35 listed

Protocols & benchmarks

The standards and benchmarks behind agent tooling: MCP, A2A, Agent Skills, AGENTS.md and other protocols, plus benchmarks such as SWE-bench and Terminal-Bench. Protocol pages count the listings that use them; benchmark pages link to the official leaderboards.

Showing 1–8 of 8

0.825score
Agent Skills
Originally developed by Anthropic, released as an open standard
Open folder format (a SKILL.md plus optional scripts and files) for packaging instructions an agent loads on demand.
ReferenceBFreshness: B★ 26.6K
0.822score
MCP Registry
MCP Registry Working Group
Official open catalog and API for publicly available MCP servers, run by the MCP project.
ReferenceAFreshness: A★ 7.4K
0.809score
AGENTS.md
Contributed by OpenAI
Plain Markdown file at a repository root that tells coding agents how to build, test and work in the project.
ReferenceBFreshness: B★ 25.1K
0.776score
MCP Apps
Model Context Protocol project
Official MCP extension that lets tools return interactive HTML interfaces rendered in a sandboxed iframe inside the chat.
ReferenceAFreshness: A★ 3K
0.719score
llms.txt
Proposed by Jeremy Howard
Proposal for a Markdown /llms.txt file that gives language models a short, curated map of a website's content.
ReferenceBFreshness: B★ 2.7K
0.689score
OpenTelemetry GenAI semantic conventions
OpenTelemetry GenAI SIG
OpenTelemetry attribute names and signal shapes for tracing LLM calls, agents, tool execution and MCP operations.
ReferenceAFreshness: A★ 481
0.673score
Open Agent Specification (Agent Spec)
Oracle
Framework-neutral configuration language for describing agents and flows so they can be serialized and run on different runtimes.
ReferenceAFreshness: A★ 445
0.557score
OpenAI Apps SDK (ChatGPT plugins)
OpenAI
OpenAI's toolkit for building ChatGPT plugins from MCP servers, skills and optional in-chat UI, now documented under Plugins.
ReferenceDFreshness: D★ 2.4K