aegis

Your agent's context is your attack surface. Act accordingly.

Secure context engineering for production AI agents.
Content security. Integrity verification. Trust hierarchy. Context that improves itself.

Find the unsafe memory writes in your agent (aegis inspect), then gate every write (aegis_memory.guard).

Website • Docs • Blog • Quickstart • Security Guide

---

The Problem Nobody Else Is Solving

Agents are getting compromised. Not theoretically — right now.

• EchoLeak (CVE-2025-32711, CVSS 9.3) — a single email triggered zero-click data exfiltration from Microsoft 365 Copilot[^echoleak]
• CrewAI + GPT-4o — researchers achieved 65% exfiltration success rate against multi-agent systems (COLM 2025)[^crewai]
• Drift chatbot cascade — one compromised chatbot integration cascaded into 700+ organizations via Salesforce, Google Workspace, Slack, S3, and Azure[^drift]
• OWASP Top 10 for Agentic Applications published December 2025 — memory and context manipulation is a top risk category[^owasp-top10]

Agent A's output is Agent B's instruction. Memory is the vector.

Every other memory layer trusts content by default. That is the vulnerability.

What Your Context Layer Is Missing

We audited the docs, repos, and changelogs of every major memory tool.[^comparison] These protections do not exist anywhere else:

Security Feature	mem0	Zep	Letta	Aegis
Content injection detection	—	—	—	4-stage pipeline
Memory integrity	—	—	—	HMAC-SHA256
Agent identity binding	—	—	—	Cryptographic API key
Trust hierarchy	—	—	—	4-tier OWASP model
Per-agent rate limiting	—	—	—	Sliding window
Security audit trail	—	—	—	Immutable event log
Sensitive data protection	—	—	—	Auto-detect + reject/redact/flag

Guard every write (the firewall)

One write boundary. Every source and agent funnels through a single Aegis guard — clean writes persist, poisoned writes are rejected and never stored.