tokentrim 4x limit extension
Yes, tokentrim can extend Claude Code limits about 4 times by compacting your conversation history. Install the full version, enable the compaction window, and the toolkit will trim and summarize earlier turns automatically.
How it works for a single Claude Code session
- Clone the repository or add the plugin to your environment.
- Run Claude Code as usual; tokentrim records each response.
- When the conversation grows, the compaction window rewrites earlier turns into a short summary.
- The trimmed output is stored locally; long outputs are spooled to disk.
- The replay command lets you see the exact reduction numbers for your session.
What you get and the cost
- Free tier – all hooks, three strength profiles, replay command, local dashboard, daily budget guard, cold‑cache alert. Nothing leaves your machine.
- Pro lifetime – $49 one‑time (first 500 buyers). Adds a hosted dashboard usable on any device, Monday digest, weekly budget alert at 80 %, Slack totals, and support for up to 3 machines.
- Pro monthly – $9 per month, same Pro features on a subscription basis.
All features run on Python 3.9+ and are tested on macOS and Linux.
FAQ
How much history can tokentrim cut? On the author’s 135 real conversations, history re‑read dropped by 75 % and limits lasted 4.0 × longer.
Do I need an internet connection for the free version? No. By default nothing leaves your machine; all processing is local.
Can I see the savings for my own runs? Yes. Use the replay command; it prints your own reduction percentages (typically 6.9 % from output trimming alone).
Ready to extend your Claude Code limits? Install tokentrim now
Updated 2026-10-26