Show HN: Supe – Give your AI agent a brain, not just memory(github.com)
github.com
Show HN: Supe – Give your AI agent a brain, not just memory
https://github.com/xayhemLLC/supe
3 comments
Interesting approach. I've been experimenting with AI for content schema generation in a CMS context - the challenge is always balancing AI suggestions with deterministic output that developers can trust.
How do you handle cases where the "brain" makes decisions that need to be auditable or reversible?
How do you handle cases where the "brain" makes decisions that need to be auditable or reversible?
Doesn't look like a brain to me.
It looks like a few lines of python code written by a desperate human being, who has introjected all the hype and is projecting his own fantasies into, and onto, an autocomplete machine.
There is no spoon and there is no brain.
It looks like a few lines of python code written by a desperate human being, who has introjected all the hype and is projecting his own fantasies into, and onto, an autocomplete machine.
There is no spoon and there is no brain.
The problem: Most agent frameworks treat memory as flat storage. Store a key, get a value. That's not how useful memory works.
What Supe provides:
1. Neural Memory - Hebbian learning ("fire together, wire together"). Cards connected by synaptic links that strengthen with co-activation and decay with disuse. Spreading activation for recall. Hubs emerge naturally.
2. Validation Gates - Python functions that run before/after tool executions. Block `rm -rf`, enforce read-only mode, whitelist commands. Code, not configuration.
3. Proof-of-Work - SHA256 hashes chain every execution. Tamper with logs and proofs won't verify.
4. Cognitive Hierarchy - Moments (sessions) → Cards (knowledge units) → Buffers (raw data). Not flat.
5. Semantic Relations - 7 typed connections: CAUSES, IMPLIES, CONTRADICTS, SUPPORTS, DEPENDS_ON, EQUALS, TRANSFORMS.
Example gate:
Example neural recall:
343 tests. MIT license. Works with Claude SDK.
pip install supe