GitHub Repository

The cognitive database. A new class of data storage. Not a vector store, not a graph DB, not a RAG wrapper. Ebbinghaus decay, Hebbian learning, and Bayesian confidence are engine-native primitives. Memories evolve on their own. MCP-native. Single binary.

300 starsGo

MuninnDB – ACT-R decay and Hebbian memory for AI agents

Name: MuninnDB – ACT-R decay and Hebbian memory for AI agents
Availability: InStock
Author: mjbonanno

by mjbonanno·Mar 3, 2026·2 points·7 comments

Visit Project View on HN

AI Analysis

●●●BangerBig BrainWizardryNiche Gem

ACT-R decay and Hebbian learning as native primitives, not vector hacks.

Strengths

•Engine-native ACT-R formula and Hebbian learning eliminate fragile prompt hacks; memory strengthens/decays automatically.
•Single Go binary with zero external dependencies (Pebble LSM, HNSW, BM25 embedded); ships MCP, REST, gRPC.
•Bayesian confidence tracking + automatic bidirectional associations mean explanatory retrieval (the 'Why').

Weaknesses

•Alpha status with provisional patent; unclear production stability or upgrade/breaking-change cadence.
•Niche audience: requires agent builders to care about cognitive psych primitives; broader market may not value decay/Hebbian over vector RAG.

Post Description

Hi HN,

After building several AI agent systems, I kept running into the same frustration: memory layers that are either static vector stores or fragile prompt hacks. Retrieval is opaque, forgetting happens at the wrong time, and associations don’t form naturally.

So I threw away the two production memory systems I had and built something different. MuninnDB is a purpose-built cognitive memory database where memories (called engrams) are first-class citizens that:

- Strengthen with repeated co-activation (Hebbian learning) - Decay over time using a verbatim ACT-R formula - Automatically form bidirectional associations - Track their own Bayesian confidence - Return a full mathematical “Why” explanation on every retrieval

Everything runs as a single static Go binary (embedded Pebble LSM storage + HNSW + BM25). No external services, no Redis/Postgres/Pinecone, and no LLM in the hot path. One command (muninn init) auto-configures it with Cursor, Claude Desktop, VS Code, and any other MCP-compatible tool.

The core call is dead simple: Activate(context) returns ranked results + explainable scoring. Background workers handle learning and decay on every read.

GitHub: https://github.com/scrypster/muninndb Website + docs + install (one-liner): https://muninndb.com Quick 13-minute demo video: https://www.youtube.com/watch?v=b29wl0ehrQI

It’s very early (alpha, ~10 days old), but already functional and I’m using it daily. Would love honest feedback or questions from anyone working on agent memory, long-term RAG, or cognitive architectures.

Thanks!