Recently Added
3,528 documents
WARP.md
Documents a monorepo MCP server for transit data, covering setup, architecture, tool creation, and API integration.
MCP Prompts
Describes a prompt management system for MCP, with a phased task list and integration notes for IoT and voice agent projects.
MCP (Model Context Protocol)
Explains the Model Context Protocol (MCP) architecture, its JSON-RPC flow, and how FastMCP simplifies server creation.
AGENTS.md
Documents the architecture, API managers, development commands, and rules for an Anthropic Claude Rust client library.
Datalevin MCP Server
Runs a local Datalevin MCP server over stdio, exposing read-only or read-write database tools to any MCP-compliant client.
Function Calling / Tool Use
Documents eight tools an LLM can invoke to read, search, patch, and create files in a workspace.
LLM Constraint Agent - Implementation Plan
Plans a hybrid LLM agent that translates natural-language budget descriptions into structured JSON for an OR-Tools CP-SAT solver with hard and soft constraints.
MODEL CONTEXT PROTOCOL (MCP)
Explains the Model Context Protocol (MCP) as a universal standard for connecting AI tools to external services, solving the N×M integration problem.
txDevMCP
Documents i-Telex error codes, printer startup feedback, and three dialling modes (instant, timeout, plus) for piTelex MCP.
Paper List for Machine Learning Systems
Curates 400+ research papers on machine learning systems, organized by topic from data processing to distributed training.
Anthropic Tool API in TypeScript
Walks through adding tool use (function calling) to an Anthropic Claude TypeScript app with a weather lookup example.
Note 7: Scaling Tool Use — Advanced Patterns + Token Economics
Teaches six advanced patterns to reduce token consumption and cost when scaling tool-using AI agents.
New Papers
Collects and categorises 100+ papers on tool use, reasoning, and RL for LLMs, with personal notes and links.
Fetch budgets for each unique level
Describes three beta features, Tool Search Tool, Programmatic Tool Calling, and Tool Use Examples, that reduce context bloat and improve tool selection accuracy for Claude agents.
Advanced Tool Use Implementation
Reduces context window usage by 88% through tiered tool loading, on-demand discovery, and batch sandbox execution.
AGENTS.MD — Akıllı Kariyer Asistanı · AI Geliştirici Protokolü
Defines an autonomous AI developer agent's role, authorized files, coding standards, function tools, and PR checklist for a career assistant project.
The Pozitive AI Epic: Roadmap to AI Empowerment
Maps an 8-phase product roadmap for evolving an AI education platform from basic guide to certification-ready system.
Great Deep Learning Tutorials for Natural Language Processing (NLP)
Curates 200+ links to deep learning NLP tutorials, papers, libraries, and datasets, organised by topic.
Model Context Protocol (MCP) 2025-06-18: Complete Implementation Guide
Explains the 2025-06-18 MCP specification with five key features, architecture, and code examples for building enterprise-grade servers.
agents.md — *Codex* Engineering & Data Fetch Agent
Defines an OpenAI Assistants API agent that fetches stock data, generates code, and returns structured results with strict schema validation.
api_llm Specification
Defines a workspace of thin HTTP API clients for major LLM providers with no abstraction layer and explicit developer control.
第5章：ツール利用
Explains the tool-use pattern for LLM agents and provides three framework-specific code examples (LangChain, CrewAI, Google ADK).
Gemini by Example
Collects 20+ Gemini API code examples covering text, images, audio, video, PDFs, agents, and token counting.
Agent Skills
Presents a slide deck explaining the Agent Skills concept, its relationship to Tool Use and MCP, and how major platforms implement it.