Agentmem

C 66 completed
Ai Ml
cli / python · tiny
22
Files
7,453
LOC
0
Frameworks
4
Languages

Pipeline State

completed
Run ID
#368386
Phase
done
Progress
1%
Started
Finished
2026-04-13 01:31:02
LLM tokens
0

Pipeline Metadata

Stage
Cataloged
Decision
proceed
Novelty
53.02
Framework unique
Isolation
Last stage change
2026-05-10 03:35:02
Deduplication group #48296
Member of a group with 18 similar repo(s) — canonical #21216 view group →
Top concepts (2)
Project DescriptionWeb Backend
Methodology: Repobility · https://repobility.com/research/state-of-ai-code-2026/

AI Prompt

Create a lightweight, persistent memory solution for AI agents using Python. I need the core functionality to support hybrid search, combining FTS5 full-text keyword search with vector semantic search. The system should manage memory across different tiers like 'core', 'learned', and 'episodic', and support namespaces for isolation. Ideally, it should also provide an HTTP REST API with several endpoints, and include features for entity extraction and conversation extraction. The implementation should be robust enough to run from a single SQLite file.
python cli sqlite ai-agent memory hybrid-search rest-api nlp
Generated by gemma4:latest

Catalog Information

agentmem-lite is a lightweight persistent memory solution designed for use in AI agent applications, providing a compact and efficient storage option.

Description

Agentmem-lite is a lightweight persistent memory solution that enables AI agents to store and retrieve data efficiently. It uses a single SQLite file and supports up to 16 tools, making it suitable for various AI applications. The project's goal is to provide a zero-to-12MB footprint, catering to the needs of resource-constrained environments.

الوصف

هو حل ذاكرة مستدام خفيف الوزن يسمح لل एजينتس الذكية بالتخزين والاسترجاع البيانات بفعالية. يستخدم ملف SQLite واحد ويدعم حتى 16 أداة، مما يجعلها مناسبة للاستخدام في تطبيقات الذكاء الاصطناعي المختلفة. الهدف من المشروع هو تقديم footprint من صفر إلى 12 ميجا بايت، مما يلبي احتياجات البيئات التي تحتوي على موارد محدودة.

Novelty

7/10

Tags

persistent-memory ai-agents data-storage sqlite lightweight-solution resource-constrained-environments

Technologies

numpy

Claude Models

claude-opus-4.6

Quality Score

C
66.3/100
Structure
70
Code Quality
61
Documentation
65
Testing
60
Practices
61
Security
92
Dependencies
60

Strengths

  • Code linting configured (ruff (possible))
  • Consistent naming conventions (snake_case)
  • Good security practices \u2014 no major issues detected
  • Containerized deployment (Docker)
  • Properly licensed project

Weaknesses

  • No CI/CD configuration \u2014 manual testing and deployment
  • 727 duplicate lines detected \u2014 consider DRY refactoring
  • 2 'god files' with >500 LOC need decomposition

Recommendations

  • Set up CI/CD (GitHub Actions recommended) to automate testing and deployment

Security & Health

7.3h
Tech Debt (C)
A
OWASP (100%)
PASS
Quality Gate
A
Risk (2)
Open data scored by Repobility · https://repobility.com
MIT
License
1.7%
Duplication
Full Security Report AI Fix Prompts SARIF SBOM

Languages

python
95.6%
markdown
2.9%
json
1.0%
toml
0.6%

Frameworks

None detected

Concepts (2)

Generated by the Repobility scanner · https://repobility.com
CategoryNameDescriptionConfidence
Repobility · open methodology · https://repobility.com/research/
auto_descriptionProject Descriptionmcp-name: io.github.oxgeneral/agentmem80%
auto_categoryWeb Backendweb-backend70%

Quality Timeline

1 quality score recorded.

View File Metrics

Embed Badge

Add to your README:

![Quality](https://repos.aljefra.com/badge/92584.svg)
Quality BadgeSecurity Badge
Export Quality CSVDownload SBOMExport Findings CSV