#token-optimization Repositories
Discover 29 active open source GitHub repositories tagged with #token-optimization, accumulating 208,169 total stars (averaging 7,178 stars per project). Leading this topic is rtk-ai/rtk with 87,357 stars.
29 repositories total
CLI proxy that reduces LLM token consumption by 60-90% on common dev commands. Single Rust binary, zero dependencies
Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens for JSON, same answers. Library, proxy, MCP server.
A modular, documentation-driven framework using Cursor custom modes (VAN, PLAN, CREATIVE, IMPLEMENT) to provide persistent memory and guide AI through a structured development workflow with visual process maps.
Find the ghost tokens. Fix them. Survive compaction. Avoid context quality decay.
Symbol-level code retrieval for AI agents: fetch the function you need, not the whole file. Runs locally. 96.2% fewer tokens per lookup on average than grep-and-read on our 15-lookup benchmark. Works with Claude Code, Cursor, Codex, and any MCP client. Free for non-commercial use; commercial use requires a one-time license.
The ripgrep of AI context: a zero-dependency C++23 CLI + MCP server for coding agents. Cut agent token costs by finding code without reading the repo, then keep large codebases off the complexity wall: blast radius, tests to run, quality deltas as you write. Every guess labelled, every loss published. Paddle out with a map.
Portable project memory across Claude Code, Codex and OpenCode, plus token accounting measured from harness transcripts. Local file I/O, no API calls, no telemetry.
Non-destructive compression gateway for AI coding agents. Cuts token bills 25% on turn 1 to past 85% in long or saturated sessions, and fits ~3ร more turns in the same context window. Powered by our open-source code-native 4B model. Drop-in for Claude Code, Cursor, Codex, OpenHands, and any BASE_URL agent.
Cut your AI coding agent's token bill on three axes: terse prose, YAGNI-first code, and tool-output compression. Claude Code, Pi, Cursor, Codex, Gemini + 4 more. Zero deps, published benchmarks including the runs it loses.
A CLI that reads Claude Code, Codex, and Gemini CLI session logs and works out how much they cost, by model, project, and day.
A CLI that reads Claude Code, Codex, and Gemini CLI session logs and works out how much they cost, by model, project, and day.
Up to 71.5x fewer tokens per session on Claude Code with Obsidian + Graphify. Persistent memory, codebase knowledge graphs, and chat import pipeline. ๐ง๐ท PT-BR included.
โ๏ธ The fastest HTML to markdown convertor on GitHub. Optimized for LLMs and supports streaming.
A local plugin for image-heavy chats in Codex, Claude Code, and other AI agents: earlier images are replaced with short placeholders instead of being sent with every message, the model retrieves the original by its ID (even after compaction), and the prompt cache keeps working.
Turn any codebase into a knowledge graph grounded in formal methods. Your AI agents get exact answers for any code-related task, ensure correctness, and optimize time and token usage.
ANOLISA (Agentic Nexus Operating Layer & Interface System Architecture) | Agentic OS with runtime, security, observability, and Tokenless response compression for lower token usage and cost.
A CLI tool to aggregate your codebase into a single Markdown file for use with Claude Projects or custom ChatGPTs.
Context compression for AI coding agents: compresses tool output before it enters the model, deduplicating repeats into 13-token references. Claude Code, Cursor, Codex, Kiro, Zed, and any MCP client. Rust, zero LLM calls.
Cut the tokens Claude Code loads at session start. A CLI that sets up a small CLAUDE.md with on-demand docs, measures startup tokens, and keeps them small.
Menu bar app for macOS, Windows and Linux that cuts Claude Code and ChatGPT Codex token costs by ~50%
91.5% fewer tokens in tool output on Headroomโs own benchmark, where Headroom removes 61.4%. Separately, the same SWE-bench tasks resolved at 0.71x the cost of plain Claude Code. Plus memory across sessions and subscription quota pacing. Claude Code, Codex, Copilot, Gemini, and 12 more. Local, MIT.
The self-improvement layer for AI agents. Ratel reads your agent's traces, finds what fails, recommends fixes, and runs evaluations on real sessions before you ship. Self-hosted: one app, one Postgres. Includes the TypeScript and Python SDKs.
Frequently Asked Questions
What is the most popular #token-optimization repository on GitHub?
The top ranked open source #token-optimization project on GitHub is rtk-ai/rtk with 87,357 stars. CLI proxy that reduces LLM token consumption by 60-90% on common dev commands. Single Rust binary, zero dependencies
Which programming languages are most used in #token-optimization repositories?
Among the top ranked #token-optimization projects on GitHub, the most common programming languages are Python, Rust, TypeScript, JavaScript.
How is the #token-optimization repository ranking calculated?
We track 29 active open source repositories tagged with #token-optimization (500+ stars), totaling 208,169 stars with an average of 7,178 stars per repository. Rankings update daily from the GitHub API.