I built a CLI that turns your codebase into clean LLM input
Yet another code-to-LLM formatter when repomix and git2llm already exist.
A lightweight alternative to OpenClaw that runs in containers for security. Connects to WhatsApp, Telegram, Slack, Discord, Gmail and other messaging apps,, has memory, scheduled jobs, and runs directly on Anthropic's Agents SDK
Makes token bloat visible like bundle size, but GitHub Actions badge metrics already exist.
Open-source maintainers and teams using AI coding agents who want to track codebase size relative to LLM context limits.
Bundlephobia (bundle size badges) · CodeFactor (code quality badges)
Repo Tokens is a GitHub Action that counts your codebase's size in tokens (using tiktoken) and updates a badge in your README. The badge color reflects what percentage of an LLM's context window the codebase fills: green for under 30%, yellow for 50-70%, red for 70%+. Context window size is configurable and defaults to 200k (size of Claude models).
It's a composite action. Installs tiktoken, runs ~60 lines of inline Python, takes about 10 seconds. The action updates the README but doesn't commit, so your workflow controls the git strategy.
The idea is to make token size a visible metric, like bundle size badges for JS libraries. Hopefully a small nudge to keep codebases lean and agent-friendly.
GitHub: https://github.com/qwibitai/nanoclaw/tree/main/repo-tokens
Yet another code-to-LLM formatter when repomix and git2llm already exist.
Promises $15k consultant value in 60s, but 'auto-generated fixes' for whole repos sounds optimistic.
Fits in AI context windows, but Solid.js already does signals without the pitch.
Entropy-based context compression beats naive token stuffing, but the category is crowded.
Windows context menu integration for LLM scripts avoids terminal context switching entirely.
Two-pass scanner prunes folders before reading files, but keyword patterns beat structural analysis.