This product was not featured by Product Hunt yet.
It will not be visible on their landing page and won't be ranked (cannot win product of the day regardless of upvotes).

Product Thumbnail

flatten-mcp

Resume Claude Code sessions 61% lighter, losslessly

Open Source
Developer Tools
Artificial Intelligence
GitHub
Visit WebsiteSee on Product HuntGithub

Hunted byShaya ShavivShaya Shaviv

Claude Code compacts long sessions into a lossy summary. flatten-mcp moves bulky tool output to a backup, keeps every prompt verbatim, and resumes the session at a lower token count. 340k->133k on a real run. Reversible, MIT.

Top comment

Maker here. Claude Code stores each session as a JSONL event log, and near the context limit it compacts the whole thing into a summary that regularly drops the detail you needed two hours later. flatten-mcp does the opposite. In long sessions the bulk of the tokens is tool output (file reads, command logs, base64 screenshots), not your conversation. So it moves that output above a size threshold into a backup copy next to the session and leaves a small reference marker in place. Every prompt and reply stays verbatim, the session resumes as itself, and any moved blob can be pulled back by id on demand. On a real session that went 340,071 -> 132,800 tokens (61% lighter). Fully reversible, crash safe (atomic writes plus a self-cleaning backup), Claude Code only, local stdio, no telemetry, MIT. Happy to answer anything about the session format or the safety model.

Comment highlights

No comment highlights available yet. Please check back later!

About flatten-mcp on Product Hunt

Resume Claude Code sessions 61% lighter, losslessly

flatten-mcp was submitted on Product Hunt and earned 4 upvotes and 1 comments, placing #156 on the daily leaderboard. Claude Code compacts long sessions into a lossy summary. flatten-mcp moves bulky tool output to a backup, keeps every prompt verbatim, and resumes the session at a lower token count. 340k->133k on a real run. Reversible, MIT.

flatten-mcp was featured in Open Source (68.6k followers), Developer Tools (515.5k followers), Artificial Intelligence (473.1k followers) and GitHub (41.3k followers) on Product Hunt. Together, these topics include over 218.1k products, making this a competitive space to launch in.

Who hunted flatten-mcp?

flatten-mcp was hunted by Shaya Shaviv. A “hunter” on Product Hunt is the community member who submits a product to the platform — uploading the images, the link, and tagging the makers behind it. Hunters typically write the first comment explaining why a product is worth attention, and their followers are notified the moment they post. Around 79% of featured launches on Product Hunt are self-hunted by their makers, but a well-known hunter still acts as a signal of quality to the rest of the community. See the full all-time top hunters leaderboard to discover who is shaping the Product Hunt ecosystem.

Want to see how flatten-mcp stacked up against nearby launches in real time? Check out the live launch dashboard for upvote speed charts, proximity comparisons, and more analytics.