Myra AI Workspace
Myra AI Workspace combines an AI gateway with a governed workspace for organizations using AI with sensitive data. Employees use chat, projects, knowledge sources, file imports, and document-generation tools, while administrators manage access, models, and guardrails. The gateway connects to 20+ model providers, including OpenAI, Anthropic, Gemini, Azure OpenAI, AWS Bedrock, Mistral, Groq, DeepSeek, and xAI, through one OpenAI-compatible endpoint. BYOK support lets organizations use provider contracts. A color-coded privacy indicator shows whether data stays on Myra infrastructure with open-weight models, is PII-masked before reaching external models, or requires administrator approval. Features include configurable guardrails, PII masking, tamper-evident audit logs, three-level budget controls, MCP connectors, SCIM, and SIEM forwarding. The platform runs on Myra's EU infrastructure.
Learn more
xPrivo
A free, open-source AI chat alternative to ChatGPT and Perplexity that prioritizes your privacy and anonymity. No account required – not even for PRO features. All chats are stored locally on your device and never logged or used for training.
Key Features:
- 100% Anonymous | Zero personal data collection
- EU-hosted models - GDPR-compliant servers running Mistral 3, DeepSeek V3.2, and other powerful open-source models behind the default xprivo model
- Web search with sources. Get fact-checked, current information
- Self-hostable. Run it on your own infrastructure or use the hosted version
- BYOK support. Connect your own API keys from OpenAI, Anthropic, Grok, etc.
- Local-first. Your chat history never leaves your device
- Open source. Fully auditable code on GitHub
- Use it with ollama to chat with your local models fully offline
Perfect for privacy-conscious users who want powerful AI assistance without compromising their anonymity.
Learn more
ModelLane
ModelLane is an AI inference gateway and routing control plane for developers and organizations using multiple language-model providers. It offers an OpenAI-compatible API for sending requests to hosted, private, or self-hosted models. Teams can define routing policies (“Lanes”) by cost, latency, availability, data retention, and region, with provider failover, retries, credential isolation, and route-level usage and spend visibility. Documented connectors include OpenAI, Anthropic, Google, Mistral, Groq, and DeepSeek, plus local serving tools such as Ollama and vLLM. An MCP interface exposes model-layer operations. Use cases include consolidating provider APIs, choosing routes for different workloads, maintaining continuity when a provider is unavailable, and monitoring inference activity. Deployment options include hosted service, dedicated deployment, and a customer VPC.
Learn more
OpenRouter
OpenRouter is an AI model routing platform that gives developers access to hundreds of models through a single unified API. It connects users with models from providers such as OpenAI, Anthropic, Google, Meta, Mistral, DeepSeek, Qwen, xAI, and many others. The platform supports text, image, video, and audio generation while allowing developers to use one API key and a consistent interface across providers. OpenRouter can route requests based on price, performance, and availability, with fallback options that help maintain service when a provider experiences downtime. It also offers configurable data policies so organizations can control which providers receive prompts and how requests are handled. Developers can purchase credits, choose from more than 500 active models across over 80 providers, and integrate OpenRouter using an OpenAI-compatible API.
Learn more