Havuz

Cost control for long Claude Code sessions on Windows, macOS and Linux: tiered context ceilings, a blocking handoff gate, and effort gears.

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

Context window optimization for AI coding agents. Sandboxes tool output (98% reduction), persists session memory via SQLite + FTS5, and enfo

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

Experience-Driven Black-Box Cost Control for Coding Agents

⚡ Terminal HUD, hard budget breakers & prompt-cache leak alerts for AI coding agents (Claude Code, Cursor, Codex)

Two Claude Code subagents that start at about 7.5k tokens instead of 131k: no CLAUDE.md, no skills list, no MCP tools.

Delta MCP is a free app that sits between your AI apps and their MCP servers: any server, every tool. It checks each task before it runs, ap

TOMC Memory: CPU context compression and task memory for Codex, Claude Code, Cursor, TRAE, WorkBuddy and other MCP clients.

Claude skill + plugin that picks the right model and effort for every task: Opus plans, Haiku/Sonnet build, every step is verified, and it e

dsh-sieve: context engineering & token optimization plugin for DeepSeek Harness (DSH) — tool output filtering, context pruning, progressive

Spend fewer tokens on the same work. A local CLI that finds wasted tokens in Claude Code, Codex, opencode and your own API calls.

Claude Code and Codex CLI skill: an LLM router that delegates bulk, already-decided coding tasks to another model you already pay for (GPT v

Occam's razor for Claude Code and Codex: a 30-line rule set. Benchmarks vs base: 51-55% lower estimated task cost on Opus/Sonnet 5.5 max wit

Turn Codex and Claude Code into your AI assistant director. Pair them with your favorite image-generation tools, keep image-heavy chats ligh

Local CLI and MCP server for compacting test and build output, with retrieval from a redacted local cache.

Gobstopper is an intelligent compaction proxy for Claude Code and Codex. It compacts more often, keeps history local, and cut tokens 29% on

面向 AI Agent 的高并发、低延迟上下文治理与 Prompt Cache 守护网关 (Tree-sitter AST / Tool Delta / 50%~80% Token 削减)

A tiny Claude Code skill that keeps your prompt cache warm during idle sessions, so your next message reads from cache instead of paying ful

Share your claude/codex subscriptions ! multi-account router

Open WebUI filter that defers MCP and builtin tool schemas until the model asks for them by name, cutting per-call prompt tokens

The context exoskeleton for AI development: optimize the entire development lifecycle to reduce token usage and context occupancy.

Model router for AI coding agents: routes routine work to cheaper models with routing rules, 8 subagents, hooks and a CLI runner

A tool that replaces everything that can be deterministic in repository work: search, symbols, callers, task scope, history, review and Git

CDAF (Cached Descriptive Asset Files) - open sidecar format for video so AI agents stop re-analyzing the same footage. Spec, CLI, agent skil

Token-efficient facade and Codex skill for MCP for Unity: 96% smaller measured tool-schema surface, compact results, batching, and recovery.

Local Claude Code and Codex plugin that bounds oversized and repeated tool output, preserving complete redacted artifacts. Runs locally, mak

Turn any codebase into a knowledge graph grounded in formal methods. Your AI agents get exact answers for any code-related task, ensure corr

A token-saving CLI for AI coding agents: query symbols and call graphs instead of grepping and reading files

Context compression for MCP. Same upstream call, exact results recoverable.

ripwire, coding agents için kod tabanını indeksleyip call graph, değişiklik etkisi ve ilgili testleri yerel bir CLI ve MCP server üzerinden sunar.

Neden yükseliyor · 60 günde 2.348 yıldız alması ve coding-agent araçlarına yönelik ilgi dikkat çekmesini açıklayabilir; ancak yükselişin doğrudan nedeni verilen verilerden doğrulanamıyor. Son 28 günde 2.779 commit yüksek aktivite gösterirken, yalnızca 2 farklı yazar görünmesi bu aktivitenin dar bir katkıcı grubunda toplandığını düşündürüyor.

Agentic coding framework and meta-harness for planning, building, reviewing, and tuning software across coding agents. Portable agent squads

One zero-dependency MCP gateway CLI for every server and agent skill. Token optimization, tool discovery and context compression: 71,929 ->

Model-agnostic output control for LLM agents: concise, action-first answers with proof and risk preserved. Native install paths for Claude C

Measured, monotonic, lossless input savings for Codex.

TERSE - a hierarchical state language for humans and AI agents.

Paritok, coding agent isteklerini LLM'e iletmeden önce sıkıştıran ve sıkıştırılmış içeriğin gerektiğinde geri alınmasını sağlayan bir gateway'dir.

Neden yükseliyor · Token maliyeti ve context window kullanımı coding agent ekipleri için görünür sorunlar; drop-in entegrasyon vaadi anlaşılır bir değer önerisi sunuyor. 74 günlük repo için 1.453 yıldız ve son 28 günde 12 commit, 4 farklı yazar ilgi ve yakın dönem aktivitesine işaret ediyor; bunlar tek başına ürün kalitesini kanıtlamıyor.

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

Windows fork of pxpipe: transparent Fable 5 compression for Claude Desktop on Windows 11.

Use any AI model, locally or in the cloud, while tracking on-device token usage and collecting token telemetry data.

Free desktop app: run Claude Code with multiple accounts and auto-switch when one hits its 5-hour limit. 24/7 auto-loop, parallel chats, liv

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

Tura, coding agent’ların birden çok araç adımını tek bir runtime-managed command graph içinde çalıştırarak tekrar eden LLM çağrılarını azaltmayı hedefleyen açık kaynak bir agent runtime harness’tir.

Neden yükseliyor · 83 günde 644 yıldız ve son 28 günde 18 commit dikkat çekiyor; token tasarrufu vaadini karşılaştırmalı benchmark’larla desteklemesi de ilgiyi artırmış olabilir. Ancak son 28 gündeki 2 farklı yazar, katkı tabanının hâlâ sınırlı olduğuna işaret ediyor.

The Distillery. A Token Optimization Proxy

Carves your agent's tool outputs down to what matters. Never cuts what doesn't come back.

A lossless token-optimization codec for LLM agents — cut input tokens up to 82%, nothing dropped, every fact kept. Drop-in proxy + one-line

Control plane for AI coding agents: route tasks, reduce token spend, run multi-agent workflows, fallback executors, and track cost per task.

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

Tech-lead orchestration for Claude Code — the top-tier model (Fable) keeps architecture & decisions, cheap subagents (Sonnet/Opus) do the ro

Cut your AI coding agent's token bill on three axes: terse prose, YAGNI-first code, and tool-output compression. Claude Code, Pi, Cursor, Co