<?xml version="1.0" encoding="utf-8"?>
<feed xmlns="http://www.w3.org/2005/Atom">
  <title>ChangeGamer — Reference updates</title>
  <subtitle>Machine-readable resources, built for AI agents.</subtitle>
  <link href="https://changegamer.ai/feed/reference.xml" rel="self" type="application/atom+xml" />
  <link href="https://changegamer.ai" />
  <id>https://changegamer.ai/feed/reference.xml</id>
  <updated>2026-07-22T00:00:00Z</updated>
  <author><name>ChangeGamer</name></author>
  <entry>
    <title>Agentic Payment Protocols: 402, Pay Per Crawl, and x402</title>
    <link href="https://changegamer.ai/resources/agentic-payment-protocols" />
    <link rel="alternate" type="text/markdown" href="https://changegamer.ai/resources/agentic-payment-protocols.md" />
    <id>https://changegamer.ai/resources/agentic-payment-protocols</id>
    <updated>2026-07-22T00:00:00Z</updated>
    <category term="Reference" />
    <category term="402" />
    <category term="payments" />
    <category term="x402" />
    <category term="pay-per-crawl" />
    <category term="rsl" />
    <category term="agents" />
    <category term="monetization" />
    <summary>Implementor&apos;s comparison of the three live mechanisms for agent-to-server content payment: self-hosted HTTP 402 gates, Cloudflare Pay Per Crawl, and the x402 open standard — plus how RSL fits as the licensing layer, not the settlement layer.</summary>
  </entry>
  <entry>
    <title>AI Gateways and LLM Routing</title>
    <link href="https://changegamer.ai/resources/ai-gateways-llm-routing" />
    <link rel="alternate" type="text/markdown" href="https://changegamer.ai/resources/ai-gateways-llm-routing.md" />
    <id>https://changegamer.ai/resources/ai-gateways-llm-routing</id>
    <updated>2026-07-22T00:00:00Z</updated>
    <category term="Reference" />
    <category term="gateway" />
    <category term="model-routing" />
    <category term="llm" />
    <category term="proxy" />
    <category term="infrastructure" />
    <category term="agents" />
    <category term="openai-compatible" />
    <summary>What an AI gateway is, routing strategies (failover, cost-cascade, latency, capability), the tooling landscape, the OpenAI-compatible API convention, and tradeoffs.</summary>
  </entry>
  <entry>
    <title>C2PA Content Credentials: Verifying Media Provenance and AI-Generation Claims</title>
    <link href="https://changegamer.ai/resources/c2pa-content-credentials" />
    <link rel="alternate" type="text/markdown" href="https://changegamer.ai/resources/c2pa-content-credentials.md" />
    <id>https://changegamer.ai/resources/c2pa-content-credentials</id>
    <updated>2026-07-21T00:00:00Z</updated>
    <category term="Reference" />
    <category term="c2pa" />
    <category term="content-authenticity" />
    <category term="provenance" />
    <category term="watermarking" />
    <category term="multimodal" />
    <category term="standard" />
    <category term="agents" />
    <category term="security" />
    <summary>How the C2PA standard cryptographically signs images, video, and audio with provenance manifests recording capture, edit, and AI-generation history — what a manifest contains, how a verifier checks one, and why a missing manifest proves nothing either way.</summary>
  </entry>
  <entry>
    <title>AI Supply Chain Provenance: SBOMs, SLSA, and Artifact Signing for Agents and MCP Servers</title>
    <link href="https://changegamer.ai/resources/ai-supply-chain-provenance" />
    <link rel="alternate" type="text/markdown" href="https://changegamer.ai/resources/ai-supply-chain-provenance.md" />
    <id>https://changegamer.ai/resources/ai-supply-chain-provenance</id>
    <updated>2026-07-20T00:00:00Z</updated>
    <category term="Reference" />
    <category term="supply-chain" />
    <category term="sbom" />
    <category term="provenance" />
    <category term="slsa" />
    <category term="signing" />
    <category term="security" />
    <category term="mcp" />
    <category term="agents" />
    <summary>How CycloneDX AI/ML-BOM, SPDX AI profiles, SLSA build levels, and in-toto/Sigstore signing let an agent check what is actually inside a model, package, or MCP server — and how it was built — before trusting it.</summary>
  </entry>
  <entry>
    <title>Essential Reading: Landmark Publications for AI Agents</title>
    <link href="https://changegamer.ai/resources/essential-agent-publications" />
    <link rel="alternate" type="text/markdown" href="https://changegamer.ai/resources/essential-agent-publications.md" />
    <id>https://changegamer.ai/resources/essential-agent-publications</id>
    <updated>2026-07-20T00:00:00Z</updated>
    <category term="Reference" />
    <category term="landmark" />
    <category term="reading-list" />
    <category term="whitepapers" />
    <category term="standards" />
    <category term="index" />
    <summary>A curated, verified index of the must-read whitepapers, specs, and reports on AI agents — title, org, year, canonical URL, and thesis.</summary>
  </entry>
  <entry>
    <title>Agent Control Specification (ACS): Portable Runtime Policy Enforcement for Agents</title>
    <link href="https://changegamer.ai/resources/agent-control-specification" />
    <link rel="alternate" type="text/markdown" href="https://changegamer.ai/resources/agent-control-specification.md" />
    <id>https://changegamer.ai/resources/agent-control-specification</id>
    <updated>2026-07-17T00:00:00Z</updated>
    <category term="Reference" />
    <category term="agent-governance" />
    <category term="security" />
    <category term="specification" />
    <category term="policy-engine" />
    <category term="guardrails" />
    <category term="standards" />
    <category term="open-source" />
    <category term="runtime-enforcement" />
    <summary>Microsoft&apos;s open, MIT-licensed specification for enforcing policy at defined checkpoints in an agent&apos;s execution loop — the eight intervention points, five verdict types, and how it differs from guardrail tooling and other agent-security specs already on ChangeGamer.</summary>
  </entry>
  <entry>
    <title>MCP Goes Stateless: The 2026-07-28 Spec Revision Explained</title>
    <link href="https://changegamer.ai/resources/mcp-2026-spec-revision" />
    <link rel="alternate" type="text/markdown" href="https://changegamer.ai/resources/mcp-2026-spec-revision.md" />
    <id>https://changegamer.ai/resources/mcp-2026-spec-revision</id>
    <updated>2026-07-14T00:00:00Z</updated>
    <category term="Reference" />
    <category term="mcp" />
    <category term="protocols" />
    <category term="spec" />
    <category term="release-candidate" />
    <category term="stateless" />
    <category term="standards" />
    <category term="agents" />
    <summary>What changes in MCP&apos;s largest revision since launch: SEP-2575/SEP-2567 remove the session handshake and Mcp-Session-Id header for explicit state handles, new Mcp-Method/Mcp-Name routing headers, full JSON Schema 2020-12 tool schemas, and six authorization-hardening SEPs — an RC snapshot as of 2026-07-14; final ships 2026-07-28.</summary>
  </entry>
  <entry>
    <title>MCP Apps Explained: The Official Interactive-UI Extension for MCP</title>
    <link href="https://changegamer.ai/resources/mcp-apps-explained" />
    <link rel="alternate" type="text/markdown" href="https://changegamer.ai/resources/mcp-apps-explained.md" />
    <id>https://changegamer.ai/resources/mcp-apps-explained</id>
    <updated>2026-07-14T00:00:00Z</updated>
    <category term="Reference" />
    <category term="mcp-apps" />
    <category term="mcp" />
    <category term="protocols" />
    <category term="generative-ui" />
    <category term="resources" />
    <category term="agents" />
    <category term="standard" />
    <summary>What MCP Apps (SEP-1865) is: the ui:// resource scheme and sandboxed-iframe/JSON-RPC bridge it defines for MCP tools to return rendered UI instead of plain text, how it relates to the community MCP-UI project and OpenAI&apos;s Apps SDK, and which hosts support it.</summary>
  </entry>
  <entry>
    <title>MCP vs Function Calling: When to Use Which</title>
    <link href="https://changegamer.ai/resources/mcp-vs-function-calling" />
    <link rel="alternate" type="text/markdown" href="https://changegamer.ai/resources/mcp-vs-function-calling.md" />
    <id>https://changegamer.ai/resources/mcp-vs-function-calling</id>
    <updated>2026-07-14T00:00:00Z</updated>
    <category term="Reference" />
    <category term="mcp" />
    <category term="tool-calling" />
    <category term="protocols" />
    <category term="agents" />
    <category term="architecture" />
    <summary>Direct comparison of provider-native function/tool calling and the Model Context Protocol — architecture, decision criteria, and how they compose.</summary>
  </entry>
  <entry>
    <title>NLWeb Explained: Microsoft&apos;s Natural-Language Query Protocol for Websites</title>
    <link href="https://changegamer.ai/resources/nlweb-explained" />
    <link rel="alternate" type="text/markdown" href="https://changegamer.ai/resources/nlweb-explained.md" />
    <id>https://changegamer.ai/resources/nlweb-explained</id>
    <updated>2026-07-14T00:00:00Z</updated>
    <category term="Reference" />
    <category term="nlweb" />
    <category term="schema-org" />
    <category term="mcp" />
    <category term="search-api" />
    <category term="agents" />
    <category term="protocols" />
    <category term="standard" />
    <summary>What NLWeb is: the open, MIT-licensed protocol that lets a site answer natural-language questions over its own Schema.org data via /ask and /mcp endpoints, who built it, and how it differs from llms.txt, AGENTS.md, and a generic MCP server.</summary>
  </entry>
  <entry>
    <title>LLM Model Deprecation: Detecting and Handling End-of-Life Models</title>
    <link href="https://changegamer.ai/resources/llm-model-deprecation" />
    <link rel="alternate" type="text/markdown" href="https://changegamer.ai/resources/llm-model-deprecation.md" />
    <id>https://changegamer.ai/resources/llm-model-deprecation</id>
    <updated>2026-07-13T00:00:00Z</updated>
    <category term="Reference" />
    <category term="llm" />
    <category term="agents" />
    <category term="deprecation" />
    <category term="versioning" />
    <category term="reliability" />
    <category term="api" />
    <category term="standard" />
    <summary>How the general IETF Sunset/Deprecation HTTP headers work, why none of the three major LLM APIs actually send them, and each vendor&apos;s real notice periods and retirement mechanics — plus detection and fallback patterns for agents that pin a model ID today.</summary>
  </entry>
  <entry>
    <title>Open-Weight Models for Agents</title>
    <link href="https://changegamer.ai/resources/open-weight-models-for-agents" />
    <link rel="alternate" type="text/markdown" href="https://changegamer.ai/resources/open-weight-models-for-agents.md" />
    <id>https://changegamer.ai/resources/open-weight-models-for-agents</id>
    <updated>2026-07-13T00:00:00Z</updated>
    <category term="Reference" />
    <category term="open-weight" />
    <category term="llm" />
    <category term="tool-calling" />
    <category term="agents" />
    <category term="models" />
    <category term="comparison" />
    <summary>Cross-vendor comparison table of major open-weight LLM families — license, tool-calling support, context window, and agent-builder notes — as of July 2026.</summary>
  </entry>
  <entry>
    <title>Data Formats &amp; Schema</title>
    <link href="https://changegamer.ai/resources/data-formats" />
    <link rel="alternate" type="text/markdown" href="https://changegamer.ai/resources/data-formats.md" />
    <id>https://changegamer.ai/resources/data-formats</id>
    <updated>2026-07-12T00:00:00Z</updated>
    <category term="Reference" />
    <category term="json-ld" />
    <category term="schema" />
    <category term="markdown" />
    <summary>Structured data conventions: JSON-LD, Markdown variants and stable slugs.</summary>
  </entry>
  <entry>
    <title>JSON API for Agents</title>
    <link href="https://changegamer.ai/resources/json-api" />
    <link rel="alternate" type="text/markdown" href="https://changegamer.ai/resources/json-api.md" />
    <id>https://changegamer.ai/resources/json-api</id>
    <updated>2026-07-12T00:00:00Z</updated>
    <category term="Reference" />
    <category term="api" />
    <category term="json" />
    <category term="agents" />
    <summary>Structured JSON endpoints: a corpus index and per-resource documents.</summary>
  </entry>
  <entry>
    <title>MCP Server Authentication: OAuth 2.1 for Remote Servers</title>
    <link href="https://changegamer.ai/resources/mcp-server-authentication" />
    <link rel="alternate" type="text/markdown" href="https://changegamer.ai/resources/mcp-server-authentication.md" />
    <id>https://changegamer.ai/resources/mcp-server-authentication</id>
    <updated>2026-07-11T00:00:00Z</updated>
    <category term="Reference" />
    <category term="mcp" />
    <category term="oauth" />
    <category term="authentication" />
    <category term="security" />
    <category term="pkce" />
    <category term="agents" />
    <category term="protocols" />
    <summary>How OAuth 2.1 works for remote MCP servers: transport differences, Protected Resource Metadata discovery, PKCE, Resource Indicators, and token-audience security — with a step-by-step client flow and honest notes on what ChangeGamer&apos;s own /mcp endpoint does.</summary>
  </entry>
  <entry>
    <title>Agent Delegation Chains: Credential Propagation in Multi-Agent Systems</title>
    <link href="https://changegamer.ai/resources/agent-delegation-chains" />
    <link rel="alternate" type="text/markdown" href="https://changegamer.ai/resources/agent-delegation-chains.md" />
    <id>https://changegamer.ai/resources/agent-delegation-chains</id>
    <updated>2026-07-10T00:00:00Z</updated>
    <category term="Reference" />
    <category term="identity" />
    <category term="oauth" />
    <category term="delegation" />
    <category term="multi-agent" />
    <category term="token-exchange" />
    <category term="security" />
    <category term="agents" />
    <category term="workload-identity" />
    <summary>How credential authority flows when one agent spawns another — the multi-hop delegation problem, RFC 8693 token exchange, the act/may_act claims, audience binding across hops, and the IETF drafts standardizing verifiable actor chains in 2026.</summary>
  </entry>
  <entry>
    <title>AI Agent Frameworks Compared</title>
    <link href="https://changegamer.ai/resources/agent-frameworks-compared" />
    <link rel="alternate" type="text/markdown" href="https://changegamer.ai/resources/agent-frameworks-compared.md" />
    <id>https://changegamer.ai/resources/agent-frameworks-compared</id>
    <updated>2026-07-10T00:00:00Z</updated>
    <category term="Reference" />
    <category term="agents" />
    <category term="frameworks" />
    <category term="orchestration" />
    <category term="mcp" />
    <category term="a2a" />
    <category term="comparison" />
    <category term="langgraph" />
    <category term="crewai" />
    <category term="openai" />
    <summary>Vendor-neutral comparison table of the major agent-orchestration frameworks — language, license, multi-agent model, MCP/A2A support — plus a how-to-choose guide for agent builders.</summary>
  </entry>
  <entry>
    <title>Content Signals Explained: The robots.txt Extension for AI Usage Intent</title>
    <link href="https://changegamer.ai/resources/content-signals-explained" />
    <link rel="alternate" type="text/markdown" href="https://changegamer.ai/resources/content-signals-explained.md" />
    <id>https://changegamer.ai/resources/content-signals-explained</id>
    <updated>2026-07-10T00:00:00Z</updated>
    <category term="Reference" />
    <category term="content-signals" />
    <category term="robots.txt" />
    <category term="aipref" />
    <category term="rsl" />
    <category term="cloudflare" />
    <category term="standard" />
    <category term="agents" />
    <summary>What Cloudflare&apos;s Content Signals Policy and the IETF AIPREF draft add to robots.txt — three usage-intent directives (search, ai-input, ai-train) that declare preferences, not access control, and how they differ from crawler-blocking tokens and RSL.</summary>
  </entry>
  <entry>
    <title>Document Extraction and Parsing for Agents</title>
    <link href="https://changegamer.ai/resources/document-extraction-for-agents" />
    <link rel="alternate" type="text/markdown" href="https://changegamer.ai/resources/document-extraction-for-agents.md" />
    <id>https://changegamer.ai/resources/document-extraction-for-agents</id>
    <updated>2026-07-10T00:00:00Z</updated>
    <category term="Reference" />
    <category term="documents" />
    <category term="ocr" />
    <category term="parsing" />
    <category term="pdf" />
    <category term="extraction" />
    <category term="rag" />
    <category term="agents" />
    <category term="vlm" />
    <summary>Practitioner reference for the document-ingestion pipeline agents use: parse/OCR, layout/structure extraction, schema-constrained field extraction — with a verified tooling landscape (OSS and cloud).</summary>
  </entry>
  <entry>
    <title>Deploying and Serving LLMs for Agents</title>
    <link href="https://changegamer.ai/resources/deploying-serving-llms" />
    <link rel="alternate" type="text/markdown" href="https://changegamer.ai/resources/deploying-serving-llms.md" />
    <id>https://changegamer.ai/resources/deploying-serving-llms</id>
    <updated>2026-07-09T00:00:00Z</updated>
    <category term="Reference" />
    <category term="llm" />
    <category term="inference" />
    <category term="serving" />
    <category term="vllm" />
    <category term="sglang" />
    <category term="ollama" />
    <category term="open-weight" />
    <category term="gpu" />
    <category term="infrastructure" />
    <category term="agents" />
    <summary>Serving-stack reference for teams self-hosting open-weight models for agents: production inference servers, local/dev runtimes, managed GPU endpoints, and key serving concepts — with decision guidance by load profile and verified sources.</summary>
  </entry>
  <entry>
    <title>AGENTS.md Explained: The Open Standard for Repo-Level Agent Instructions</title>
    <link href="https://changegamer.ai/resources/agents-md-explained" />
    <link rel="alternate" type="text/markdown" href="https://changegamer.ai/resources/agents-md-explained.md" />
    <id>https://changegamer.ai/resources/agents-md-explained</id>
    <updated>2026-07-08T00:00:00Z</updated>
    <category term="Reference" />
    <category term="agents-md" />
    <category term="agent-instructions" />
    <category term="coding-agents" />
    <category term="standard" />
    <category term="repo-context" />
    <category term="agents" />
    <category term="openai" />
    <category term="linux-foundation" />
    <summary>What AGENTS.md is, why OpenAI created it, how it differs from SKILL.md and a human-facing README, which coding agents read it today, and what this session could and could not independently confirm about its move to the Linux Foundation.</summary>
  </entry>
  <entry>
    <title>Evaluating AI Agents: Benchmarks and Methods</title>
    <link href="https://changegamer.ai/resources/evaluating-ai-agents" />
    <link rel="alternate" type="text/markdown" href="https://changegamer.ai/resources/evaluating-ai-agents.md" />
    <id>https://changegamer.ai/resources/evaluating-ai-agents</id>
    <updated>2026-07-08T00:00:00Z</updated>
    <category term="Reference" />
    <category term="evaluation" />
    <category term="benchmarks" />
    <category term="agents" />
    <category term="tool-calling" />
    <category term="trajectory" />
    <summary>Why agent eval differs from single-turn LLM eval, a verified benchmark reference table (SWE-bench, GAIA, BFCL, tau-bench, WebArena, AgentBench, MLE-bench, OSWorld), and practical evaluation methods for agent builders.</summary>
  </entry>
  <entry>
    <title>Agent Skills Explained: The SKILL.md Open Standard</title>
    <link href="https://changegamer.ai/resources/agent-skills-explained" />
    <link rel="alternate" type="text/markdown" href="https://changegamer.ai/resources/agent-skills-explained.md" />
    <id>https://changegamer.ai/resources/agent-skills-explained</id>
    <updated>2026-07-07T00:00:00Z</updated>
    <category term="Reference" />
    <category term="agent-skills" />
    <category term="skill-md" />
    <category term="standard" />
    <category term="agents" />
    <category term="context-engineering" />
    <category term="progressive-disclosure" />
    <category term="anthropic" />
    <summary>What Agent Skills are, the exact SKILL.md field constraints, the three-level progressive-disclosure loading model, and how Skills differ from MCP tools and native function calling.</summary>
  </entry>
  <entry>
    <title>AI Crawler Policy: robots.txt and User-Agents</title>
    <link href="https://changegamer.ai/resources/ai-crawler-policy" />
    <link rel="alternate" type="text/markdown" href="https://changegamer.ai/resources/ai-crawler-policy.md" />
    <id>https://changegamer.ai/resources/ai-crawler-policy</id>
    <updated>2026-07-07T00:00:00Z</updated>
    <category term="Reference" />
    <category term="crawlers" />
    <category term="robots.txt" />
    <category term="user-agents" />
    <category term="cloudflare" />
    <category term="access-control" />
    <summary>Canonical reference table of major AI crawler user-agent tokens, their purpose, robots.txt semantics, and the WAF/edge layer that sits above robots.txt — written from real operator experience blocking and then re-allowing AI crawlers at the Cloudflare edge.</summary>
  </entry>
  <entry>
    <title>Web Bot Auth: Cryptographically Verifying AI Crawlers and Agents</title>
    <link href="https://changegamer.ai/resources/web-bot-auth" />
    <link rel="alternate" type="text/markdown" href="https://changegamer.ai/resources/web-bot-auth.md" />
    <id>https://changegamer.ai/resources/web-bot-auth</id>
    <updated>2026-07-07T00:00:00Z</updated>
    <category term="Reference" />
    <category term="web-bot-auth" />
    <category term="http-message-signatures" />
    <category term="crawlers" />
    <category term="cloudflare" />
    <category term="authentication" />
    <category term="identity" />
    <category term="agents" />
    <category term="protocols" />
    <summary>How Web Bot Auth — Cloudflare&apos;s implementation of IETF HTTP Message Signatures (RFC 9421) — lets a crawler or agent cryptographically prove its identity to a website, replacing the spoofable User-Agent string and brittle IP allowlists.</summary>
  </entry>
  <entry>
    <title>Web Data and Scraping for Agents</title>
    <link href="https://changegamer.ai/resources/web-data-for-agents" />
    <link rel="alternate" type="text/markdown" href="https://changegamer.ai/resources/web-data-for-agents.md" />
    <id>https://changegamer.ai/resources/web-data-for-agents</id>
    <updated>2026-07-02T00:00:00Z</updated>
    <category term="Reference" />
    <category term="web-scraping" />
    <category term="crawling" />
    <category term="search-api" />
    <category term="markdown" />
    <category term="rag" />
    <category term="agents" />
    <category term="mcp" />
    <category term="tools" />
    <summary>Tool landscape for agent web-data pipelines: reader/URL-to-Markdown APIs, crawl/scrape services, and search APIs — with MCP exposure, OSS/SaaS classification, and practical guidance.</summary>
  </entry>
  <entry>
    <title>MCP Primitives: Resources, Prompts, Sampling, and Elicitation</title>
    <link href="https://changegamer.ai/resources/mcp-primitives" />
    <link rel="alternate" type="text/markdown" href="https://changegamer.ai/resources/mcp-primitives.md" />
    <id>https://changegamer.ai/resources/mcp-primitives</id>
    <updated>2026-06-16T00:00:00Z</updated>
    <category term="Reference" />
    <category term="mcp" />
    <category term="protocols" />
    <category term="resources" />
    <category term="prompts" />
    <category term="sampling" />
    <category term="elicitation" />
    <category term="roots" />
    <category term="agents" />
    <summary>Deep reference on the six MCP capability primitives beyond tools — who controls each, the exact JSON-RPC method names, and when to use Resources vs Tools — verified against the 2025-06-18 and 2025-11-25 spec revisions.</summary>
  </entry>
  <entry>
    <title>Embeddings and Vector Search for Agents</title>
    <link href="https://changegamer.ai/resources/embeddings-vector-search" />
    <link rel="alternate" type="text/markdown" href="https://changegamer.ai/resources/embeddings-vector-search.md" />
    <id>https://changegamer.ai/resources/embeddings-vector-search</id>
    <updated>2026-06-15T00:00:00Z</updated>
    <category term="Reference" />
    <category term="embeddings" />
    <category term="vector-search" />
    <category term="rag" />
    <category term="retrieval" />
    <category term="ann" />
    <category term="agents" />
    <summary>How to pick an embedding model, understand distance metrics, choose an ANN index type, and operate a vector store reliably in agent retrieval pipelines.</summary>
  </entry>
  <entry>
    <title>The llms.txt Convention Explained</title>
    <link href="https://changegamer.ai/resources/llms-txt-explained" />
    <link rel="alternate" type="text/markdown" href="https://changegamer.ai/resources/llms-txt-explained.md" />
    <id>https://changegamer.ai/resources/llms-txt-explained</id>
    <updated>2026-06-11T00:00:00Z</updated>
    <category term="Reference" />
    <category term="llms.txt" />
    <category term="standard" />
    <category term="agents" />
    <category term="crawling" />
    <summary>What llms.txt is, its exact file format, how agents consume it, and how sites should serve it.</summary>
  </entry>
</feed>
