Show HN: Aegis Memory v1.2 – We solved "what's worth remembering" for AI agents

[Arulnidhi_k]

Aegis Memory is an open-source, self-hostable memory layer for multi-agent AI systems.

v1.2 adds Smart Memory - a two-stage pipeline that automatically decides what's worth storing: 1. Fast rule-based filter catches obvious noise (greetings, "thanks", etc.) 2. LLM extracts atomic facts only when the filter passes

This saves ~70% of extraction costs while keeping memory high-quality.

Try it in 15 seconds: pip install aegis-memory aegis demo

GitHub: https://github.com/quantifylabs/aegis-memory

Happy to answer questions about multi-agent memory architecture.

[austinbaggio]

Are you working with any projects to implement this yet?

[Arulnidhi_k]

Not yet in production, but actively looking for devs to test it and gain feedback..

[dmarwicke]

memory voting sounds interesting but does it work? i tried having agents mark useful chunks once, they just marked everything as helpful. accuracy went to shit

[Arulnidhi_k]

Voting requires context.agents must specify 'why' something was helpful, not just thumbs up/down. This adds friction that reduces noise.

Here's the Effectiveness score that is implemented in the project: (helpful - harmful) / (total + 1), so marking everything helpful dilutes the signal rather than inflating it.

Along with it gotta pair voting with reflections, agents store "this worked because of X" not just "this worked."

May I know what setup you tried.. was it a single agent or multi-agent?