why use many token when few token do trick. Skill + local proxy for coding agents: shorter answers, smaller tool output, every original recoverable.
Repository Index
109,091 visible repositories in the index
1–24 of 130 · Most stars
CLI proxy that reduces LLM token consumption by 60-90% on common dev commands. Single Rust binary, zero dependencies
- agentic-coding
- ai-coding
- anthropic
- claude-code
Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens for JSON, same answers. Library, proxy, MCP server.
Pre-indexed code knowledge graph, auto syncs on code changes, for Claude Code, Codex, Gemini, Cursor, OpenCode, AntiGravity, Kiro, CoPilot, and Hermes Agent — fewer tokens, fewer tool calls, 100% local
Rebuild the object in a reference image as a code-only, procedural, quality-gated, animation-ready Three.js model. Token-efficient image-to-3D.
A Claude skill that writes the accurate prompts for any AI tool. Zero tokens or credits wasted. Full context and memory retention
Self-evolving agent: grows skill tree from 3.3K-line seed, achieving full system control with 6x less token consumption
- ai-agent
- automation
- autonomous-agent
- browser-automation
Self-evolving memory OS for LLM & AI Agents: ultra-persistent memory, hybrid-retrieval, and cross-task skill reuse, with 35.24% token savings and DeepSeek Harness support.
Astrid is a portable, capability-secure operating system for composable software.
End-to-End Speech Processing Toolkit
- deep-learning
- end-to-end
- chainer
- pytorch
TranslatedThe Xianyu (闲鱼) Auto-Reply Management System is an automated customer service system developed with Python + FastAPI, designed specifically for the Xianyu platform. The system connects to Xianyu servers through WebSocket, receives and processes messages in real time, and provides intelligent automatic reply service. It also integrates features such as automatic Xianyu delivery, automatic reviews, and automatic polishing, enabling an automated workflow for virtual goods on Xianyu.
cut Claude Code token usage by rendering text context as images
A context-compression plugin for month-long single sessions (billions of tokens) and small context windows (a 100K context is enough), billion-context is all you need .
A CLI tool to convert your codebase into a single LLM prompt with source tree, prompt templating, and token counting.
Experience-Driven Black-Box Cost Control for Coding Agents
- agentic-ai
- agentic-coding
- ai-coding
- ai-coding-assistant
OpenSquilla — Token-Efficient AI Agent with same budget, higher intelligence density
Fast and Accurate Code Search for Agents. Uses 99% fewer tokens than grep+read
One CLAUDE.md file. Keeps Claude responses terse. Reduces output verbosity on heavy workflows. Drop-in, no code changes.
TranslatedA toolkit for low-level operations in DSH, designed to reduce token usage and task execution time
- dsh
- dsh-plugin
- dsh-plugins
Keep searching, reading webpages, reasoning until it finds the answer (or exceeding the token budget)
- deepresearch
- deepsearch
Extract any website's complete design system with one command. DTCG tokens, semantic+primitive+composite, MCP server for Claude Code/Cursor/Windsurf, multi-platform emitters (iOS SwiftUI, Android Compose, Flutter, WordPress), Tailwind v4, Figma variables, shadcn/ui, CSS health audit, WCAG remediation, Chrome extension. MIT, Playwright, Node 20+.
GOWA - WhatsApp REST API with support for UI, Multi Account, Webhooks, and MCP, and Chatwoot. Built with Golang for efficient memory use.
- whatsapp-api
- whatsapp-api-go
- golang
Execution rails for agents. Equip your AI to work with sensitive enterprise systems. Give agents precise permissions and custom tools that work faster with fewer tokens.
MockServer is an HTTP(S) mock server and proxy for testing that lets you mock APIs, inspect and modify live traffic, and inject failures. It supports HTTP/1.1, HTTP/2, gRPC, WebSockets, TCP and more on a single port, with additional support for HTTP/3, message brokers, and AI/LLM APIs.
- mock-server
- proxy
- java-client
- javascript-client