# router | Weave | Knowledge Base | Instagit

Model router for agentic systems. Routes every prompt to the right model in <50ms. Cut costs 40-70% with just an endpoint change.

GitHub Stars: 3.1k

Repository: https://github.com/workweave/router

---

## Articles

### [Understanding the Translation Compatibility Setting in WorkWeave Router: Three Modes Explained](/workweave/router/what-are-different-modes-for-translation-compatibility-setting-in-workweave-router)

Explore the three translation compatibility modes Off Shadow and Enforce in WorkWeave Router. Understand how each mode governs compatibility between AI providers and the internal model catalog.

- Tags: deep-dive
- Published: 2026-08-30

### [How WorkWeave Router's Semantic Cache Determines Response Equivalence](/workweave/router/how-does-workweave-routers-semantic-cache-determine-response-equivalence)

Discover how WorkWeave Router's semantic cache determines response equivalence using cosine similarity and configurable thresholds for efficient caching.

- Tags: deep-dive
- Published: 2026-08-30

### [What Is the TTL for Session Pinning Entries in WorkWeave Router?](/workweave/router/what-is-ttl-for-session-pinning-entries-in-workweave-router)

Discover the default 30-minute TTL for session pinning entries in WorkWeave Router. Learn how to configure this setting using the ROUTER_SESSION_PIN_TTL environment variable for optimized performance.

- Tags: api-reference
- Published: 2026-08-30

### [How Session Pinning State Is Persisted and Invalidated in WorkWeave Router](/workweave/router/how-is-session-pinning-state-persisted-and-invalidated-in-workweave-router)

Discover how WorkWeave Router persists session pinning state in PostgreSQL and invalidates pins via TTL expiration error thresholds degenerate response detection loop detection and policy deadline violations.

- Tags: internals
- Published: 2026-08-30

### [Enterprise Custom Gateway Configuration in WorkWeave Router: A Deep Dive](/workweave/router/how-does-workweave-router-handle-enterprise-configurations-for-custom-gateways)

Learn how WorkWeave Router handles enterprise configurations with BYOK, routing traffic through private gateways by filtering requests against tenant-specific providers and model aliases.

- Tags: deep-dive
- Published: 2026-08-30

### [Which AI Model Providers Are Supported by WorkWeave Router? A Complete Technical Guide](/workweave/router/which-ai-model-providers-are-supported-by-workweave-router)

WorkWeave Router supports 12 AI model providers like OpenAI, Gemini, and Bedrock via a unified architecture. Discover all compatible providers and integrate seamlessly.

- Tags: how-to-guide
- Published: 2026-08-30

### [How Provider Clients Are Registered and Managed in WorkWeave Router](/workweave/router/how-are-provider-clients-registered-and-managed-in-workweave-router)

Learn how WorkWeave Router registers and manages provider clients at startup. Discover its centralized mapping strategy for intelligent request routing and credential tracking.

- Tags: internals
- Published: 2026-08-30

### [Where Are Embedder Assets Stored in the WorkWeave Router Docker Image?](/workweave/router/where-are-embedder-assets-stored-in-workweave-router-docker-image)

Discover where embedder assets are stored in the WorkWeave Router Docker image. Learn how Go embed directive compiles assets into the router binary for read-only access via the artifacts variable.

- Tags: how-to-guide
- Published: 2026-08-30

### [What Embedder Backends Does WorkWeave Router Support?](/workweave/router/what-embedder-backends-does-workweave-router-support)

Discover the ONNX Runtime and stub backends supported by WorkWeave Router. Choose between local inference or efficient testing solutions for your projects.

- Tags: api-reference
- Published: 2026-08-30

### [How WorkWeave Router Artifacts Are Versioned and Selected for Deployment](/workweave/router/how-are-workweave-router-artifacts-versioned-and-selected-for-deployment)

Discover how WorkWeave Router versions artifacts in discrete directories and selects them for deployment using the ROUTER_CLUSTER_VERSION environment variable or the latest symlink.

- Tags: internals
- Published: 2026-08-30

### [WorkWeave Router Artifact Bundles: Complete File Structure and Layout](/workweave/router/what-files-are-included-in-workweave-router-artifact-bundles)

Understand the WorkWeave Router artifact bundle file structure including centroids bin model registry metadata yaml and version specific JSON files for embedder data

- Tags: api-reference
- Published: 2026-08-30

### [How cluster.Scorer Determines Routing Decisions in the WorkWeave Router](/workweave/router/how-does-cluster-scorer-determine-routing-decision)

Learn how the WorkWeave cluster.Scorer makes routing decisions by filtering candidates scoring models blending quality cost and speed to select the best option.

- Tags: internals
- Published: 2026-08-30

### [How the Semantic Cache Improves WorkWeave Router Performance](/workweave/router/how-does-semantic-cache-improve-workweave-router-performance)

Discover how the WorkWeave Router's semantic cache boosts performance by eliminating redundant LLM calls. Reduce latency and API costs with intelligent prompt matching.

- Tags: performance
- Published: 2026-08-30

### [What Is the handover.Summarizer in WorkWeave Router?](/workweave/router/what-is-function-of-handover-summarizer-in-workweave-router)

Discover how WorkWeave Router's handover.Summarizer creates concise conversation summaries. Seamlessly switch inference models mid-session while preserving context and managing token limits.

- Tags: deep-dive
- Published: 2026-08-30

### [How Session Pinning Works in WorkWeave Router: Sticky Routing Architecture Explained](/workweave/router/how-does-session-pinning-work-in-workweave-router)

Understand session pinning in WorkWeave Router. Learn how sticky routing ensures persistent decisions for provider selection, cache-aware costing, and automatic failover. Discover the architecture now.

- Tags: internals
- Published: 2026-08-30

### [How the turntype.Detect Component Classifies Request Types in WorkWeave Router](/workweave/router/how-does-turntype-detect-component-classify-request-types)

Discover how the turntype.Detect component in WorkWeave Router classifies request types. Learn about its heuristic cascade for distinguishing probes, compaction tasks, and more.

- Tags: how-to-guide
- Published: 2026-08-30

### [What Is proxy.Service in WorkWeave Router? Core Orchestration Explained](/workweave/router/what-is-role-of-proxy-service-in-workweave-router)

Understand proxy.Service in WorkWeave Router. Discover its role as the central orchestrator for routing decisions, session state, and provider dispatch, ensuring efficient request handling.

- Tags: internals
- Published: 2026-08-30

### [How WorkWeave Router Enforces Unidirectional Imports: Layered Architecture Deep Dive](/workweave/router/how-are-unidirectional-imports-enforced-in-workweave-router)

Discover how WorkWeave Router enforces unidirectional imports with its layered architecture. Learn about golangci-lint rules and AGENTS.md for strict package dependencies. Improve your code quality today.

- Tags: deep-dive
- Published: 2026-08-30

### [Understanding the Three-Layer Architecture of the WorkWeave Router](/workweave/router/what-is-three-layer-architecture-of-workweave-router)

Explore the WorkWeave Router's three-layer architecture: Presentation, Business Logic, and Infrastructure. Discover how this design ensures clean code and eliminates circular dependencies.

- Tags: architecture
- Published: 2026-08-30

### [How WorkWeave Router Handles Translation Between Different API Formats](/workweave/router/how-does-workweave-router-handle-translation-between-different-api-formats)

Discover how WorkWeave Router translates API formats using its internal translate package. Get unified OpenAI-style responses from any LLM service.

- Tags: how-to-guide
- Published: 2026-08-30

### [WorkWeave Router AI Model APIs: Complete Provider Support Guide](/workweave/router/what-ai-model-apis-does-workweave-router-support)

Explore WorkWeave Router AI model APIs. Integrate seamlessly with OpenAI, Gemini, Azure, Bedrock and more using our unified adapter architecture. Simplify your AI integrations today.

- Tags: api-reference
- Published: 2026-08-30

### [Understanding the AvengersPro Clustering Approach in WorkWeave Router: A Deep Dive into Content-Aware Model Routing](/workweave/router/what-is-avengerspro-clustering-approach-in-workweave-router)

Discover WorkWeave Router's AvengersPro clustering approach. This content-aware engine routes requests to optimal AI models efficiently using vector embeddings and cluster centroids. Learn more.

- Tags: deep-dive
- Published: 2026-08-30

### [How the WorkWeave Router Chooses the Optimal AI Model Provider: A Deep Dive into the Selection Pipeline](/workweave/router/how-does-workweave-router-choose-optimal-ai-model-provider)

Discover how the WorkWeave Router selects the optimal AI model provider using a five-stage pipeline with HMM policy engine. Learn about its deterministic selection process.

- Tags: deep-dive
- Published: 2026-08-30