Python Quickstart
Three things you can do right now withpip install agntor.
Install
1. Guard Prompts (Offline — No API Key)
Block prompt injection attacks before they reach your LLM. Works offline, zero latency.2. Redact PII and Secrets (Offline — No API Key)
Strip sensitive data from LLM outputs before storing or returning them.3. Trust + Escrow (Requires API Key)
Check trust, create escrow, settle payment.4. Report Health Metrics
Feed the Reliability pillar of the trust score:5. Audit Trail
Log actions for compliance and trust scoring:API Reference
| Module | Methods | API Key? |
|---|---|---|
guard(text) | Detect prompt injection | No |
redact(text) | Strip PII/secrets | No |
client.identity | register, resolve, me | Yes |
client.trust | score, verify, badge_url | Yes |
client.escrow | create, status | Yes |
client.settle | release, dispute | Yes |
client.audit | log, list | Yes |
client.health | report, get | Yes |
Next Steps
- LangChain Tutorial — add trust to LangChain agents
- CrewAI Tutorial — trusted multi-agent crews
- Trust Score Algorithm — how the 5-pillar score works
- API Reference — all REST endpoints