Havuz

Compile an AI agent's repeated workflows into deterministic, auditable routines that replay for free, with a fallback to the agent.

Save 87% token usage for Claude Code. Zero install. 8 rules covering input+output+context. 6 months verified.

Open-source LLM control plane: observe every call, recommend savings, then apply only human-approved, reversible routing.

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

멀티에이전트 Claude Code 하네스를 위한 토큰 비용 lint — 10 카테고리 × 31 sub-patterns 분류학 + 정적 감사 스크립트 + LLM 0회 결정 트리. Korean primary, English mirror.

The cheapest way to run GitHub Actions: AWS spot machines in your own account at AWS's price, nothing added ($0.0008 a minute for 2 vCPU). O

An analytics tool to explore Claude code usage patterns, errors, and token costs

Open-source SaaS subscription management platform — discover unused subscriptions, match payments to apps, and manage users, seats, and cost

Freeze Claude Code's prompt prefix so DeepSeek's automatic cache always hits — alignment proxy + coalescing + keepalive, installable as a CC

Long-term memory for AI agents with no LLM call: an MCP server and Claude Code plugin, plus local-first context compression for LLM apps.

Fugusashi — Federated Learning of LLM Routing with Human-Interpretable Decisions. Open-source alternative to Sakana AI Fugu.

Local-first AWS cost analysis and evidence CLI. Read-only by construction.

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

Beastmode: MofA (Mixture of Agents) orchestration framework for Hermes/OpenClaw/Codex with MemroOS-style context continuity.

Local MCP server that helps coding agents stop re-reading the same code every turn. Repository intelligence, cache-write optimization, and l

Compression with a quality contract — cache-aware, causally-pruned LLM context compression for agentic runtimes, certified non-inferior acro

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

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

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

The headless FinOps intelligence layer: API-first, agent-first cost control for cloud + AI. Connect your cloud stack in Claude, Cursor, or t

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

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

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

Call the Google Antigravity CLI (agy) headlessly from any non-TTY context — Windows ConPTY + POSIX pty + MCP server. Fixes the empty-output

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

Automatic model+effort routing for Claude Code: tiered subagents, escalation ladder, independent verifier

⚡ Adaptive multi-model LLM router — 80+ providers, Jev System One single-pass routing (model=jev-auto), pheromone-trail failover, parallel e

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

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

Claude doesn't do its own stunts. Plan with Claude, execute with a near-free model, review with Claude — a delegation harness for Claude Cod

Run Claude Code with OpenRouter models while keeping tools, file editing, bash, MCP, VS Code support, smart caching, model switching, and sa

Cloudrift is an open-source AWS cost optimization CLI that discovers idle, orphaned and overprovisioned resources and estimates potential sa

SKILL: Claude FABLE 5 spanking Claude OPUS 4.8. Orchestrator-worker cost model for Claude Code: the expensive model reads and judges, Opus 4

Local-first control center for AI-assisted development — observe usage and cost, compare models, code with OpenCode, and understand capacity

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

Per-turn model routing for the Pi coding agent: a small judge picks the cheap or the strong tier for each message, with multi-model failover

AWS Bedrock token monitoring & cost governance platform — ML-powered anomaly detection, automated alerting, forensic analytics, real-time da

Distil an expensive LLM API call on a narrow task into a small local model: capture traffic, curate, LoRA fine-tune with MLX on Apple Silico

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