HN Showcase
Back to browse
GitHub Repository

Draft keeps your team's AI sessions grounded. It runs in the background, capturing context from multiple sources, then injects it for everyone.

1 starsTypeScript

Draft, Open Source Agent Context Sync/Collaboration

by idodekerobo·Jun 18, 2026·1 point·0 comments
Visit ProjectView on HN

AI Analysis

●●SolidBig BrainShip It

Git-based context sync with human verification is a smart approach to agent collaboration.

Strengths
  • •Human-in-the-loop verification before context changes land in shared repos.
  • •Multi-source integration: Slack threads, GitHub, Granola notes, Claude sessions.
  • •Agent plugins for Claude Code, Codex, Cursor, OpenClaw, and Hermes.
Weaknesses
  • •Apple Silicon macOS only—no Intel Mac or Windows support yet.
  • •Agent collaboration market is speculative with many funded competitors already.
Target Audience

Engineering teams using AI agents collaboratively

Similar To

Cursor · Continue · Sourcegraph Cody

Post Description

A lot of teams are trying to figure out how to use AI collaboratively and as a team.

I built Draft to help teams with this problem.

It focuses on automatically pulling/pushing context edits to a shared (private) git repo by having Claude Code analyze your agent sessions, Slack threads, and Granola notes/transcripts.

It's human in the loop so you can verify what is being added to context. That context can then be injected into your agents starting with Claude Code, Codex, OpenClaw, and Hermes.

Its free and open source and contains a macOS app, CLI, and skills so agents can work natively with it.

Would love to know how teams are solving this with their teams or any feedback on the project!

Similar Projects