Progressive memory layer for AI agents with Header+Content indexing, chain recall, and file-first governance.
-
Updated
Apr 11, 2026 - Python
Progressive memory layer for AI agents with Header+Content indexing, chain recall, and file-first governance.
DRESS: A Continuous Framework for Structural Graph Refinement
Search private data inside your app. A fast local SDK for vector, BM25, hybrid, and graph-aware retrieval—no server, account, or API key.
Dynamic Segmented Memory (DSM): A hierarchical graph-based retrieval engine for scalable LLM context management and associative reasoning.
Structured memory for agents: weighted retrieval and replayable evidence paths
RAG-based method for mapping variables to PrimeKG subgraphs with textual graph descriptions.
The Memory of your Agent
Parameter inference of a synthetic graph generator for real-world multilayer networks
Research-grade neuro-symbolic RAG framework where retrieval is a policy, not a vector search, built for evaluation, ablation, and reliability analysis.
Local-first provenance memory and compaction recovery plugin for OpenAI Codex.
Topology-Aware Sparse Distributed Memory for knowledge graph retrieval. Binary 256-bit addresses combining SimHash content + weighted majority vote over 1-hop neighbors, plus classical quantum walk refinement. MRR=0.919 globally, MRR=1.000 in 50-node subgraphs. Python stdlib, no GPU, no API, no training. DOI: 10.5281/zenodo.19645323
个人 Agent 的可重放记忆引擎
Unified Hybrid Retrieval–Generation Architecture for Structured Domain Reasoning
Local SQLite memory for AI agents through MCP. Includes text search, bounded graph recall, and examples for hosted and local models.
To associate your repository with the graph-retrieval topic, visit your repo's landing page and select "manage topics."