Hyvor Post vs Switchyard: Features, Pricing & Which Is Better (2026)
A side-by-side comparison of Hyvor Post and Switchyard — features, pricing, and ideal use cases — to help you decide which AI tool fits your workflow.
Hyvor Post
HYVOR (Hyvor, SARL)
Privacy-first, open-source newsletter platform built on Hyvor Relay for simple, tracker-free email publishing.
Key features
- Privacy-First Delivery: Sends newsletters without user tracking or behavioral analytics, focusing on subscriber privacy and minimal data collection.
- Built-on Hyvor Relay: Uses Hyvor Relay — an open-source SMTP-based email API — to send mail through your own infrastructure for better deliverability control and scalability.
- Rich Embeds and Link Previews: Generates link previews and rich embeds via custom parsers and oEmbed; can scrape meta tags for link cards to enrich newsletter content.
- Open-Source Architecture: Distributed under the AGPL-3.0 license with separate frontend, backend, embed, and archive components to inspect, modify, and self-host the platform.
- Developer-Friendly APIs: Provides a developer-focused stack and integration points (Hyvor Relay and internal libraries) for customizing delivery, templates, and automation workflows.
- Scalable Email Sending: Designed to integrate with infrastructure capable of sending high volumes of emails (Relay aims for millions/day) while remaining observable and manageable.
- Modular Codebase: Clear repository layout (backend, frontend, embed, archive) enabling contributors to run the app locally via the HYVOR development environment and Docker tooling.
- Privacy-Oriented Defaults: Default settings and design choices prioritize no-tracking and minimal telemetry to align with privacy-conscious publishers and organizations.
- Privacy-first newsletter delivery with no tracking
- Built on Hyvor Relay — an open-source email API that uses SMTP
- Open-source codebase licensed under AGPL-3.0
- Repository split into backend, frontend, embed, and archive components
- Supports rich embeds and link previews (embed tooling / custom parsers / oEmbed)
- Developer-focused dev workflow (./run post in hyvor/dev environment)
- Docker-friendly components (Dockerfile present in related repos)
- Designed to interoperate with a self-hosted email stack (Relay/SMTP)
Best for
- Privacy-Focused Newsletters: Independent writers or organizations sending subscriber newsletters without tracking open rates or collecting behavioral data.
- Self-Hosted Email Infrastructure: Teams that want to send newsletters using their own SMTP infrastructure and avoid third-party email providers like SendGrid or Mailgun.
- Developer Integrations and Automation: Engineering teams building automated newsletter pipelines or custom sending logic using Hyvor Relay and Post's APIs and libraries.
- Rich Content Newsletters: Publishers who want automatic link previews and rich embeds in email issues to improve engagement and presentation of linked content.
- Open-Source Deployment and Contribution: Organizations that require an AGPL-licensed codebase to audit, extend, or host internally and contribute fixes or features upstream.
- Migration from SaaS Email Providers: Businesses seeking to move away from hosted transactional/newsletter services to a self-managed stack for cost control or privacy reasons.
- Blog-to-Newsletter Workflows: Bloggers using Hyvor's ecosystem (blogs, editor, and post) to create seamless publishing workflows that convert posts into newsletter issues.
- Running privacy-compliant newsletters for communities or businesses
- Integrating a self-hosted email API (Hyvor Relay) to power newsletters
- Developers building or customizing newsletter systems using open-source code
- Deploying a newsletter platform in environments requiring data control and no tracking
- Testing email sending and handling with a self-hosted SMTP-backed API
Switchyard
NVIDIA
An open-source Rust proxy and library that routes LLM traffic across models and providers while preserving native OpenAI and Anthropic API compatibility.
Key features
- Protocol Translation: Converts between OpenAI Chat Completions, OpenAI Responses and Anthropic Messages formats so clients keep their native API while any backend serves the request.
- Multi-Backend Routing: Spreads traffic across vLLM, NVIDIA NIM, Ollama and any OpenAI-compatible endpoint, letting you point an existing coding agent at an open-source model without changing the agent.
- LLM Classifier Router: Uses request content to decide whether a given turn needs the weak or the strong model tier, cutting spend on turns that do not need frontier capability.
- Stage Router: Routes most turns from signals already in the conversation — tool results, errors, conversation stage — so no extra model call is needed to make the decision.
- Escalation Router: Runs every turn on the weak tier first, then has a judge read that answer and decide whether the same request should be re-sent to the strong tier.
- Random Routing for A/B Tests: Applies a fixed traffic split across targets for benchmarking, baselines and cost experiments.
- Operational Metrics: Exposes Prometheus metrics for requests, errors, latency, token counts and the overhead added by routing itself.
- Server or Library Deployment: Run it as a standalone Rust proxy configured by routes.toml, or embed switchyard-libsy in your own application so it decides the target and hands the model call back to you.
Best for
- Pointing Coding Agents at Open Models: Serve Claude Code or Codex from vLLM, NIM or Ollama without the agent knowing the API changed.
- Cost/Performance Optimization: Send routine turns to a cheap weak-tier model and reserve the strong tier for turns a classifier or judge says need it.
- Model A/B Benchmarking: Split traffic on a fixed ratio across two models to compare quality, latency and cost on real production requests.
- Provider Migration and Failover: Keep application code on one API shape while swapping or mixing the providers behind it.
- Embedding Routing in an Agent Runtime: Drop the routing algorithms into an existing gateway or agent framework via the library path without adopting a new HTTP stack.
- Operational Visibility: Track per-route latency, error rates and token spend through Prometheus to find which routes are actually costing money.