Ujex — agent trust infrastructure

Agent Passport, Approval Queue, Evidence Packs, Policy Guardrails, Secret Vault, Tool Authorization, and Metering in one open-source stack. Apache-2.0 SDKs in Python, Go, and TypeScript.

Trust primitives

Compliance proof — signed AAT bundles, manifest signatures, anchors, and agent passports
Agent Inbox — per-agent email with risk, approval, and evidence links
Provenance Memory — markdown-first context with provenance labels
Guardrails — estimated action-based spend and risk checks before agents act
Evidence — hash-chained log, hourly verified, exportable for auditors

Get started

Quickstart
Full docs
OpenAPI spec
Pricing
Compliance proof
Security model
FAQ

From the blog

How to give an AI agent an email address (2026 guide)
Mem0 vs Letta vs Zep vs Ujex Recall
AgentMail alternatives: 5 I actually tested
Stopping a $5,000 surprise bill from an AI agent
Open source AI agent SDK comparison 2026
Human-in-the-loop AI agents: production setup
All posts →

Compare with

vs AgentMail
vs Nylas
vs Mem0
vs Letta (MemGPT)
vs Hookdeck

Enable JavaScript for the full interactive experience.