Havuz

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

Guardian Runtime sits securely on your machine, acting as a bodyguard for your code. Whenever you use AI tools like Cursor or Claude Code, i

Neura lets you run long, tool heavy coding sessions without blowing up token costs by compressing old context into references and only resto

Context optimization layer for LLMs. 65-90% token savings with zero quality loss. Drop-in proxy for Claude, GPT, Gemini, and local LLMs (Oll

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

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

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

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

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

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

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

Community skills for Claude Code: token optimization, productivity workflows, and development best practices. All skills tested with TDD met

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

Cuts the token bill of AI coding agents: compresses shell output, blocks token-hungry calls before they run, prices your session live, and r

Local semantic search, symbol graphs, secrets scanning, output filters, and CLI hooks that save 60-90% LLM tokens.

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

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

A smart, multi-strategy code compressor

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

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

Token-saving code search for AI coding agents — TypeScript, JavaScript & Python (zero setup), C#, C++, Go & 30+ more, via a language-server

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

Claude Code plugin that makes coding agents measurably cheaper over time: collect token costs, distill candidate rules, benchmark them on a

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