Tamper-proof memory + cryptographic audit trail for AI agents. HIPAA, SOC2, GDPR compliance built-in. Trust score for every response. Python & TypeScript SDKs. Rust-powered.

🔐 Connector OSS — Make Every AI Decision Provable

Your AI agents are making decisions. Can you prove what they did?

Every AI decision deserves proof. We're building it.

Proof = CID content hash + HMAC-chained audit + Ed25519 signatures — verifiable by anyone outside your system.

Open-source AI agent framework with tamper-proof memory, cryptographic audit trail, and trust scoring. HIPAA, SOC2, GDPR, EU AI Act evidence-ready. Python, TypeScript, Docker.

Get Started · See It Work · Why Now · The Gap · vs Others · Docs

🚀 Get Started

pip install connector-agent-oss

from connector_agent_oss import Connector
import os

c = Connector("deepseek", "deepseek-chat", os.environ["DEEPSEEK_API_KEY"])
result = c.agent("bot", "You are helpful").run("Hello!", "user:alice")

That's it. 3 lines. Every response now includes:

• result.cid — tamper-proof content hash (CIDv1, SHA2-256)
• result.trust — kernel-verified trust score, 0–100
• **`result.audi