Havuz

Claude Code usage governor: compact professional output, context slimming, tool-output filtering, telemetry, and drift guardrails.

Claude Code skill — delegate coding tasks to Mistral Vibe, supervise via git diff & save 50-90% Claude token usage

The context spine that 10x's every AI coding session. Live in 8 IDEs (Claude Code, Cursor, Cline, Continue, Aider, Codex, Windsurf, Zed) via

The Distillery. A Token Optimization Proxy

ctx-wire runs your commands, compresses the output with declarative filters, scrubs secrets, and hands your agent a short result. The full l

Local-first flight recorder for coding agents : replay every run as a live session map, score the context bill, and write the fix back into

Measured, monotonic, lossless input savings for Codex.

One command gives AI agents instant codebase context. ~250 tokens replaces 50,000+ tokens of exploration. Auto-configures Claude Code, Curso

Turn Google Drive PDFs into Obsidian wiki notes via NotebookLM MCP without loading full PDFs into Claude context

Claude Code plugin that tracks token usage, identifies wasted context, and saves 30-50% on API costs. Heatmaps, ROI reports, budget alerts,

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

Pith is the hook that makes Claude Code sessions last 3x longer.

Structured plan/execute/verify coding workflow for Claude Code: atomic commits, MCP-backed state, ~92% lower per-turn token overhead, native

Put everything on your wallpaper. Terse is a live 3D particle wallpaper for macOS & Windows: synced song lyrics, notifications, window title

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

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

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

Cut context bloat in your AI-agent stack: find and safely prune unused skills, MCP servers and subagents from real transcript evidence

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

EGC gives every AI coding agent the same brain. Shared memory, skills, and live context across Cursor, Claude Code, Copilot, Aider, and 29 A

Token-efficient MCP server for tabular data retrieval. Index CSV/Excel files, query rows, aggregate — 99%+ token savings vs raw file reads.

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

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

Claude Code skills for developers who code like cats — never more effort than the problem requires.

Agentic Runtime

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

Token-budget-aware graph navigation for AI coding agents. Serve exactly the noodles your LLM needs. 🍜

Run DeepSeek as a real sub-agent inside Claude Code / Codex CLI — with its own 7-tool agent loop, workspace-scoped file access, and bounded

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

Zed extension for Headroom — context compression for AI agents

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

State aware knowledge compression, ingestion, and hybrid retrieval engine. Zero dependencies. Sub-100ms queries.

Keep Claude Code context clean. Open-source toolkit: drift detection, re-read dedup, integrity scoring, AST-aware reads, 15 MCP tools. 62.6%

MCP-native code retrieval for AI agents — 84-88% fewer read tokens, BM25F + semantic search, AST chunks, session dedup

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

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

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

Universal AI router — save 20-40% tokens with RTK and never stop coding. Connect Claude Code, Cursor, Antigravity, Kiro, Copilot, Codex, Cli

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

Audit and shrink your Claude Code startup context. Measures what every skill, plugin, agent, and memory file costs in the system prompt, the

token-ninja routes deterministic shell commands locally — zero LLM calls, ~19µs latency. Works silently inside AI tools via MCP.

MCP server for Unity Editor — 160 tools for scene, assets, animation, VFX, playtest & more

A compiler for AI coding tasks: pre-resolves repo facts (callers, git history, blast radius, bug-site source) before your coding agent's fir

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

CLI output compressor for Claude Code. Reduces token consumption by 50–90% by compressing verbose command output before it enters the con

Self-hosted agentic OS — a Vibe-Engineering platform for Builders. Connect Claude Code Agent to Discord, Telegram, WhatsApp, Slack & Email.

MCP server that shrinks logs, JSON, docs and web pages before your AI reads them. Offline, deterministic, ~3ms, no API key. 66% fewer tokens

Cut Claude Code costs with sourced levers -- prompt caching, model routing, Batch -- plus an installable skill, CLI tools, a cost calculator

Codex Cost Router Skills - preflight task routing skills for Codex to reduce token waste, choose model tiers, reasoning effort, permissions,

Proxy MCP: one server that runs Playwright, Figma, Chrome DevTools, Shopify Dev and Context7 behind a single connection - and cuts their tok