Agents.json

AI

agent tooling specification

SHOW HN2025

212points
69comments
#293of 3,837 in 2025
Top 8%of 2025 by points

How HN took it

CuriousMostly questions and neutral comments

8 positive, 21 neutral or asking, 1 mixed, 8 critical, out of 38 comments about the project. Thread score +0.04.

Idea: 4 for, 3 againstDocs: 1 for, 1 againstPricing: 0 for, 1 against

The thread, comment by comment

Each row is a top-level comment and its replies, in HN's order. Select a cell to open that comment on HN.

positive neutral or mixed critical about another commenter or something else the maker

What HN said

What people liked

  • Good direction; wants a protocol to win the agent API space

    From 2 comments
    • I've been following agents.json for a little while. I think it has legs, and would love to see some protocol win this space soon. Will be interesting to see where the state/less…
      thomasfromcdnjs on HN
    • Agents.json and LLM.txt files could be simple de-factos like robot.txt and I hope something takes off. CrewAI or Letta/MemGPT or OpenHands/OpenDevin all have some kind of swarm…
      jimmySixDOF on HN
  • Simpler than alternatives

    From 1 comment
    • This could be more simple, which is a good thing, well done! BTW I might have found a bug in the info property title in the spec: "MUST provide the title of the `agents.json`…
      luke-stanley on HN

Objections

  • AGPL license blocks adoption

    From 2 comments
    • AGPL is a great way to prevent people from adopting it.
      cruffle_duffle on HN
    • Cool idea but seems to be dead on arrival due to licensing. Would love to have the team explain how anyone can possibly adopt their agpl package into their product.
      bberenberg on HN
  • Unclear business model and who pays for the standard

    From 2 comments
    • can’t an AI just take an OpenAPI spec and throw it into this standard? if it’s an open source standard, who’s paying for that?
      dkdcwashere on HN
    • I've been down this road - with OpenPlugin. It's all technically feasible - we did it successfully. The question is, so what? If the new models can zero-shot the API call and fix…
      jeffrsch on HN
  • Docs hard to follow; no example agents.json visible

    From 2 comments
    • This is interesting but why do you make it so hard to view the actual agents.json file? After clicking around in the registry (https://wild-card.ai/registry) for 10 minutes I…
      melvinmelih on HN
    • I've been following agents.json for a little while. I think it has legs, and would love to see some protocol win this space soon. Will be interesting to see where the state/less…
      thomasfromcdnjs on HN
  • Providers must write the file; onboarding burden

    From 1 comment
    • So,the api provider, like stripe, is supposed to publish a second API? And then the "end developer" who is going to be making a chatbot/agent, is supposed to use that to make a…
      TZubiri on HN

Requests

  • Permissive license

    From 2 comments
    • A couple people have mentioned some relevant things in this thread. This SDK isn't meant to be restrictive. This can be implemented into other open-source frameworks as a…
      yompal on HN
    • Elastic License V2? https://www.elastic.co/licensing/elastic-license
      Onawa on HN
  • Clearer docs and example schema

    From 2 comments
    • I've been following agents.json for a little while. I think it has legs, and would love to see some protocol win this space soon. Will be interesting to see where the state/less…
      thomasfromcdnjs on HN
    • This is interesting but why do you make it so hard to view the actual agents.json file? After clicking around in the registry (https://wild-card.ai/registry) for 10 minutes I…
      melvinmelih on HN
  • Tool to generate agents.json from OpenAPI

    From 1 comment
    • I've been following agents.json for a little while. I think it has legs, and would love to see some protocol win this space soon. Will be interesting to see where the state/less…
      thomasfromcdnjs on HN

Questions

  • How it differs from MCP

    From 3 comments
    • Looks cool! How is it similar/different from MCP?
      sandinmyjoints on HN
    • I like your approach but it's not clear to me whether it's MCP compatible Anthropic just announced a MCP registry
      tsunego on HN
    • Pardon my ignorance , how is it different from MCP servers and having a supervisor agent selecting and executing the right MCP tool
      linux_devil on HN
  • How it differs from Arazzo

    From 1 comment
    • In what ways is the agents.json file different from an OpenAPI Arazzo specification? Is it more native for LLM use? Looking at the example, I'm seeing similar concepts between…
      winkle on HN
  • Why not just use OpenAPI directly

    From 1 comment
    • Can some help me understand why agents can't just use APIs documented by an openapi spec? Seems to work well in my own testing but I'm sure I'm missing something.
      alooPotato on HN

Alternatives named

  • MCP

    From 2 comments
    • Looks cool! How is it similar/different from MCP?
      sandinmyjoints on HN
    • Hmm but the OpenAPI MVP server just exposes the commands for each API it knows about to the agent - then the MCP server makes stateless API calls. Problem solved. MCP isn't…
      Blahah on HN
  • OpenAPI-to-MCP servers

    From 1 comment
    • Hmm but the OpenAPI MVP server just exposes the commands for each API it knows about to the agent - then the MCP server makes stateless API calls. Problem solved. MCP isn't…
      Blahah on HN
  • Arazzo

    From 1 comment
    • In what ways is the agents.json file different from an OpenAPI Arazzo specification? Is it more native for LLM use? Looking at the example, I'm seeing similar concepts between…
      winkle on HN
  • llms.txt

    From 1 comment
    • How does this compare to llms.txt? I think that’s also emerging as a sort of standard to let LLMs understand APIs. I guess agents.json does a better packaging/ structural…
      sidhusmart on HN

Category, keywords, summaries and labels on this page were made by AI (Thread Reader v2) and not checked by hand. Each point links to the comments it came from.

Add a badge to your READMEShown on HackerShow
[![Shown on HackerShow](https://hackershow.org/badge.svg)](https://hackershow.org/show/43243893)