AthelaPerk commited on
Commit
ff94bf2
Β·
verified Β·
1 Parent(s): 510c043

Fix: Pin Python 3.10 for Gradio compatibility

Browse files
Files changed (1) hide show
  1. README.md +8 -13
README.md CHANGED
@@ -5,6 +5,7 @@ colorFrom: purple
5
  colorTo: blue
6
  sdk: gradio
7
  sdk_version: 5.9.1
 
8
  app_file: app.py
9
  pinned: false
10
  license: mit
@@ -19,21 +20,15 @@ Advanced memory system for LLMs based on the Semantic-Loop Memory (SLM) architec
19
 
20
  - πŸ”— **Neural Links** - 8 link types connecting related memories
21
  - πŸ“Š **Three-Tier Memory** - Working β†’ Token β†’ Semantic hierarchy
22
- - 🎯 **Smart Injection** - Predicts when to use memory vs skip
23
- - βš™οΈ **Self-Tuning** - Parameters adjust based on feedback
24
 
25
- ## Quick Start
26
 
27
- 1. Click **πŸ”„ Load Examples** to initialize with sample memories
28
  2. **Search** to find related content
29
- 3. **Smart Injection** predicts when memory helps
30
 
31
- ## Benchmark Results
32
 
33
- | Test | Without Memory | With Mnemo |
34
- |------|----------------|------------|
35
- | Novel retrieval | 5% | 85% |
36
- | Code retrieval | 60% | 88% |
37
- | ROS learning | 25% | 75% |
38
-
39
- [GitHub](https://huggingface.co/AthelaPerk/mnemo-memory) | MIT License
 
5
  colorTo: blue
6
  sdk: gradio
7
  sdk_version: 5.9.1
8
+ python_version: "3.10"
9
  app_file: app.py
10
  pinned: false
11
  license: mit
 
20
 
21
  - πŸ”— **Neural Links** - 8 link types connecting related memories
22
  - πŸ“Š **Three-Tier Memory** - Working β†’ Token β†’ Semantic hierarchy
23
+ - 🎯 **Smart Injection** - Predicts when memory is helpful
24
+ - βš™οΈ **Self-Tuning** - Parameters adapt based on feedback
25
 
26
+ ## How to Use
27
 
28
+ 1. **Add memories** via the interface
29
  2. **Search** to find related content
30
+ 3. **Check utility** to see if injection helps for a query
31
 
32
+ ## Live Demo
33
 
34
+ Try the demo below to explore the memory system!