repoGitHubTrust 82 · PrimaryPublished 1mo agoLive · 1mo ago
ardhaecosystem/synapse
Synapse — Temporal knowledge graph memory for AI agents. Self-hosted FalkorDB + Graphiti with hippocampus-layer memory management.
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- LinkedLinked via unknownAI agents need context everywhere they run, even where the cloud can't follow →
- LinkedLinked via unknownEmpowering biomedical evidence exploration and synthesis with deep knowledge graph research →
- PossiblePossibly related (embedding) · 58%MRMS: A Multi-Resolution Memory Substrate for Long-Lived AI Agents →
- PossiblePossibly related (embedding) · 47%Nested Episodic State Topology (NEST): A Graph-Theoretic Architecture of Cognitive States →
- PossiblePossibly related (embedding) · 63%The biggest problem with AI memory isn't recall—it's stale facts [P] →
- PossiblePossibly related (embedding) · 50%Show HN: What 180k words look like as a temporal knowledge graph (Oz series) →
Covers (incoming)
newsAI agents need context everywhere they run, even where the cloud can't follownewsEmpowering biomedical evidence exploration and synthesis with deep knowledge graph researchnewsThe biggest problem with AI memory isn't recall—it's stale facts [P]newsShow HN: What 180k words look like as a temporal knowledge graph (Oz series)
Implements (incoming)
Related across the graph
newsAI agents need context everywhere they run, even where the cloud can't followpaperMRMS: A Multi-Resolution Memory Substrate for Long-Lived AI AgentsnewsEmpowering biomedical evidence exploration and synthesis with deep knowledge graph researchpaperNested Episodic State Topology (NEST): A Graph-Theoretic Architecture of Cognitive StatesnewsThe biggest problem with AI memory isn't recall—it's stale facts [P]newsShow HN: What 180k words look like as a temporal knowledge graph (Oz series)