Sign in

Repository Index

47,133 repositories indexed

Filters (1)

Filters

Clear all filters

1–23 of 23 · Most stars

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.

TranslatedSelf-hosted TikTok, Douyin & Bilibili scraper and no-watermark video downloader — async REST API, MCP server for AI agents, CLI and web console, plus offline speech-to-text for downloaded videos. Self-healing identity pool, PostgreSQL archive, one docker compose up.

[MLsys2026 Best Paper]: https://arxiv.org/abs/2506.08276. RAG on Everything with LEANN. Enjoy 97% storage savings while running a fast, accurate, and 100% private RAG application on your personal device.

One 8 KB skill that replaces REA (Reverse Engineer Anything): plain CLI tools, no MCP. Benchmarked: 38% faster, 35% cheaper.

Source-available agent platform for Global × China enterprises — wire every system through one agent core. Self-hosted, any LLM.

TranslatedMcDonald's money-saving ordering assistant (麦门精算师, Màimén Jīngsuànshī, "McDonald's actuary") | McDonald's coupon combination optimization Skill: fetches the McDonald's menu and all available coupons, and works out the cheapest ordering combination, Big Mac meal ¥47 → ¥21.9 (53% saved). McDonalds MCP (McDonald's MCP) coupon optimizer · McDonalds China MCP Server · Agent Skill for WorkBuddy · Entry in the McDonald's Programmer Creative Development Contest

A fast software factory workflow for Claude Code: one approval gate, parallel waves, routed models

TranslatedHow many more calories you can eat today depends on how far you are willing to walk — a meal decision that trades walking distance for a calorie allowance. McDonald's official nutrition values × nearby restaurants, to work out what you can still afford to eat for this meal.

  • ai-agent-skill
  • calorie
  • claude-skill
  • mcdonalds

身材管控期也想吃麦当劳?这个专家会帮你根据每日消耗搭配麦麦套餐。基于 SP 矩阵理论,打通麦当劳官方 MCP Server 的营养选型与点餐闭环(35 个官方工具 · 14 个 REST 接口 · 零第三方前端依赖)。

AI-powered platform for OSINT intelligence analysis. Features archive discovery with hypothesis-driven investigation, GLiNER entity extraction, Mapbox geospatial visualization, network analysis, and document processing. Built with FastAPI, Next.js, Weaviate, and DSPy.

  • ai-agents
  • document-processing
  • dspy
  • entity-extraction

Prompt-injection firewall for LLM applications — 33 input detectors, 9 output scanners, federated ed25519-signed threat-intel feed. Apache 2.0, 1040 tests, F1 96.0% with 0% false positives. Docker, GitHub Action, LangChain/LlamaIndex/CrewAI integrations.