fmerian

Edgee Team - Strava for your coding assistants

Who on your team shipped more with less? Which repo is silently eating your AI budget? Edgee Teams gives coding assistants their missing dashboard. Invite your team, connect GitHub, and every session gets tracked, attributed, and ranked. Compare compression ratios across developers. Share session stats publicly or keep them private. Climb the monthly leaderboard and claim the title of biggest token spender. Built for teams shipping with Claude Code, Codex, and other agents.

Add a comment

Replies

Best
Sacha MORARD
Maker
πŸ“Œ
Hey Product Hunt πŸ‘‹ Sacha here, co founder of Edgee. For our past two launches we showed what compression does at the individual level: Claude Code Compressor extending Pro limits by 26.2%, Codex Compressor cutting costs by 35.6%. Great for solo devs. But then we started talking to teams running Claude Code, Codex, and other agents across 10, 30, sometimes 100 developers. Every team told us the same thing: "We have no idea what's happening." No attribution, no visibility, no idea which repo is burning the budget, no way to know if someone just ran a $200 session by accident. So we built Edgee Team. Invite your team, and every coding assistant session gets tracked, attributed, and ranked. Connect your GitHub org, and sessions auto-link to the repos and PRs they worked on. Each session generates a detailed dashboard: requests, tokens, compression ratio, cost, and a debug view showing exactly what Edgee compressed away. The fun part: every developer gets a shareable public profile with their stats, and there's a monthly leaderboard ranking who used the most tokens. Climb it and claim the "biggest token spender of the month" title. Or don't, and stay private. Your call, per session and per user. What this unlocks: β†’ CTOs finally see where their AI budget goes β†’ Teams can benchmark who ships more with fewer tokens β†’ Devs get bragging rights on their compression game β†’ Everything still runs through the same compression engine, so you keep the savings from the previous launches Free to try, no credit card. Connect your GitHub in 30 seconds. Would love to hear what you'd want us to track next. Per-branch attribution? Slack digest of team usage? Drop ideas in the comments.
Whetlan

@sachamorardΒ  Does compression hold up for non-English prompts? Thinking CJK specifically, tokenizers already split those into way more tokens per character.

Sacha MORARD
@whetlan yes, no problem, with any languages. Compression happens mainly on tool results
Azero0

Congrats @sachamorard , did some quick market analysis for Edgee: https://www.ideajarvis.ai/idea-posts/ddbf4b65-76ed-46dc-978a-e3b656eb7109

one idea: flip the leaderboard from "biggest token spender" to tokens-per-merged-PR. You already have the GitHub attribution and the compression-adjusted token counts in one place, so joining them is mostly UX work. The reframe is bigger than it sounds though β€” cost dashboards are observability, but tokens-per-PR is actual AI engineering productivity. It's also a much better pitch upgrade for CTOs: "where did our budget go" is interesting, but "who ships the most with the least" is what they'd actually want to know.