# Immune

- **Event:** [The Persistent Context Sprint Hackathon | Live at MongoDB .Local Build Fest](https://cerebralvalley.ai/e/persistent-context-sprint-hackathon)
- **When:** Thu, Aug 13 at 12:30 – 8:00 PM (PDT)
- **Where:** Pier 48, San Francisco, CA
- **Team:** [Sameer Nagar](https://cerebralvalley.ai/u/sameernagar), [Abhishek Jani](https://cerebralvalley.ai/u/Abhishekjani), [Soham Jagrit](https://cerebralvalley.ai/u/sohamjagrit)
- **GitHub:** https://github.com/sameernagar-hub/immune
- **Demo video:** https://youtu.be/D2nTUuST3Uc
- **Gallery:** https://cerebralvalley.ai/e/persistent-context-sprint-hackathon/hackathon/gallery
- **Page:** https://cerebralvalley.ai/e/persistent-context-sprint-hackathon/hackathon/gallery/57

IMMUNE is a 5-call memory adapter (remember, derive, recall, guard, challenge) that immunizes AI agents against persistent memory poisoning.

When an agent reads untrusted input, IMMUNE records every stored claim with its full provenance tree in MongoDB Atlas. When a belief is refuted, IMMUNE executes a single $graphLookup aggregation pipeline to recursively traverse the provenance graph downward, revoking all derived contaminated beliefs in one transaction and reversing flagged side-effectful actions—leaving clean, unrelated memory branches completely untouched.

By enforcing trust floors directly at the database level via vector search pre-filtering (source_trust >= 0.5), poisoned context remains invisible to future agent sessions across cold restarts without relying on prompt rules or blocklists.

---

Markdown version of https://cerebralvalley.ai/e/persistent-context-sprint-hackathon/hackathon/gallery/57. Site index for agents: https://cerebralvalley.ai/llms.txt · full text: https://cerebralvalley.ai/llms-full.txt