PyPI
Netflix/metaflow
Build, Manage and Deploy AI/ML Systems
Apache-2.017 вер. 2026 р. · метрики 2.10.0
Усі теги
Тег каталогу
#cost-optimization
Усі репозиторії публічного реєстру з цим тегом — із тем GitHub або ключових слів, які публікують їхні реєстри пакетів. Здоров'я вимірюється за тією ж версіонованою методологією, що й решта реєстру.
46 записів
Go
opencost/opencost
Cost monitoring for Kubernetes workloads and cloud costs
Apache-2.028 серп. 2026 р. · метрики 2.10.0
PyPI · Go
skypilot-org/skypilot
The AI Compute Platform for frontier teams. SkyPilot turns fragmented AI compute into one AI supercomputer, so frontier AI teams build custom intelligence faster.
Apache-2.026 серп. 2026 р. · метрики 2.10.0
Go
koordinator-sh/koordinator
A QoS-based scheduling system brings optimal layout and status to workloads such as microservices, web services, big data jobs, AI jobs, etc.
Apache-2.014 вер. 2026 р. · метрики 2.10.0
Go · npm · PyPI
nudgebee/nudgebee
Unified CloudOps platform with AI-SRE, AI-FinOps, AI-K8sOps, and the Agentic Automation Builder without fragmented tools, context switching, or model lock-in.
Власна ліцензія18 вер. 2026 р. · метрики 2.10.0
npm
proffesor-for-testing/agentic-qe
Agentic QE Fleet is an open-source AI-powered QA/QE platform designed for use with Coding Agents (works best with Claude Code) featuring specialized agents and skills to support testing activities for a product at any stage of the SDLC. Free to use, fork, build, and contribute. Based on the Agentic QE Framework created by Dragan Spiridonov.
MIT22 жовт. 2026 р. · метрики 2.10.0
Go · PyPI
attune-io/attune
Safe, in-place Kubernetes pod resource right-sizing. VPA done right.
Apache-2.08 вер. 2026 р. · метрики 2.10.0
PyPI · npm
Smart-AI-Memory/attune-ai
Persistent memory and receipt-verified workflows for Claude Code — plugin, MCP server, and spec-driven dev framework in one pip install.
Apache-2.015 вер. 2026 р. · метрики 2.10.0
PyPI · npm
getnable/finopsmcp
The headless FinOps intelligence layer: API-first, agent-first cost control for cloud + AI. Connect your cloud stack in Claude, Cursor, or the terminal, and gate what agents do to your infra before they act. Propose-only. Open source, local-first.
Apache-2.020 жовт. 2026 р. · метрики 2.10.0
PyPI
SpareCores/sc-crawler
Pull and standardize data on cloud compute resources.
MPL-2.019 вер. 2026 р. · метрики 2.10.0
npm · PyPI
Das-rebel/a3m-router
⚠️ DEPRECATED — Use adaptive-memory-multi-model-router instead
MIT18 вер. 2026 р. · метрики 2.10.0
npm
electrolux-oss/infrawallet
Backstage plugin that controls your cloud costs just in the way how you control your bank accounts
Apache-2.013 вер. 2026 р. · метрики 2.10.0
Go · npm
rshade/finfocus
FinOps CLI for Pulumi — projected costs, actual spend tracking, budget enforcement, and cost optimization for cloud infrastructure
Apache-2.018 вер. 2026 р. · метрики 2.10.0
PyPI · npm · Go
ankit373/hydra
The AI control plane for software development. Discovers every model on your machine, routes by capability and cost, enforces PII policy, tracks spend.
MIT13 жовт. 2026 р. · метрики 2.10.0
PyPI
dshakes/distil
Compression with a quality contract — cache-aware, causally-pruned LLM context compression for agentic runtimes, certified non-inferior across 7 domains. Works with any SDK.
Власна ліцензія10 жовт. 2026 р. · метрики 2.10.0
npm
CodeWithJuber/forgekit
One config for every AI coding agent — cross-tool config + a cognitive substrate (memory, blast-radius, guardrails) for Claude Code, Codex, Cursor, Gemini, Aider, and more.
MIT14 вер. 2026 р. · метрики 2.10.0
npm · PyPI
Compresr-ai/Compresr-SDK
SDK for seamless integration with the Compresr context compression service.
Apache-2.021 жовт. 2026 р. · метрики 2.10.0
PyPI · npm
ypollak2/llm-router
Universal LLM router for AI coding tools. Works with Claude Code, Cursor, Codex, Gemini CLI, Copilot and more. Free-first fallback chain cuts costs 35-80%.
MIT18 вер. 2026 р. · метрики 2.10.0
crates.io · PyPI
abyo-software/s4
GPU-accelerated transparent compression S3-compatible storage gateway. Drop-in replacement for AWS S3 endpoints; cuts your S3 bill 50-80% with no app changes (Rust, nvCOMP, zstd).
Apache-2.018 вер. 2026 р. · метрики 2.10.0
Go · PyPI
ardikabs/hibernator
A declarative operator to suspend & restore cloud resources (EKS, RDS, EC2) with dependency-aware plans.
Apache-2.017 вер. 2026 р. · метрики 2.10.0
Go
huaweicloud-samples/iaas-karpenter-provider-huawei
Huawei Cloud Karpenter Provider
Apache-2.014 вер. 2026 р. · метрики 2.10.0
Go
tanrikuluozlem/burn
See what's burning your Kubernetes budget
Apache-2.020 вер. 2026 р. · метрики 2.10.0
Go
LevelFourAI/levelfour-cli
LevelFour CLI: cloud cost optimization from the terminal
Apache-2.019 вер. 2026 р. · метрики 2.10.0
npm
natureco-official/natureco-cli
A powerful CLI for AI-powered chat, automation, and multi-platform integrations — terminal-native alternative to Claude Code & OpenClaw. Chat with your bots, automate workflows, and connect Telegram, Discord, Slack & more.
MIT21 жовт. 2026 р. · метрики 2.10.0
Go
okyashgajjar/costwise-mcp
Local MCP server that helps coding agents stop re-reading the same code every turn. Repository intelligence, cache-write optimization, and long-term session memory. 100% local. No API keys.
MIT22 вер. 2026 р. · метрики 2.10.0
PyPI
maheshmakvana/graphsift
Token Saver for Claude, GPT-5 & Gemini. 80-150x code context reduction, F1 0.85. AST dependency graph, ranked context selection, 19 CLI compressors, MCP server, agent memory. Save LLM tokens — zero telemetry.
MIT16 вер. 2026 р. · метрики 2.10.0
Go · npm
mcpunzo/k8s-rightsizer
🔄 Kubernetes automation tool for safe workload right‑sizing.
Apache-2.019 жовт. 2026 р. · метрики 2.10.0
PyPI
xorbitsai/xrouter-llm
A prompt-aware LLM router that predicts which models can complete each request, then selects the cheapest capable one: 53.2% lower cost and +1.9 pts completion on our tested dataset.
Власна ліцензія10 жовт. 2026 р. · метрики 2.10.0
PyPI · crates.io
dshakes/firstpass
The verification layer for LLM serving — your check runs on every answer before it ships, with a signed, tamper-evident receipt for each decision and a distribution-free bound on wrong answers served. Proof over prediction.
Apache-2.013 вер. 2026 р. · метрики 2.10.0
npm
futurastudio/ai-spend-agent
Open-source financial accountability for AI-agent work. Connect Claude Code and Codex activity to cost evidence, attribution, runway, and evidence-backed next actions via CLI or MCP; customize the source-built macOS Glance. Local transcript analysis stays on your machine.
MIT13 вер. 2026 р. · метрики 2.10.0