Radar / AI infrastructure / Weave Router 2.0
Weave Router 2.0
Open-source routing model that plugs into coding agents and dispatches each task to the best LLM, matching GPT-6 Astra's coding-agent quality at about half the cost.
Why it matters
Show HN launch claiming Terminal Bench 4.0 and SWE Atlas parity with GPT-6 Astra at 52-54% of the cost and 2.2-2.5x faster — ensemble routing as a credible alternative to a single frontier model.
What you could build with it
An indie developer running a coding-agent service could drop Weave Router into Claude Code or Codex to deliver client work at frontier quality while halving API spend, turning the cost savings into margin on fixed-price contracts.
Does it hold up?
Too early to judge — announced today via Show HN; the Terminal Bench 4.0 and SWE Atlas numbers are vendor-run and await independent reproduction.
Built with Weave Router 2.0
- Show HN discussion: Open-source model routing for coding agents at Astra-level performancehn · Launch thread (80+ points, 23 comments) where the authors explain the new architecture, larger training data, and smarter cache-eviction impact calculation behind Router 2.0.
Learn more
First spotted on github: source.
More AI infrastructure
Modular open-sources MAX inference server, Mojo stdlib and accelerator kernelsThe core of Modular's unified AI deployment stack is now open: the MAX inference server (OpenAI-compatible endpoints)…infra · JEV 0.76OmniRouteFree MIT AI gateway: one endpoint, 290+ providers and 500+ models with quota-aware auto-fallback.infra · JEV 0.75Microsoft releases 301,000 Copilot coding-agent tracesMicrosoft open-sourced 301,026 GitHub Copilot coding-agent sessions (9.3M model calls, 8.7M tool calls) with timings…infra · JEV 0.71Cloudflare Agents Week: Sandboxes GA, 50K concurrent Workflows, Managed OAuth for agentsA dozen agent-infrastructure launches in one week: persistent Linux Sandboxes (GA) with real shell/filesystem/state…infra · JEV 0.69ai-memory: long-term memory for agent coding CLIsRust solution for long-term memory for agent coding CLIs, facilitating handoff between different agents and sessions.infra · JEV 0.68Ai2 Olmo-Core 3: open MoE training stackThe Allen Institute for AI released Olmo-Core 3, a redesigned open training framework for mixture-of-experts models…infra · JEV 0.67
Get the week's best AI launches, plus 3 ideas worth building
One email every Saturday. Ranked by traction, not hype. Free.