Move fast. Prove it.
Trinitite puts a Guardian between every AI output and your application. Each response is Passed, Corrected, or Blocked before it reaches your users. Govern from the SDK, the MCP gateway, or the Warden, and prove every decision in the Glass Box Ledger.
Agents welcome.
Most code that integrates with Trinitite is written by AI coding agents. The docs are for them, too. Three ways in: the agent guide, the manifest, the full digest.
The human-readable page with the loop and the copy-paste prompt library.
→A short list of links to every section, in the conventional llms.txt format. Fetch this first if you only need a map.
→The redesigned core in one shot, about 80 KB. Read this once and the SDK, evals, Emu, Warden, and architecture are in context.
→Pick the lane that fits your role.
Inline governance for OpenAI, Anthropic, Bedrock, vLLM, SGLang. One env-var swap. Zero re-architecture.
→Every AI decision Merkle-chained, replayable bit-for-bit, mapped to HIPAA / SOC 2 / GDPR / EU AI Act / NIST AI RMF.
→Forensic ledger that proves what the AI tried to do and exactly how the Guardian intervened. Reasonable care, documented.
→Per-tool specialist Guardians for stripe.create_refund, postgres.query, aws.iam.create_role. Schema-aware. Intent-aware.
→One endpoint. Three outcomes.
Every AI response from your model passes through a Guardian and returns exactly one of:
403 + full forensic record.A four-layer assurance stack.
Inline governance is one layer. Trinitite wraps it in streaming and batch assurance, all resting on a reproducible data plane — so proof scales from one request to an entire audit window.
Nineteen surfaces. One Guardian.
Enforcement, evals, the data plane, network discovery, and coverage — each surface is a product page with a diagram and a direct link into the API reference.
The verdict stream, live.
Every governed call writes a signed receipt into the Glass Box Ledger. This is what the live feed looks like — each row is reproducible bit-for-bit from its receipt id.
One environment variable.
# Before
OPENAI_BASE_URL=https://api.openai.com/v1
# After — route through the Guardian
OPENAI_BASE_URL=http://localhost:8080/v1/proxyYour application doesn't change. The platform intercepts every call, applies governance, and proxies to your configured backend.