Git Stars Git Stars

#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
Total Repositories
208,169
Total Stars
7,178
Avg Stars/Repo
1
rtk-ai/rtk

CLI proxy that reduces LLM token consumption by 60-90% on common dev commands. Single Rust binary, zero dependencies

rtk-ai
โญ 87,357 Rust ๐Ÿ‘ค rtk-ai Organization ๐Ÿ• Updated 2026-11-21 ๐Ÿ“… Created 2026-01-22
2
headroomlabs-ai/headroom

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.

headroomlabs-ai
โญ 80,240 Python ๐Ÿ‘ค headroomlabs-ai Organization ๐Ÿ• Updated 2026-11-20 ๐Ÿ“… Created 2026-01-07
3
microsoft/TokenEconomizer

Experience-Driven Black-Box Cost Control for Coding Agents

microsoft
โญ 7,875 Python ๐Ÿ‘ค microsoft Organization ๐Ÿ• Updated 2026-11-20 ๐Ÿ“… Created 2026-10-13
4
vanzan01/cursor-memory-bank

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.

vanzan01
โญ 3,055 ๐Ÿ‘ค vanzan01 User ๐Ÿ• Updated 2026-05-26 ๐Ÿ“… Created 2025-03-22
5
alexgreensh/token-optimizer

Find the ghost tokens. Fix them. Survive compaction. Avoid context quality decay.

alexgreensh
โญ 3,040 Python ๐Ÿ‘ค alexgreensh User ๐Ÿ• Updated 2026-11-19 ๐Ÿ“… Created 2026-02-26
6
jgravelle/jcodemunch-mcp

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.

jgravelle
โญ 2,856 Python ๐Ÿ‘ค jgravelle User ๐Ÿ• Updated 2026-11-21 ๐Ÿ“… Created 2026-02-09
7
redhat-et/ripwire

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.

redhat-et
โญ 2,560 C++ ๐Ÿ‘ค redhat-et Organization ๐Ÿ• Updated 2026-11-21 ๐Ÿ“… Created 2026-07-29
8
cytostack/openwolf

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.

cytostack
โญ 2,401 TypeScript ๐Ÿ‘ค cytostack User ๐Ÿ• Updated 2026-10-19 ๐Ÿ“… Created 2026-03-15
9
glebkudr/shotgun_code

Oneโ€‘click codebase โ€œblastโ€ for Largeโ€‘Languageโ€‘Model workflows.

glebkudr
โญ 1,999 Go ๐Ÿ‘ค glebkudr User ๐Ÿ• Updated 2025-12-04 ๐Ÿ“… Created 2025-05-08
10
Paritok-official/paritok-4b-v1

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.

Paritok-official
โญ 1,439 Python ๐Ÿ‘ค Paritok-official Organization ๐Ÿ• Updated 2026-11-17 ๐Ÿ“… Created 2026-07-15
11
JayPokale/Chisle

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.

JayPokale
โญ 1,243 JavaScript ๐Ÿ‘ค JayPokale User ๐Ÿ• Updated 2026-11-19 ๐Ÿ“… Created 2026-06-30
12
damejan80/tokentab

A CLI that reads Claude Code, Codex, and Gemini CLI session logs and works out how much they cost, by model, project, and day.

damejan80
โญ 1,160 Python ๐Ÿ‘ค damejan80 User ๐Ÿ• Updated 2026-08-27 ๐Ÿ“… Created 2026-08-27
13
crwdla/tokentab

A CLI that reads Claude Code, Codex, and Gemini CLI session logs and works out how much they cost, by model, project, and day.

crwdla
โญ 1,146 Python ๐Ÿ‘ค crwdla User ๐Ÿ• Updated 2026-09-19 ๐Ÿ“… Created 2026-09-07
14
saidsurucu/yargi-mcp

MCP Server For Turkish Legal Databases

saidsurucu
โญ 1,112 Python ๐Ÿ‘ค saidsurucu User ๐Ÿ• Updated 2026-09-06 ๐Ÿ“… Created 2025-05-21
15
lucasrosati/claude-code-memory-setup

Up to 71.5x fewer tokens per session on Claude Code with Obsidian + Graphify. Persistent memory, codebase knowledge graphs, and chat import pipeline. ๐Ÿ‡ง๐Ÿ‡ท PT-BR included.

lucasrosati
โญ 1,074 Python ๐Ÿ‘ค lucasrosati User ๐Ÿ• Updated 2026-10-21 ๐Ÿ“… Created 2026-04-12
16
harlan-zw/mdream

โ˜๏ธ The fastest HTML to markdown convertor on GitHub. Optimized for LLMs and supports streaming.

harlan-zw
โญ 1,032 TypeScript ๐Ÿ‘ค harlan-zw User ๐Ÿ• Updated 2026-11-21 ๐Ÿ“… Created 2025-04-16
โญ 952 Python ๐Ÿ‘ค sagar-n User ๐Ÿ• Updated 2025-11-10 ๐Ÿ“… Created 2025-08-13
18
chipfighter/context-attachment-manager

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.

chipfighter
โญ 812 TypeScript ๐Ÿ‘ค chipfighter User ๐Ÿ• Updated 2026-11-20 ๐Ÿ“… Created 2026-09-24
19
AxiomCodeAI/axiomcodegraph

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.

AxiomCodeAI
โญ 758 TypeScript ๐Ÿ‘ค AxiomCodeAI Organization ๐Ÿ• Updated 2026-11-19 ๐Ÿ“… Created 2026-08-22
20
agentic-os-org/ANOLISA

ANOLISA (Agentic Nexus Operating Layer & Interface System Architecture) | Agentic OS with runtime, security, observability, and Tokenless response compression for lower token usage and cost.

agentic-os-org
โญ 686 Rust ๐Ÿ‘ค agentic-os-org Organization ๐Ÿ• Updated 2026-11-21 ๐Ÿ“… Created 2026-03-30
21
khromov/ai-digest

A CLI tool to aggregate your codebase into a single Markdown file for use with Claude Projects or custom ChatGPTs.

khromov
โญ 682 TypeScript ๐Ÿ‘ค khromov User ๐Ÿ• Updated 2026-10-15 ๐Ÿ“… Created 2024-07-15
22
ojuschugh1/sqz

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.

ojuschugh1
โญ 681 Rust ๐Ÿ‘ค ojuschugh1 User ๐Ÿ• Updated 2026-11-12 ๐Ÿ“… Created 2026-04-12
23
Tura-AI/tura

Build agent that uses 80% less token and delivers better results.

Tura-AI
โญ 670 Rust ๐Ÿ‘ค Tura-AI Organization ๐Ÿ• Updated 2026-10-07 ๐Ÿ“… Created 2026-07-06
24
nadimtuhin/claude-token-optimizer

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.

nadimtuhin
โญ 661 JavaScript ๐Ÿ‘ค nadimtuhin User ๐Ÿ• Updated 2026-11-16 ๐Ÿ“… Created 2025-11-10
25
gglucass/headroom-desktop

Menu bar app for macOS, Windows and Linux that cuts Claude Code and ChatGPT Codex token costs by ~50%

gglucass
โญ 650 Rust ๐Ÿ‘ค gglucass User ๐Ÿ• Updated 2026-11-20 ๐Ÿ“… Created 2026-03-30
26
ooples/token-optimizer-mcp

91.5% fewer tokens in tool output on Headroomโ€™s 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.

ooples
โญ 590 JavaScript ๐Ÿ‘ค ooples User ๐Ÿ• Updated 2026-11-18 ๐Ÿ“… Created 2025-10-11
27
zdk/lowfat

lowfat - slim your command output. strips noise, saves tokens.

zdk
โญ 589 Rust ๐Ÿ‘ค zdk User ๐Ÿ• Updated 2026-11-06 ๐Ÿ“… Created 2026-04-09
28
ratel-ai/ratel

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.

ratel-ai
โญ 566 TypeScript ๐Ÿ‘ค ratel-ai Organization ๐Ÿ• Updated 2026-11-21 ๐Ÿ“… Created 2025-11-12

Frequently Asked Questions

1

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

2

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.

3

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.