Weave Router
Dev tools
model routing for coding agents
SHOW HN2026
Weave Router
Open-source model routing for coding agents at Astra-level performance
news.ycombinator.comHow HN took it
3 positive, 17 neutral or asking, 0 mixed, 3 critical, out of 23 comments about the project. Thread score +0.06.
Idea: 1 for, 2 againstExecution: 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
Multi-model systems seen as better than single models for complex tasks.
From 1 comment
I would like to see this (and any model router, frankly) benchmarked against two things, personally: 1) Claude Code's "advisor mode" (nominally, Sonnet 5.5 with a Fable advisor)…
devmor on HN
Objections
Benchmarks from the maker are synthetic and not trusted by some commenters.
From 1 comment
I’m not really sure, I can’t say I trust any kind of synthetic AI benchmarks. > Also I’m very interested in the unique failure cases you’re referring to! What have you noticed?…
devmor on HN
Frontier-labeled training data may limit exceeding frontier model performance.
From 1 comment
If you are training on data labeled by frontier models, how do you expect to exceed the performance of frontier models, other than in the cost dimension by recognizing simpler…
svnt on HN
Requests
Support for local or LAN hosted open-weight models.
From 1 comment
Can it route to locally or LAN hosted Qwen or some other open weights model?
gitowiec on HN
Support for GitHub Copilot as a provider.
From 1 comment
Sounds very interesting. Do you have plan to support gh copilot as model provider?
361994752 on HN
Benchmarks against Claude Code advisor mode and Copilot HydraFusion.
From 1 comment
I would like to see this (and any model router, frankly) benchmarked against two things, personally: 1) Claude Code's "advisor mode" (nominally, Sonnet 5.5 with a Fable advisor)…
devmor on HN
Questions
How does it compare to Cursor auto mode?
From 1 comment
Interesting work, and thanks for describing how your router works internally. It's definitely a fascinating subject. How would you say this compares to Cursor's auto mode?
thefourthchime on HN
How are non-cache input tokens and provider variance handled?
From 2 comments
That sounds really quite interesting- one question pops up, this sounds like it could produce a lot of non-cache input tokens. How much impact does this have, and are you…
capocasa on HNHow do you handle provider variance on OpenRouter for the opensource models? Or do you use your own hosted version to mitigate this? And for both opensource and closed source,…
ajspig1 on HN
Is the trained model available as open weights?
From 1 comment
Is the model you trained available as open weights?
redrove on HN
Alternatives named
Cursor auto mode
From 1 comment
Interesting work, and thanks for describing how your router works internally. It's definitely a fascinating subject. How would you say this compares to Cursor's auto mode?
thefourthchime on HN
Copilot auto mode and HydraFusion
From 2 comments
And similarly, Copilot’s Auto mode?
aschla on HNYou might be interested in GitHub's native take on this concept, HydraFusion:…
ryanhecht on HN
Claude Code advisor mode
From 1 comment
I would like to see this (and any model router, frankly) benchmarked against two things, personally: 1) Claude Code's "advisor mode" (nominally, Sonnet 5.5 with a Fable advisor)…
devmor on HN
Jev
From 1 comment
what about jev
dackdel on HN