Havuz

Caveman, coding agent’ların yanıtlarını ve okudukları araç çıktılarını kısaltarak token kullanımını azaltmayı hedefleyen bir skill, proxy ve middleware sunuyor.

Neden yükseliyor · 176 günde 107.974 yıldız ve son 28 günde 220 commit ile 12 farklı yazar, olağanüstü ilgi ve belirgin geliştirme faaliyeti gösteriyor. README ayrıca ThePrimeagen videosunu, Hacker News ve Product Hunt görünürlüğünü, Adobe Research çalışmasını ve JetBrains testlerini öne çıkarıyor; bu dış kaynaklardaki sonuçlar burada bağımsız olarak doğrulanmış değil.

High-performance code-intelligence engine for AI agents and IDE, supports 257 languages, multi repositories, based on graph, with access via

Inline Antigravity dashboard: tok/s, DSH-style cache hit rate, five-hour and weekly quotas. English by default, Chinese switching, reversibl

Quicksilver, toplu sınıflandırma ve arama işlerini Jev modeline devrederek Claude Code'un daha az token kullanmasını amaçlayan bir skill ve plugin'dir.

Neden yükseliyor · README, 12 görevlik benchmark'ta token kullanımında medyan %82 azalma ve bazı görevlerde hız artışı iddia ediyor; ölçülebilir tasarruf vaadi dikkat çekici. Ancak bu sonuçlar repo'nun kendi benchmark'ına dayanıyor ve bağımsız olarak doğrulanmış değil. Proje yalnızca 2 günlük olduğundan 66 yıldız erken ilgi göstergesi; 2 commit ve 1 farklı yazar ise henüz sınırlı geliştirme kanıtı sunuyor.

Context compression for AI coding agents: compresses tool output before it enters the model, dedups repeats to 13-token refs. Claude Code, C

Get FAR MORE done with FAR FEWER tokens 🔥

Measure and safely cut the token cost of LLM tool and MCP schemas, with equivalence checking and a CI gate.

Claude Code plugin: see where your tokens go, audit your setup against the docs, and tune settings with an approved diff

Cut your AI coding agent's token bill, locally: Claude Code, Codex, Cursor, Copilot. #1 on THOL, 39% cheaper on long sessions.

Print a store receipt for your AI coding: tokens, what they'd cost at API prices, and how many times the agent said "You're absolutely right

Pons üzerinde token launch ve alım kampanyalarını çoklu wallet ile yürüten, pozisyonları izleyip otomatik çıkış işlemleri yapan bir TypeScript aracı.

Neden yükseliyor · 26 günlük bir repoda 60 yıldız dikkat çekiyor; ancak son 28 günde 2 commit ve 1 farklı yazar var. İlginin nedenini verilen verilerden belirlemek mümkün değil; yıldız sayısı tek başına kullanım veya güvenilirlik kanıtı değil.

htop for your Claude Code sessions — real-time cost, cache efficiency, model comparison, and smart alerts

Private, provider-neutral context compression for LLMs. Reversibly compress schemas and logs inside your perimeter with zero third-party cal

Packs text files into small images that an AI model reads for about half the input tokens. Includes a Claude Code plugin, a right-click tool

A local proxy that aggregates usage across your Codex and Claude Code accounts — with live token-throughput analytics.

📊 Browse your AI coding spend in the terminal — OpenCode, Claude Code, Codex & friends

Local-first encrypted vault for API keys, tokens, SSH keys, database credentials, and developer configs. Nokuo 是一个本地优先的开发者密钥保险库，用于安全管

Quieter sessions for Claude Code: less narration, shorter tool output and concise answers focused on the result.

The AI-native wire format for structured data. 100% comprehension on every frontier model. 50-92% fewer tokens than JSON. 43B+ lossless roun

Open-source bot for buying tokens launched on Pons

Losslessly compress the tool output your AI agent sends the model, prove every value survived, and report the exact tokens removed. Run it a

Eco mode for Claude Code. /eco: -31% to -73% output tokens with critical findings intact; /eco-max: up to -75% with lowered effort. Measured

A fast codebase indexer and knowledge wiki for AI agents.

The missing human checkpoint for AI coding agents. Give your AI agent a "pause & ask" button — review, correct, or enrich every step before

Cross-platform component library. Eleven npm packages, per-package install, branded tokens, first-party MCP. Web + native via .ts / .native.

What your AI coding agents actually cost — by task, branch, model and file. Runs locally, dashboard on 127.0.0.1:4976, no telemetry.

「DSH·缓存账单」：在上下文圆环弹层里实时算账，缓存命中、未命中与输出各带 token 与金额，峰谷自动计价，第三方中转照常记账。

See your AI coding costs in real time. Tokenline adds context usage, prompt-cache savings, TTL countdown and rate-limit pacing to Claude Cod

A token-spend profiler and cost-regression gate for AI agents.

A Rust TUI and Desktop app for exploring AI coding tool token and cost usage

🦴 paleo — token-saving skills for LLM agents: compress output, trim context, cap budget (Claude Code / Codex / Gemini / Hermes)

Token-efficiency linter for LLM prompts and payloads

Skill and template for GTC design tokens model.

Scan your Claude Code logs and find the habits silently burning your tokens. No LLM calls, no deps, offline.

See where your Claude Code tokens go — cost per call scales 4.3x with context size. Hooks + SQLite + dashboard + MCP server for context wind

CLI-first, local LLM cost tracker for indie devs — drop it in front of any OpenAI-compatible API and watch token usage + spend in real time.

Cuts the token bill of AI coding agents: compresses shell output, blocks token-hungry calls before they run, prices your session live, and r

The honest, local-first usage meter for AI coding tools. With full privacy and with no server or reading your chats.

A benchmarking suite for Agent Skills (SKILL.md files) that measures whether a skill actually improves LLM output quality, and by how much.

Local-first dashboard for Claude Code token usage. Parses ~/.claude/projects/*.jsonl and serves an interactive viewer on localhost. No API c