Mastra adds private model gateways for self-hosted models
Start here
Mastra introduced private model gateways that let agents route requests to self-hosted open-weight models, addressed by a prefix such as private/ollama/gpt-oss:20b. According to Mastra, self-hosting keeps sensitive data inside the network and replaces per-token costs with infrastructure costs. The feature requires @mastra/core@1.82.0 or later and was added in PR #18153. Setting AUTO_BLOCK_EXTERNAL_PROVIDERS=true in the .env file hides external providers in Studio's model picker, so users can only select models from the operator's own gateways.
Generated from reports · updated 12 h ago
Report timeline
Follow the reports to see the event from different sides.
- Mastra BlogMastra Agents Private Model Gateways for Self-Hosted Models
Mastra added private model gateways that let agents route requests to self-hosted open-weight models, referenced by a prefix like private/ollama/gpt-oss:20b. Self-hosting keeps sensitive data inside the network and replaces per-token costs with infrastructure costs, and setting AUTO_BLOCK_EXTERNAL_PROVIDERS=true hides external providers in Studio. The feature requires @mastra/core@1.82.0 or later.
Heat for this event
Not enough continuous observations yet to draw a trend.