ThunderboltThunderbolt was built to protect your data, not profit from it.
Find your path to private AIUse Thunderbolt with Ollama, llama.cpp, Unsloth, and other local model tools. Run inference on your own hardware and keep your prompts on your device.
Connect an OpenAI-compatible local server and choose the models that work for you. You control the models, the hardware, and who has access.
Confidential AI providers such as Tinfoil and NEAR AI run models inside hardware-protected enclaves, designed to keep your prompts and responses private from infrastructure operators.
Thunderbolt makes attestation a first-class part of the experience, with built-in verification for Tinfoil. Check the evidence behind your connection before sending encrypted requests to the model.
Thunderbolt doesn’t use your conversations to train AI models. When you connect Tinfoil as your provider, your prompts and responses aren’t used for training, either.
If you connect a different model provider, its own retention and training policies apply. Choosing your provider is part of choosing your privacy.
Where things live. What gets shared. What you can change. Here’s how Thunderbolt approaches each.
Read the technical detailsConversations are stored locally first. Uploaded files and provider API keys aren’t included in cross-device sync. An attachment can still be sent to the model you ask to work with it.
When you enable sync, sensitive content—including messages and chat titles—is encrypted on your device before upload. Some metadata, such as timestamps and record relationships, stays readable on the server.
A search service receives your query. A connected tool receives the arguments it needs. An external model or agent receives the conversation it answers. These connections aren’t automatically protected by Tinfoil’s enclave.
Choose the services you trust, and turn off connections you don’t need. Self-hosting alone doesn’t keep requests to external services local. Manage your connections.
Protecting people and protecting their private conversations should move forward together. We believe safety should be transparent, accountable, and built with respect for the person using the technology.
Our partner Tinfoil shows one way forward: running safeguard models inside trusted execution environments, or TEEs. In Tinfoil Chat, the checks happen within the protected boundary, without exposing conversation content to operators.
Thunderbolt is the client; you choose and connect the provider that runs your models. When you connect Tinfoil, you use its infrastructure and the privacy and safety protections it provides.
Safety Without Compromising on PrivacyInside Tinfoil Chat’s secure enclave
Private conversation
A limited signal can leave.
The conversation stays private.
Tinfoil Chat may share a violation flag and conversation ID associated with an account, but not the conversation content or violation category.
Open source means you can look closer. Read the code, understand the trade-offs, and choose the setup that feels right for you.