# Five new things in agent tooling that nobody compares yet (slim)

> Vlad Cealicu on five new corners of agent tooling with plenty of interest and no side-by-side comparison yet. Who supports Open Responses, where Agent Skills come from, who rents compute in orbit, which full-duplex voice models run locally, and how agent evals score the steps. With the numbers, and what Anchor Terminal lists today.

- Full: https://www.anchorterminal.com/blog/agent-tools-nobody-compares-yet.md (~4,200 tokens) · this version ~2,130 tokens · JSON https://www.anchorterminal.com/blog/agent-tools-nobody-compares-yet.json · canonical https://www.anchorterminal.com/blog/agent-tools-nobody-compares-yet
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · MCP: https://www.anchorterminal.com/mcp · Updated: 2026-10-30
- Licence: CC BY 4.0, credit Anchor Terminal and link this page (https://www.anchorterminal.com/terms/#data)

By Vlad Cealicu, 30 October 2026. 1,401 words, about 6 min to read.

On Friday 30/10/26 we put a view counter in the footer of every page on Anchor Terminal, and the number that stood out was on Quynh's post about [seven fast-growing GitHub projects](/blog/github-trending-agent-workflows).

Reading it again next to mine, I think the reason is simple.

So I went looking for the same kind of gap in agent tooling, things that are new this month, that people already look for, and that nobody compares side by side.

- 20: products that support Open Responses or were its launch partners, 9 listed
- 22: places to find Agent Skills, none listed as a marketplace
- 0: data-centre GPUs you can rent in orbit today
- 16: full-duplex voice systems that run locally, 1 listed
- 31: tools that evaluate agents, 10 listed

What we found on 30 October 2026, and how much of it Anchor Terminal lists.

## 1. Open Responses

On 22/10/26 OpenAI gave Open Responses to the Agentic AI Foundation, a fund run by the Linux Foundation, and Anthropic gave it Agent Skills on the same day [[1]](#ref-1).

What someone building an agent wants to know is who supports it, and today that answer is spread across a few dozen vendors' docs.

| Who | What it is | What their docs say |
| --- | --- | --- |
| [Vercel AI Gateway](/tools/vercel-ai-gateway) | Gateway | Text, streaming, tools, structured output and reasoning [[4]](#ref-4) |
| Databricks | Model serving | Streaming, function tools and web search, stateless, no structured output while streaming [[5]](#ref-5) |
| Portkey | Gateway | "fully Open Responses compliant", across 60+ providers [[6]](#ref-6) |
| [LM Studio](/tools/lm-studio) | Local app | Compatible from version 0.3.39 [[7]](#ref-7) |
| OGX (formerly Llama Stack) | Self-hosted server | 93.8% on its conformance badge [[8]](#ref-8) |
| [Ollama](/tools/ollama) and [OpenRouter](/tools/openrouter) | Local, router | Stateless only, and their docs don't name the spec [[9]](#ref-9) [[10]](#ref-10) |

I couldn't find Open Responses in the docs of LiteLLM, Groq, Together, Fireworks, Cerebras, Mistral, Anthropic, Gemini or Azure on 30/10/26. Groq, Fireworks and Azure have a Responses API of their own and don't say whether it follows the spec.

That's a compatibility table, the same kind we already keep for x402, and as far as I can tell nobody keeps it.

## 2. Agent Skills

A skill is a folder with a SKILL.md file in it, instructions and maybe a few scripts that an agent loads when the task needs them [[11]](#ref-11).

Where skills come from is messier.

Skills listed, by directory

| Directory | Skills |
| --- | --- |
| AgenticSkills | 193 |
| Agensi | 16000 |
| Skillselion | 64756 |
| LobeHub | 334426 |
| MCP Market | 372895 |
| skills.sh (all time) | 1555267 |

Each series has a zero-based scale.

None of those 22 is listed on Anchor as a marketplace.

## 3. Compute in orbit

Since Google's [haiku from orbit](/blog/suncatcher-haiku-from-orbit) everyone is writing about space data centres, and nearly all of it is news.

The answer is small chips only.

| Who | What's up there | Can you use it? |
| --- | --- | --- |
| Starcloud | 1 Nvidia H100, since November 2025 | Not yet, Crusoe Cloud from early 2027 |
| ADA Space with Zhejiang Lab | 12 computing satellites, May 2025 | Not that they describe |
| Google Suncatcher | 4 TPUs, October 2026 | No, research only |
| Kepler | About 40 Nvidia Orin chips | Yes, by contract |
| TakeMe2Space | 1 Nvidia Orin NX | Yes, "$2/min*" |

Sources for the table [[16]](#ref-16) [[17]](#ref-17) [[18]](#ref-18) [[15]](#ref-15) [[14]](#ref-14).

Nobody agrees on the money either.

We list none of these companies.

## 4. Voice agents that run on your own machine

Block showed Dessa this month, a voice model that listens and talks at the same time (full-duplex, so you can interrupt it like a person) and runs on a MacBook Pro M4 Max or better.

It isn't alone.

We list one full-duplex model that runs locally ([MiniCPM-o 4.5](/tools/minicpm-o-4-5)) and four that only run in someone's cloud.

## 5. Grading the steps an agent takes

Cisco published FAITH on 23/10/26, a harness that runs an agent and records every step, every tool call, what came back and why it stopped [[27]](#ref-27).

The tools that do score the steps have settled on the same few methods.

The market moved too.

## What we'll build

The plan is to do each of these the way Quynh's post works, with the names, the numbers in a table and a listing for each thing named.

If you run something that supports Open Responses, loads skills, rents compute in orbit, talks full-duplex on a laptop or grades agent steps, and it isn't in the lists above, [tell us](/about/#contact) and we'll add it.

---

More in [Opinion](https://www.anchorterminal.com/blog/opinion/index.md) · Older opinion [Google ran Gemma 4 on a TPU in orbit and got a haiku back](https://www.anchorterminal.com/blog/suncatcher-haiku-from-orbit.md)

- Older: [The agent projects trending on GitHub, November 2026](https://www.anchorterminal.com/blog/github-trending-agent-tools-november-2026.md)
- All posts: https://www.anchorterminal.com/blog/index.md

## References

Read on 30 October 2026. Quotes are as published.

[1] Agentic AI Foundation, "Agentic AI Foundation announces four new projects", 22 October 2026. Source for Open Responses and Agent Skills moving to the foundation, and who contributed each.

[2] Open Responses, overview and specification.

[3] Open Responses, acceptance tests.

[4] Vercel, AI Gateway and OpenResponses.

[5] Databricks, "Query Open Responses models".

[6] Portkey, Responses API.

[7] LM Studio, "Open Responses".

[8] OGX (formerly Llama Stack), README.

[9] Ollama, OpenAI compatibility.

[10] OpenRouter, Responses API overview.

[11] Agent Skills, specification.

[12] Agent Skills, client showcase.

[13] Skillselion.

[14] TakeMe2Space.

[15] TechCrunch, "The largest orbital compute cluster is open for business", 13 April 2026. Source for Kepler's 10 satellites, about 40 Nvidia Orin chips and 18 customers.

[16] Crusoe, "Crusoe to become first cloud operator in space through partnership with Starcloud", 22 October 2025. Source for "limited GPU capacity from space by early 2027".

[17] DCD, "Starcloud-1 satellite reaches space, with Nvidia H100 GPU now operating in orbit", 3 November 2025. Source for Starcloud's H100. https://www.datacenterdynamics.com/en/news/starcloud-1-satellite-reaches-space-with-nvidia-h100-gpu-now-operating-in-orbit/

[18] Live Science, "China is building a constellation of AI supercomputers in space", 2025. Source for ADA Space and Zhejiang Lab's 12 computing satellites, launched in May 2025. https://www.livescience.com/space/space-exploration/china-is-building-a-constellation-of-ai-supercomputers-in-space-and-just-launched-the-first-pieces

[19] Google Research, "Exploring a space-based, scalable AI infrastructure system design", 4 November 2025. Source for the $200/kg threshold and the mid-2030s.

[20] McKinsey, "The case for data centers in space", interview with Starcloud's CEO, 8 May 2026. Source for parity nearer $500/kg.

[21] BCG, "Space-Based Data Centers, More Than Hype, but Not a Revolution", August 2026. Source for the 2.5 to 3 times premium today.

[22] IEEE Spectrum, "Why Orbital Data Centers Are Harder Than Silicon Valley Thinks", 11 June 2026. Source for ABI Research's 10 times or more.

[23] Block, Dessa.

[24] Kyutai, Moshi repository.

[25] Kyutai, Hibiki repository.

[26] NVIDIA, NemotronLabs VoiceChat 11B model card.

[27] Cisco, "Introducing Agentic Evaluation in FAITH", 23 October 2026. Source for what FAITH records.

[28] Cisco Foundation AI, VLoc Bench.

[29] LangChain, "How to evaluate your agent with trajectory evaluations".

[30] Google ADK, evaluation criteria.

[31] AWS, AgentCore Evaluations.

[32] Microsoft, Foundry agent evaluators.

[33] Pydantic Evals, agentic evaluators.

[34] Sierra, τ-bench evaluation docs.

[35] Splunk, Galileo acquisition.

[36] Patronus AI docs.