GitHub Repository

Open-source causal graph memory for AI agents. 89.9% on LoCoMo. MCP server with ACT-R scoring, spreading activation, and active forgetting.

16 starsPython

Genesys – Causal graph memory for AI agents, not just vectors

Name: Genesys – Causal graph memory for AI agents, not just vectors
Availability: InStock
Author: rmm2496

by rmm2496·Apr 26, 2026·1 point·0 comments

Visit Project View on HN

AI Analysis

●●SolidBig BrainNiche Gem

ACT-R scoring and active forgetting beat standard vector similarity for agent context.

Strengths

•Implements ACT-R scoring formulas instead of relying solely on vector similarity.
•Native MCP server support means easy integration with existing agent workflows.
•Active forgetting lifecycle prevents context window drowning from stale memories.

Weaknesses

•AI memory space is crowded with established players like Mem0 and Zep.
•Causal graph overhead might be overkill for simple chatbot use cases.

Similar Projects

AI/ML●●Solid

AgentKV – SQLite for AI agent memory (MMAP vector+graph DB)

Single-file mmap storage plus an HNSW vector index and explicit graph edges is an elegant, practical combo — think "SQLite for agent memory" with CRC-32 crash recovery and zero-server convenience. The C++20 core + nanobind gives zero-copy NumPy views and GIL-free searches, and the claimed FAISS-like throughput makes this genuinely interesting for local setups; main caveat is build/toolchain friction and how rich the surrounding ecosystem becomes.

WizardryNiche Gem

shiwang_khera

104mo ago

AI/ML●●●Banger

ClawMem – Open-source agent memory with SOTA local GPU retrieval

Fuses 5 research papers into local agent memory that actually persists across sessions.

Big BrainDark HorseZero to One

yoloshii

502mo ago

AI/ML●●Solid

AI memory with biological decay (52% recall)

Ebbinghaus forgetting curve cuts token waste 84% while doubling recall versus Zep.

Big BrainShip It

SachitRafa

98531mo ago

AI/ML●●Solid

Memgraph-agent – NER+PageRank memory for AI agents, $0 LLM cost

NER+PageRank graph memory beats vectors on speed, but GraphRAG and Mem0 already handle multi-hop reasoning.

Big BrainNiche GemShip It

yangyihe0305

103mo ago

Developer Tools●●●Banger

FlowScript – Agent memory where contradictions are features

Five queries vector stores can't answer: why(), tensions(), blocked(), whatIf(), alternatives().

Big BrainZero to OneWizardry

phillipclapham

212mo ago

AI/ML●●Solid

AFS – filesystem-native memory layer for AI agents

Putting the memory layer on-disk as a .afs/ tree is a gutsy, practical move — you get searchable JSON, FTS5 for text queries, HNSW vectors for similarity, and msgpack edges for relationships without running a separate DB service. It feels like a thoughtful toolkit for agents that must persist thinking artifacts (observations → reflections → knowledge), though I want to see details on concurrency, index portability, and how this performs at scale before betting production workloads on it.

Big BrainBold Bet

thompson0012

203mo ago