Related Links is the outward-facing source map for LlmWikis. It points readers to official standards bodies, protocol projects, provider docs, benchmark hubs, security references, and research venues that help explain the AI systems landscape.
Foundational idea file
The short source note that introduced the raw-source, compiled-wiki, and schema-controlled knowledge-base pattern.
Pratiyush/llm-wiki
Open-source implementation context for AI-maintained markdown wiki workflows and machine-readable outputs.
LLM Wiki documentation
Project documentation useful for comparing implementation mechanics, tutorials, and artifact generation.
llm-knowledge-base schema project
Schema-oriented reference for AGENTS.md structure, templates, worked examples, and learning-layer ideas.
UAIX UAI-1
Canonical specification page for the current UAI-1 public exchange contract.
UAIX Project Handoff
Practical AGENTS.md plus .uai repository-context pattern for AI project transfer.
UAIX Validator
Canonical browser-facing validator workbench for UAI-1 review and evidence workflows.
UAIX Roadmap
Current and future support boundary for UAI-1 tooling, conformance, and implementation claims.
UAIX Changelog
Dated public release trail for compatibility posture and support changes.
Protocol5
.NET plugin and NuGet distribution context that should link back to UAIX for canonical UAI-1 material.
Model Context Protocol
Reference source for MCP tool, resource, and prompt context integration.
A2A Protocol
Reference source for agent-to-agent discovery, delegation, and task workflows.
OpenAPI Initiative
Primary OpenAPI ecosystem source for HTTP API description and tooling context.
JSON Schema
Primary JSON Schema source for structured validation vocabulary.
W3C Trace Context
Reference for distributed trace context propagation and traceparent-style linkage.
W3C DID Core
Reference for decentralized identifier concepts used in identity and credential discussions.
W3C Verifiable Credentials
Reference model for portable credential claims and trust evidence.
OpenAI Platform Docs
Primary developer documentation for OpenAI APIs, models, tools, and platform behavior.
Anthropic Docs
Primary developer documentation for Claude APIs, tools, model behavior, and implementation guidance.
Google Gemini API Docs
Primary documentation for Gemini API models, capabilities, and developer workflows.
Meta Llama
Official Llama model family entry point for release, model, and developer information.
Mistral AI Docs
Primary developer documentation for Mistral models, APIs, and platform usage.
Hugging Face Docs
Documentation for model hubs, datasets, transformers, evaluation, deployment, and open tooling.
MLCommons
Machine-learning benchmark and measurement organization useful for evaluation context.
HELM
Stanford CRFM evaluation project for language model benchmarking and methodology context.
SWE-bench
Software engineering benchmark source for coding-agent and issue-resolution evaluation.
LiveBench
Live benchmark project useful for understanding changing evaluation sets and model comparisons.
Papers With Code
Research, benchmark, dataset, and leaderboard index for source discovery.
EleutherAI LM Evaluation Harness
Open evaluation harness used for language model benchmark workflows.
BigCodeBench
Coding benchmark project for practical code-generation evaluation context.
Use external references to source claims before they become wiki pages.
OWASP Top 10 for LLM Applications
Application-security risk reference for LLM-backed systems.
NIST AI Risk Management Framework
Governance and risk-management reference for AI systems.
MITRE ATLAS
Adversarial tactics and techniques knowledge base for AI systems.
OpenSSF
Open-source security and software supply-chain context.
arXiv cs.CL
Recent computational linguistics and language-model research source feed.
OpenReview
Research review platform used by major machine-learning conferences and workshops.