Weave Router
Dev tools
model router for coding agents
SHOW HN2026
How HN took it
5 positive, 18 neutral or asking, 1 mixed, 19 critical, out of 43 comments about the project. Thread score -0.33.
Idea: 3 for, 6 againstPerformance: 0 for, 6 againstPricing: 0 for, 2 againstPrivacy: 1 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
Cache-aware routing addresses a key concern about proxies.
From 1 comment
If you statelessly route each new request: yes it does end up being more expensive! So our routing is cache-aware. It will have a much higher threshold to switch from one model…
adchurch on HN
Objections
Routing across models breaks prompt caching and adds cache-miss cost.
From 3 comments
The thing I do not get with these routers is that you will have more cache misses (5min ttl). And if there is one thing i’ve learned; using the cache is crucial. How does this…
stpedgwdgfhgdd on HNThis would not work in the way that shows any significant genuine benefit IMO. Caching and optimum routing of a single request are at odds with each other. Higher the distinct…
GodelNumbering on HNIt's rather hard to do at the proxy level with agentic coding, such as Claude Code or similar. These are long-chained sessions of tool use that heavily rely on prompt caching.…
jakozaur on HN
Proxy routing breaks the coding agent's own model-aware control loop.
From 1 comment
I'm glad there are more attempts at solving model routing, as costs (at API rates) has really become an issue. Some feedback: 1. Reiterate the cache issue from other comments…
nikcub on HN
Routing through a proxy may violate subscription terms or get accounts banned.
From 1 comment
Is this talking to claude code, or to claude api (and paying api rates)? programatically routing requests through claude code sounds like a good way to get banned, just like the…
notatoad on HN
Sending code and prompts through a third-party router raises privacy concerns.
From 1 comment
How come data privacy and confidentiality is not an issue with services like these? Do people voluntarily use these proxies/routers, knowing their prompts, outputs and code will…
bijowo1676 on HN
Requests
Publish benchmarks such as Terminal-Bench or DeepSWE-Bench with cost and performance charts.
From 1 comment
I'm glad there are more attempts at solving model routing, as costs (at API rates) has really become an issue. Some feedback: 1. Reiterate the cache issue from other comments…
nikcub on HN
Show A/B evidence for the claimed quality parity.
From 1 comment
> with no noticeable differences in quality or velocity. Have you done any A/B tests on this with evidence? (That's one thing I'd be very interested to see for claims like this -…
jmalicki on HN
Questions
How does it compare with vLLM Semantic Router?
From 1 comment
Looks interesting! Out of curiosity, how does it compare with vLLM Semantic Router? For reference: https://vllm-semantic-router.com/…
matt_d on HN
How does routing differ from Cursor's auto mode?
From 1 comment
What is the difference from Cursors 'auto' mode?
arendtio on HN
How is the router kept current as new models release?
From 1 comment
I'm glad there are more attempts at solving model routing, as costs (at API rates) has really become an issue. Some feedback: 1. Reiterate the cache issue from other comments…
nikcub on HN
Alternatives named
vLLM Semantic Router
From 1 comment
Looks interesting! Out of curiosity, how does it compare with vLLM Semantic Router? For reference: https://vllm-semantic-router.com/…
matt_d on HN
Cursor auto mode
From 1 comment
What is the difference from Cursors 'auto' mode?
arendtio on HN