IdeaCredIdeaCred

Long-term conversational memory system for AI agents — cell-based architecture with hybrid BM25 + semantic retrieval. 96% accuracy on LoCoMo benchmark.

What's novel

Long-term conversational memory system for AI agents — cell-based architecture with hybrid BM25 + semantic retrieval. 96% accuracy on LoCoMo benchmark.

Code Analysis

8 files read · 3 rounds

A structured long-term conversational memory system for LLMs that encodes entities, temporal relationships, negations, and causal links at ingestion time into a unified multi-graph, then uses multi-strategy retrieval (vector, BM25, entity graph, temporal, hierarchical) with LLM-driven planning, atte

Strengths

Genuinely deep implementation with a coherent write-path (regex NER, temporal parsing, negation detection, causal hints) and read-path (8+ retrieval strategies, attention filter, agentic loop) that are well-integrated. The negation-as-first-class-citizen design threaded through extraction, storage, and retrieval is a thoughtful approach to adversarial robustness that most memory systems lack.

Weaknesses

The core NER and relation extraction is entirely regex-based, which is brittle on unusual phrasing and limits generalization; the LLM-dependent features (query planner, LLM reranker, LLM fact extraction) are all optional and off by default, meaning the 'intelligent' parts require external API calls. The benchmark claims (88.67% on LoCoMo) are not independently verifiable from the code alone and the evaluation harness was not fully readable.

Score Breakdown

Innovation
6 (25%)
Craft
77 (35%)
Traction
17 (15%)
Scope
83 (25%)

Signal breakdown

Innovation

Not Fork+1
Code Novelty+1
Concept Novelty+2

Craft

Ci+5
Tests+8
Polish+3
Releases+1
Has License+5
Code Quality+23
Readme Quality+15
Recent Activity+7
Structure Quality+5
Commit Consistency+0
Has Dependency Mgmt+5

Traction

Forks+6
Stars+6
Hn Points+0
Watchers+0
Early Traction+5
Devto Reactions+0
Community Contribs+0

Scope

Commits+7
Languages+3
Subsystems+13
Bloat Penalty+0
Completeness+7
Contributors+5
Authored Files+15
Readme Code Match+3
Architecture Depth+7
Implementation Depth+8

Evidence

Commits

29

Contributors

1

Files

93

Active weeks

2

TestsCI/CDREADMELicenseContributing

Repository

Language

Python

Stars

3

Forks

1

License

MIT