Havuz

Experience-Driven Black-Box Cost Control for Coding Agents

麦麦省钱助手 —— 基于麦当劳 MCP 的点餐成本优化 Skill。算出当前门店最省钱的点餐方案，并主动提示凑单陷阱。

50x your Claude usage with cheap-ag. Opus plans, a dirt-cheap model writes every line, and tests decide what ships. Your $20 plan stops hitt

Local Anthropic-compatible AI gateway with cheap-first routing, quality gates, safe model handoffs, and an embedded cost dashboard.

Make Codex and Claude Code subscriptions go further: a local model router that gives routine agent work to economical models and keeps your

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

🍟 麦麦省钱助手 —— 麦当劳中国官方 MCP 的省钱点餐 Agent Skill：官方 calculate-price 实时核价 + 券组合优化 + 沉默成本体检与多单用券排程，官方券/套餐/团购券/积分四渠道同口径算终局价。免登录在线试算。

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

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

Automatic LLM router — 82% cost savings, 79.4% accuracy, 93.4% pass rate. Drop-in OpenAI proxy.

Open-source agentic ops platform for cloud, SRE, DevOps, support and FinOps teams. AI agents investigate incidents, cut cloud and Kubernetes

Fixes prompt cache regression in Claude Code that causes up to 20x cost increase on resumed sessions

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

Drop-in prompt compression for production LLM apps. Cut your token bill 40-60% without changing your code. Python SDK, LLMLingua-2, MIT.

Free, local, open-source LLM cost analyzer - see where your LLM bill leaks, on your machine.

An experiment-driven LLM engineering lab with 9 reproducible Python experiments exploring token economics, API costs, caching, context growt

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

Sub-millisecond query routing & cost-aware execution for GraphRAG architectures. Adaptive-AtomRAG is a highly optimized conditional routing

Intelligent multi-LLM router with task-aware routing strategies, cost optimization, and production safety controls — drop-in OpenAI-compatib

Slash API Batch: Cut AI Costs by 50% in 2026

Multi-Agent Code Review Cost Benchmark 2026: Librarian vs Prompt Cache

Claude Code plugin: automatic Claude model routing. Picks Haiku, Sonnet or Opus and the reasoning effort per prompt, step and subagent; effo

Alephant is an open-source AI Agent Gateway for routing, tracking, and controlling LLM usage across AI agents, members, and workflows, and f

Claude Code v2.1.88 source analysis: system prompts, 87 hidden feature flags, cost optimization, architecture diagrams, undercover mode, and

Budget caps, runaway-loop detection and circuit breakers for AI agents. Zero dependencies, framework agnostic.

Local-first CLI that reads your Spec-Driven Development artifacts and recommends the best value-for-money AI model to implement them. Powere

Know what your stack will cost before the bill arrives. Free agent skill for Claude Code, Cursor and Codex: prices every service at your usa

Universal LLM router for AI coding tools. Works with Claude Code, Cursor, Codex, Gemini CLI, Copilot and more. Free-first fallback chain cut

⚡ Unit tests for AI. Test prompts, compare models, save money.

A repo investigator for Claude Code and Codex. Offload codebase investigation and get up to 2.7× as much work from the same limits.

The first Task-Aware MCP server and automated VRAM calculator for LLM fine-tuning. Instantly snipe the cheapest, fastest GPUs across 10+ clo

Evidence-backed attack paths, drift, and cost auditing for Hetzner Cloud.

The context intelligence layer for AI coding agents. Compressing noise, routing content to the right strategy, preserving session state acro

An open-source, coding agent harness designed specifically for local LLMs. Designed as everything a user needs to jumpstart their own harnes

Open-source Codex plugin for Sol-governed multi-agent coding, bounded AI code review, model routing, and LLM cost optimization

ZeusHammer - AI Super Agent with Local Brain, Voice Interaction & Three-Tier Memory

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

Cost-optimised agent router for Claude Code: sends every sub-task to the cheapest model that can do it, and escalates only on verified failu

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

MCP server: delegate heavy-token tasks from Claude Code to DeepSeek, Kimi, GLM, Qwen, Grok, or any OpenAI-compatible model. Mix providers pe

A prompt-aware LLM router that predicts which models can complete each request, then selects the cheapest capable one: 53.2% lower cost and

Unofficial source-linked AWS best practices for every AWS service, organized by Well-Architected pillar for Claude Code, OpenAI Codex, and A

Anthropic API reverse proxy with prompt-cache injection and request body transforms

Agent Smith, Codex görevleri için yerel model yönlendirmesi, macOS kullanım izleme arayüzü ve tekrarlanabilir benchmark araçları sunuyor.

Neden yükseliyor · Altı günde 194 yıldız alması dikkat çekici; yerel model routing, görünür kullanım takibi ve benchmark sonuçlarını tek projede birleştirmesi ilgi çekmiş olabilir. Ancak bu erken ilgi benimseme kanıtı değil: son 28 günde 5 commit ve 1 farklı yazar var.

34 FinOps specialist AI agents + 6 named-pattern playbooks. Drop into Claude Code, Copilot, Cursor, Windsurf, Aider, Gemini CLI. MIT.

The ops layer for running Claude Code and Codex all day on a Mac: subscription-first routing with overflow to GLM/OpenRouter/Bedrock, pausel

⚡ Cut Claude token usage by 90%+ — free, open-source, local-first context compression for Claude Code. Hybrid RAG (BM25 + ONNX vectors), AST

🏆Winning Project | ModelGate is a contract-aware AI control plane that ingests customer contracts, extracts SLA/privacy/routing constraints,

Local streaming reverse proxy between AI coding agents (Claude Code, Cursor, Codex) and model APIs (Anthropic, OpenAI, Gemini, MiniMax). Met

Replay real agent traces through cheaper models to prove which swaps are safe.