waynesutton/opensync

Cloud-synced dashboards for OpenCode and Claude Code. Track sessions, search with semantic lookup, export eval datasets.

What it solves

OpenSync provides a centralized dashboard to track and analyze AI coding sessions across different AI coding assistants (such as Claude Code, Cursor, and OpenCode). It solves the problem of fragmented session history and lack of visibility into token spend, tool usage, and session activity across multiple tools.

How it works

Users install sync plugins for their specific AI coding tool. These plugins sync session data in real time to a cloud-synced dashboard. The system uses Convex for the backend and real-time sync, WorkOS for authentication, and OpenAI for embeddings to enable semantic search across sessions.

Who it’s for

Developers using AI coding agents and assistants who want to monitor their usage, track costs, and build evaluation datasets from their actual work sessions.

Highlights

  • Multi-tool support: Syncs data from OpenCode, Claude Code, Codex, Cursor, Factory Droid, and Pi.
  • Evaluation dataset creation: Allows users to tag sessions as eval-ready and export them in formats like DeepEval JSON and OpenAI Evals JSONL.
  • Analytics and Search: Features token charts, cost tracking, and full-text, semantic, and hybrid search for session history.
  • Self-hosting: Supports both a hosted version and self-hosted deployment via Convex, WorkOS, and OpenAI.

Related

  • Project
    f-is-h/Usage4Claude

    A macOS menu bar app that tracks subscription usage limits for Claude and Codex, providing real-time quota monitoring and notifications.

  • Project
    chalk-lab/Mooncake.jl

    A high-performance automatic differentiation package for Julia that supports mutation and leverages optimized intermediate representations for efficient derivative code.

  • Project
    PersiaML/PERSIA

    A PyTorch-based parallel training system designed to scale deep learning recommendation models up to 100 trillion parameters on commodity hardware.

  • Project
    deel-ai/puncc

    A Python library for predictive uncertainty calibration and conformalization, providing rigorous uncertainty estimations for any machine learning model across various tasks.