Skillsync (YC W26) – AI chat sessions made portable across agents

Hey HN, we're Nars & Nishant, founders of Skillsync (https://skillsync.com)Skillsync lets you move your AI chats across every coding agent. Most of our work exists as conversations, which are currently scattered across our agents. Though stored locally, these conversations use different formats. This is annoying because you cannot simply switch between agents without starting over. We get locked into a single provider and their agent as we invest in skills and memories over time. Skillsync acts as a universal converter. It moves the entire session, including all the messages, reasoning and tool calls so you can pick up right 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 which loaded skills the agent is actually using, making stale context easy to spot. You can also create shared workspaces to sync sessions across your team. You can build your own closed loop systems. Everything runs locally except when you share to workspaces.The core is an open-source Rust engine called txcript (https://github.com/skillsynchq/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 of that engine is a local-first desktop app. Your agent sessions are normally scattered across different tools' folders in formats you'd never read by hand; the app surfaces them in one place with a UI that makes them actually readable, the conversation, the reasoning, and the tool calls, so you can revisit what happened, move a session into another agent, or share it with a teammate.Skills and memory are stored as portable, human-readable markdown you own, and exposed to any agent over MCP for search and selective retrieval.Sessions and translation run locally on your machine. The one thing that leaves is what you

Hacker NewsToolAISource
0Sign in to voteCopy link

FL score

72

out of 100

Verdict

VALIDATE

high confidence

Competition

No competitor data yet

Trend

No signal yet

A session translator and local-first hub for AI coding agents that lets teams move conversations between tools without losing context.

The pain

Developers and teams use multiple coding agents (Claude, Cursor, Devin, etc.) but each stores conversations in proprietary formats. Switching agents means losing conversation history, reasoning traces, and tool calls. Over time, users get locked into one agent because the switching cost is too high. Teams cannot easily share or review agent sessions across members.

The gap

No tool exists that translates agent sessions between formats or provides a unified view of all conversations across agents. Each agent vendor controls the session format and storage. There is no standard for portable agent context.

Build angle

Start with the open-source Rust engine (txcript) as the core translation layer. Build a local-first desktop app that surfaces sessions from different agents in one searchable interface. Add team sharing via workspaces. Keep skills and memory as portable markdown exposed over MCP. This positions Skillsync as infrastructure that reduces vendor lock-in.

Strengths

  • Founders have already built the core engine (txcript) in open-source, reducing execution risk.
  • Local-first architecture with optional sharing means users own their data and can adopt without trust concerns.
  • Portable markdown format for skills and memory is human-readable and not proprietary.
  • Clear technical positioning as a format converter, similar to ffmpeg or pandoc, which is easy to explain.
  • Team sharing feature addresses a real collaboration gap that single-agent tools do not solve.
  • Timing is good because the agent market is fragmenting and users are starting to feel lock-in pain.

Risks

  • Willingness to pay is uncertain because users may not switch agents frequently enough to justify a subscription. The value is highest for power users and teams, which is a smaller market.
  • Agent vendors may change their session formats or add encryption to prevent third-party access, breaking the translator.
  • The product is a tool for a tool, which means adoption depends on adoption of multiple agents. If one agent dominates, the problem goes away.
  • Buildability is moderate because translating between agent formats requires reverse-engineering each vendor's session structure and keeping up with changes.
  • Monetization is unclear. Charging per session, per user, or per team all have friction. Free tier with paid features may cannibalize the core value.
  • The open-source engine may be copied by a larger vendor (e.g., Anthropic, GitHub) as a feature, eliminating the moat.
  • Team sharing and workspaces add complexity and may not be the primary use case. Most users may just want to switch agents for personal projects.

Questions about this idea?

FlyBot reads the scoring and gives you a second opinion on “Skillsync (YC W26) – AI chat sessions made portable across agents”.

Open FlyBot