| | --- |
| | license: mit |
| | tags: |
| | - memory |
| | - llm |
| | - rag |
| | - semantic-search |
| | --- |
| | |
| | # 🧠 Mnemo v4.1 - SLM-Inspired Memory System |
| |
|
| | Memory augmentation library for LLMs based on the Semantic-Loop Memory architecture. |
| |
|
| | ## Installation |
| |
|
| | ```python |
| | # Download mnemo.py from this repo |
| | from mnemo import Mnemo |
| | |
| | mnemo = Mnemo() |
| | mnemo.add("User prefers Python for data analysis") |
| | results = mnemo.search("programming language") |
| | ``` |
| |
|
| | ## Features |
| |
|
| | ### Core |
| | - **Three-Tier Memory**: Working (50 items) → Token Loops → Semantic (persistent) |
| | - **Neural Links**: 8 link types with different creation thresholds and decay rates |
| | - **Memory Utility Predictor**: Decides WHEN to inject memory (90% accuracy) |
| | - **Self-Tuning**: Auto-adjusts thresholds based on feedback |
| |
|
| | ### v4.1 New |
| | - **Memory Decay**: Unused memories lose 1% quality per day |
| | - **Auto-Pruning**: Removes stale memories (quality < 0.15, unused > 30 days) |
| | - **Link Cleanup**: Orphaned links removed when memories are pruned |
| |
|
| | ## Benchmark Results |
| |
|
| | | Test | Without Memory | With Mnemo | Improvement | |
| | |------|----------------|------------|-------------| |
| | | Novel retrieval | 5% | 85% | +80% | |
| | | Code retrieval | 60% | 88% | +28% | |
| | | ROS continuous learning | 25% | 75% | +50% | |
| |
|
| | ## API |
| |
|
| | ```python |
| | mnemo = Mnemo() |
| | mnemo.add(content, namespace="default") |
| | results = mnemo.search(query, top_k=5) |
| | context = mnemo.get_context(query, top_k=3) |
| | should_inject = mnemo.should_inject(query) |
| | mnemo.maintenance_cycle() |
| | ``` |
| |
|
| | ## Links |
| |
|
| | - [Demo](https://huggingface.co/spaces/AthelaPerk/mnemo) |
| | - [MCP Server](https://huggingface.co/spaces/AthelaPerk/mnemo-mcp) |
| |
|
