Hey HN, we're Nars & Nishant, founders of Skillsync. Skillsync lets you move your AI chats across every coding agent. Most of our work exists as conversations, currently scattered across agents. Though stored locally, these conversations use different formats, so you cannot switch without starting over. Skillsync acts as a universal converter, moving the entire session, including messages, reasoning, and tool calls, so you can pick up where you left off.

Skillsync collects all your sessions in one place and makes them searchable. It breaks down what each session is carrying, including loaded skills, making stale context easy to spot. You can create shared workspaces to sync sessions across your team. Everything runs locally except when you share to workspaces. The core is an open-source Rust engine called txcript. It translates a session from one agent's on-disk format into another's, mapping conversation, reasoning, and tool history. Think ffmpeg or pandoc, but for agent sessions.

On top is a local-first desktop app that surfaces sessions in one place with a readable UI. Skills and memory are stored as portable markdown you own, exposed to any agent over MCP. Sessions and translation run locally; only what you share leaves. It's surprising how locked-in people already are. Once sessions are portable, they become something you can build on. Before Skillsync, we built an open-source payment orchestrator (30k+ GitHub stars). We came into YC with a different idea, but saw the same problem: your context is locked into whatever agent you start with.

People use Skillsync to move sessions between Claude Code, Codex, and Cursor mid-task, hand browser chats to coding agents, and share research sessions with teams. Available as a Mac app, CLI, and MCP. Would love your feedback!