Task-aware model selection
A complexity classifier scores a coding turn in single-digit milliseconds and helps determine which model is appropriate for the task.
Weave Router
Freemium
Weave Router é um roteador inteligente de modelos para agentes de programação. Ele avalia tarefas de código e direciona solicitações entre modelos abertos e fechados, ajudando desenvolvedores a manter os fluxos de trabalho atuais dos agentes e a gerenciar velocidade, qualidade e gastos com modelos.
O que é Weave Router?
Weave Router is a model-routing layer for coding agents. It reads the turns an agent takes, assesses the task, and sends each request to a model selected for the job rather than using one model for every interaction. The product is designed to preserve existing coding-agent workflows while balancing task quality, response time, and provider cost.
The router supports workflows involving Claude Code, Codex, Cursor, OpenCode, and Pi, depending on the plan or setup. Users can add the model-provider keys or subscriptions they want to route across. Weave presents Router as a way to use lower-cost models for suitable work and reserve frontier models for tasks that need them.
O que Weave Router pode fazer?
Cache-aware routing
Router considers whether switching models would cost more than the expected saving from routing the request to a less expensive option.
Escalation for incomplete work
An escalation classifier monitors task progress and can return a stalled, looping, or unsuccessful task to a frontier model.
Multiple model sources
The routing pool can include open and closed models, with examples on the site including DeepSeek, GLM, Kimi, Muse, Gemini, Claude, GPT-5, and Llama.
Existing-agent setup
A single command is provided to detect and configure supported coding tools: `npx @workweave/router claude code codex cursor`.
Benchmark and spend estimates
The product provides comparisons using coding benchmarks and an estimator for projected monthly spend. Results are described as dependent on workload, prompt mix, and provider pricing.
Casos de uso
“Mixed-difficulty coding sessions”
Route routine tasks such as explanations, release-note drafts, configuration changes, or ticket triage to less expensive models while reserving stronger models for debugging and complex refactors.
“Teams with existing Claude or Codex subscriptions”
Use Code Boost to route across existing subscriptions and additional models rather than replacing the agent interface or changing the coding workflow.
“Low-cost open-model coding”
Use Code Max as a separate subscription built around tuned open-source models and Router-based selection.
“Benchmarking routing strategies”
Compare Router with other model-selection approaches using task success, elapsed time, and cost per trial on the listed Terminal-Bench and SWE-Atlas evaluations.
“Self-hosted enterprise deployments”
Organizations that need Router in their own infrastructure can discuss a custom Enterprise deployment and hands-on setup support.
Perguntas frequentes
Which coding tools can Weave Router work with?
The site names Claude Code, Codex, Cursor, OpenCode, and Pi. The home page also provides a setup command for Claude Code, Codex, and Cursor.
Does Router replace the coding agent I already use?
No. The product is presented as working with existing agents. Code Boost is specifically designed to extend Claude and Codex subscriptions, while Code Max is positioned as a separate subscription for open-source-model coding.
What does Router return as an output?
Router sends the coding request to a selected model within the configured pool. The site illustrates routing decisions with the selected model, a score, and an indicative cost level; actual results depend on the selected providers and task.
How is Router priced?
Router is billed separately from Weave Platform. The listed plans are Code Max at $10 per month, Code Boost at $100 per month, and custom Enterprise pricing for on-premises deployment. The source pages do not specify general usage limits.
Informações rápidas
- Category
- Developer Tool
- Primary users
- Developers and teams using coding agents
- Core function
- Routes coding requests across open and closed models
- Supported workflows named by the site
- Claude Code, Codex, Cursor, OpenCode, and Pi
- Router plans
- Code Max, Code Boost, and Enterprise
- Deployment option
- Custom Enterprise on-premises deployment
Análise de tráfego de Weave Router
Os dados de tráfego são apenas para referência.
- Classificação do domínio
- 43
Alternativas ao Weave Router
SuperQode
superqode.dev
SuperQode é uma camada de harness de código aberto para agentes de programação, que permite descobrir, criar, executar, avaliar e otimizar harnesses de agentes em um único terminal. Oferece interoperabilidade entre A2A, ACP, MCP e UHP para que as equipes continuem usando seus agentes de programação e modelos atuais.
oMLX
omlx.ai
oMLX é um servidor de inferência LLM nativo do macOS, baseado em MLX, para executar localmente no Apple Silicon modelos compatíveis de linguagem, visão-linguagem, embeddings e reranking. Criado para fluxos de trabalho com agentes de programação, funciona com Claude Code, OpenClaw, Cursor e clientes compatíveis com OpenAI.
Weave
workweave.dev
Weave é uma plataforma de inteligência de engenharia que mede a produção de engenharia e a contribuição da IA em código, revisões e fluxos de trabalho relacionados, ajudando as equipes a entender produtividade, qualidade e o impacto do desenvolvimento assistido por IA.
AlphaProxy
alphaproxy.ai
AlphaProxy é um gateway compatível com OpenAI que encaminha solicitações entre mais de 450 modelos e 100 provedores, com um runtime de agentes para trabalhos em várias etapas e fluxos agendados. Um único endpoint oferece acesso a modelos, ferramentas conectadas e resultados verificáveis.
CybeDefend
www.cybedefend.com
CybeDefend é uma plataforma de segurança de código desenvolvida para fluxos de trabalho de programação com IA. A camada VibeDefend analisa prompts dos agentes e diffs, aplica regras do projeto e do negócio, protege contra ações arriscadas e combina análises de código, dependências, segredos, infraestrutura e CI/CD antes de um pull request.
Unblocked
getunblocked.com
Unblocked transforma código, documentos, tickets e conversas em contexto acionável para revisão de código, Q&A e fluxos de trabalho de programação com AI.