Target Audience

Developers using multiple AI coding tools (Claude, Cursor, Codex)

Similar To

LangGraph · CrewAI · SmythOS

Post Description

I got tired of babysitting context between my own AI sessions and having to copy-paste summaries or update MD files across sessions for different purposes, so I built this.

Every AI session starts with a blank slate. Whatever you built up in the last session, like architecture decisions, debugging history, the reasoning behind every choice, is all gone. So youu re-explain from scratch.

Khala fixes the handoff at the source. Instead of writing a summary file, the sending session packages its full context and delivers it directly to a named inbox. The receiving session picks up exactly where the sender left off. Works across any MCP-compatible tool (Claude, Cursor, Codex, ChatGPT, etc.).

Demo: https://youtube.com/shorts/i8xgbrY_Y0g

Invite-only for now, drop a comment if you want to try it free this month and I'll send you a code.

Similar Projects