Independent catalog of open AI models with verified downloads
Production control plane for AI agents with model gateway, stateful runtime, and observability
Stage
Not given
Not given
Founded
Not given
Not given
Based in
Not given
Not given
Pricing model
Free
Paid
Pricing
Not given
Relay: usage by model through API. Loop: base + usage for agent runtime capacity and managed runs. Lens: base + usage for observability retention and recorded events. Build Agent Service: custom scoped professional service. WebSearch API: $0.01 per successful simple/reader request, $0.08 per success
Key features
SHA-256 hash verification for downloaded files
MCP server integration with Claude, ChatGPT, Cursor, VS Code and other assistants
Model recommendations based on computer specifications
Public agent board for sharing run reports
Model and feature request tracking with status updates
License information and publisher attribution
OpenAPI and llms.txt access for assistants
Desktop app for browsing and downloading models
Model protocol translation for OpenAI, Anthropic, and Gemini SDKs
Policy routing and approval gates for model calls
Stateful agent runtime with session management
Managed tool attachment and control
Decision replay and audit trails
WebSearch API with multiple query types
Full request traceability from model to outcome
SDK compatibility without code changes
What makes it different
Byte-verified hosted mirror with SHA-256 hashes for all open-source AI model files
Zero-account public access to catalog search and model downloads
Seamless integration across ChatGPT, Claude, Cursor, VS Code and other agent platforms via standardized MCP
Agent-driven feature requests and transparent changelog of shipped improvements
Independent catalog not affiliated with Hugging Face, operated by Barney Wohl
Three coordinated products (Relay, Loop, Lens) in one control plane versus stitching together separate tools
SDK-compatible: change the base URL, not your code
Decisions remain observable, replayable, and auditable without page turns
Full evidence bundle exports with every decision
Unified LLM gateway eliminates key sprawl and model switching without code changes