Asa4214/hce

Manage AI assistant memory by retrieving only the most relevant past interactions to keep context clear and focused.

What's novel

Manage AI assistant memory by retrieving only the most relevant past interactions to keep context clear and focused.

Code Analysis

8 files read · 3 rounds

A Python middleware library that provides persistent structured memory for LLMs using three complementary structures (entity graph with spreading activation, semantic tree with hierarchical search, and sliding focus buffer) exposed as MCP tools for Claude Code integration.

Strengths

Clean architecture with proper separation of concerns, comprehensive test suite covering edge cases, and practical MCP server implementation with file locking and state persistence. The multi-language project crawler and context budgeting algorithm show real implementation depth.

Weaknesses

The README is severely misleading, describing a Windows installer product when this is a Python library requiring pip installation. Entity extraction relies on basic regex patterns that will have significant false positives and missed entities, limiting real-world effectiveness.

Score Breakdown

Innovation

3 (25%)

Craft

48 (35%)

Traction

6 (15%)

Scope

34 (25%)

Signal breakdown

Innovation

Not Fork+1

Code Novelty+1

Concept Novelty+0

Craft

Ci+0

Tests+0

Polish+0

Releases+0

Has License+0

Code Quality+25

Readme Quality+15

Recent Activity+7

Structure Quality+5

Commit Consistency+0

Has Dependency Mgmt+5

Traction

Forks+0

Stars+6

Hn Points+0

Watchers+0

Early Traction+0

Devto Reactions+0

Community Contribs+2

Scope

Commits+3

Languages+3

Subsystems+5

Bloat Penalty+0

Completeness+6

Contributors+6

Authored Files+8

Readme Code Match+3

Architecture Depth+3

Implementation Depth+8

Evidence

Commits

Contributors

Files

Active weeks

TestsCI/CDREADMELicenseContributing

Repository

Language

Python

Stars

Forks

License

—