Microsoft Copilot SDK 2.0
Comments on “Microsoft Copilot SDK 2.0”
Claim-checked. Scored by all three judges, and its checkable claims were compared with the sources it cites. How far stories are checked
Microsoft released Copilot SDK 2.0, formerly the GitHub Copilot SDK, with a Rust runtime that hosts many isolated sessions in one process instead of one container each. Sessions carry per-user credentials, host-owned tools and journaled state that can resume on another instance. Microsoft reports session creation plus one turn dropping from 5.25 seconds to 55.3 milliseconds, and throughput rising from 7.55 to 120 sessions per second. These figures come from the vendor's own post, with no independent source. SDKs exist for six languages.
Why it ranked
No. 6 of 142 with a score of 0.71. The panel rated it highest on new information (0.91) and practical relevance (0.85), lowest on audience breadth (0.67). Placed No. 6, No. 9 by score alone: the placement terms moved other stories past it.
- AI judgeJudge 2claude-haiku-5-5
- A major SDK release with concrete architecture, Rust benchmarks and API examples for building agents; substantial technical detail, though benchmark claims are vendor-reported and some promotional framing appears.
- AI judgeJudge 3gpt-5.6-luna
- A substantial SDK 2.0 release with concrete runtime, isolation, identity, durability, performance, and deployment details. It is highly actionable for agent builders, though still vendor-authored and partly promotional.
Each judge wrote its line after answering the rubric, with the site and the author still hidden. Every answer behind this is in the table under Score.
Score
0.71total under rubric v2.3
- Significance0.70
- Reader interest0.83
- Audience breadth0.67
- Practical relevance0.85
- Substantiated0.74
- Technical depth0.81
- New information0.91
- Counts against: Promotional0.24
- Counts against: Overclaim0.22
Each judge’s answer per question (0–1), their mean and spread, and what the question adds to the score (weight × mean).
| Question | Judge 1 | Judge 2 | Judge 3 | Mean | Spread | Weight | Contribution (weight times mean) |
|---|---|---|---|---|---|---|---|
| SignificanceHow much does this change what people in tech know or can do? | 0.77 | 0.55 | 0.78 | 0.70 | 0.23 | +0.24 | +0.168 |
| Reader interestWould a well-informed senior engineer or tech founder want to read this today, and likely pass it on? | 0.80 | 0.80 | 0.90 | 0.83 | 0.10 | +0.26 | +0.217 |
| Audience breadthHow many people who build technology does it concern? | 0.70 | 0.60 | 0.72 | 0.67 | 0.12 | +0.13 | +0.087 |
| Practical relevanceHow useful is it to someone who builds software or tech products? | 0.88 | 0.80 | 0.86 | 0.85 | 0.08 | +0.22 | +0.186 |
| SubstantiatedHow well is it backed? Consider whether it is the primary source, and whether its main claims come with data, code, a demo, a reproducible method or citations. | 0.81 | 0.60 | 0.82 | 0.74 | 0.22 | +0.05 | +0.037 |
| Technical depthHow technically substantive is it? | 0.85 | 0.75 | 0.83 | 0.81 | 0.10 | +0.05 | +0.041 |
| New informationDoes it contain information absent from the stories covered in the last 7 days (list provided)? | 0.86 | 0.90 | 0.98 | 0.91 | 0.12 | +0.05 | +0.046 |
| PromotionalIs it mainly marketing with little substance (a press release, ad or sponsored post with no real information)? A launch post that carries real news is not promotional. | 0.10 | 0.35 | 0.28 | 0.24 | 0.25 | −0.19 | −0.046 |
| OverclaimDo the headline or conclusions claim more than the body supports? | 0.17 | 0.30 | 0.18 | 0.22 | 0.13 | −0.11 | −0.024 |
| Sum of contributions | +0.711 | ||||||
| Claim-check penalty | 0.000 | ||||||
| Total, as published | 0.711 | ||||||
Spread is the highest minus the lowest judge answer. marks a spread above 0.40: the judges disagree, and the story is marked contested.
The badge for this ranking, for the author's page or anyone's: one line of HTML, and it links back here.
<a href="https://rubric.hrih.si/editions/2026-11-18/6/"><img src="https://rubric.hrih.si/badge/2026-11-18/6.svg" alt="Ranked #6 on Rubric, 18 Nov 2026" width="238" height="28"></a>Claim check
Claim check: 3 matches source · 4 no source given · 1 couldn’t check. Each claim is compared with the source the article itself cites; a flag is published only when both checkers agree.
Matches sourceVersion
The Microsoft Copilot SDK was previously named the GitHub Copilot SDK.
The cited source says the same thing.
The article says “we’re announcing the new Microsoft Copilot SDK (previously named GitHub Copilot SDK”
The source says “We’re transitioning GitHub Copilot SDK to Microsoft Copilot SDK”
Source cited by the article: github.blog/changelog/2026-10-28-github-copilot-sdk-is-becoming-microsoft-copilot-sdk
No source givenNumber
With the Rust core in-process, creating a client and session and completing one turn went from 5.25 seconds on the TypeScript CLI to 55.3 milliseconds on the same warmed workload.
The article gives no link or citation for it.
The article says “went from 5.25 seconds on the TypeScript CLI to 55.3 milliseconds with the Rust core in-process”
The source says No source to compare with.
No source givenNumber
10 clients now use 126 MB of memory instead of 1,383 MB, and throughput rose from 7.55 to 120 sessions per second.
The article gives no link or citation for it.
The article says “10 clients now use 126 MB of memory instead of 1,383 MB, and throughput rose from 7.55 to 120 sessions per second”
The source says No source to compare with.
No source givenCausal conclusion
Microsoft rebuilt the Copilot SDK runtime in Rust to keep it lean.
The article gives no link or citation for it.
The article says “That only works if the runtime itself is lean, so we rebuilt it in Rust”
The source says No source to compare with.
Couldn’t checkDate
The Copilot SDK launched (became generally available) earlier this year, and many teams across GitHub and Microsoft have since adopted the runtime as a shared platform for Copilot agents.
The source was unreachable, paywalled or too long, or the two checkers disagreed.
The article says “Since the Copilot SDK launch earlier this year, many teams across GitHub and Microsoft have adopted the runtime as a shared platform for Copilot agents across our services”
The source says No passage could be compared.
Source cited by the article: github.blog/changelog/2026-06-02-copilot-sdk-is-now-generally-available
No source givenGeneralization
Before 2.0, a container was the only option for hosting sessions, and every session used one.
The article gives no link or citation for it.
The article says “before today, the container was the only option, so its tradeoffs leaked into every implementation. Every session used a container whether it needed one or not”
The source says No source to compare with.
Matches sourceNumber
The Microsoft Copilot SDK is available in TypeScript, Python, Go, .NET, Java, and Rust.
The cited source says the same thing.
The article says “The Microsoft Copilot SDK is available in TypeScript, Python, Go, .NET, Java, and Rust”
The source says “Your preferred language runtime, at or above the version its SDK requires. Each SDK states its own floor in the Prerequisites section of its README: [Node.js](../nodejs/README.md#prerequisites), [Python](../python/README.md#prerequisites), [Go”
Source cited by the article: github.com/microsoft/copilot-sdk/blob/main/docs/getting-started.md
Matches sourceVersion
In Microsoft Foundry managed agents, Microsoft runs the agent loop and the sandbox on the Microsoft Copilot harness.
The cited source says the same thing.
The article says “Microsoft Foundry managed agents, where Microsoft runs the agent loop and the sandbox on the Microsoft Copilot harness”
The source says “The Copilot harness is an optional managed runtime for prompt agents. Foundry operates the harness and its execution environment. Your resource remains a prompt agent”
Source cited by the article: learn.microsoft.com/en-us/azure/foundry/agents/how-to/use-tools-skills-copilot-harness
Also covered by
No other coverage was clustered with this story.
Elsewhere
Elsewhere: HN 2 pts, not on front page
Recorded for context only, checked 18 Nov 2026, 05:47 UTC. It played no part in the ranking.