Roampal
以下摘录自该仓库的 README(片段) · 在 GitHub 读完整 README →
**Memory that learns what works. So you can do more of it.**
*Say it worked. Say it didn't. The AI remembers.*
Stop re-explaining yourself every conversation. Roampal remembers outcomes, learns from feedback, and gets smarter over time—all 100% private and local.
> **85.8% non-adversarial on LoCoMo (1,986 questions). +23 pts over raw ingestion. Absorbs 1,135 poison memories losing only 4 pts.** (Paper)
---
Benchmark Results
*LoCoMo dataset (1,986 questions, 5 categories, corrected ground truths). Evaluated with roampal-labs. Dual-graded by local 20B + MiniMax M2.7.*
| Metric | Result |
|--------|--------|
| **Non-adversarial accuracy (MiniMax-regraded)** | **85.8%** |
| **Overall (all 5 categories)** | **76.6%** |
| **vs raw ingestion baseline** | **+23 pts** (76.6% vs 53.0%, p
Component-level retrieval ablation
| Config | Hit@1 Clean | Hit@1 Poison | p-value |
|--------|-------------|--------------|---------|
| **TagCascade + cosine** | **27.3%** | **29.0%** | **baseline** |
| Overlap + cosine | 25.8% | 28.0% | p=0.0003 |
| Pure CE | 25.4% | 28.4% | — |
| TagCascade + Wilson | 23.0% | 25.0% | p
---
Quick Start
1. **Download from roampal.ai** and extract
2. Install Ollama or LM Studio
3. Right-click Roampal.exe → **Run as administrator**
4. Download a model in the UI → Start chatting!
Your AI starts learning about you immediately.
---
Table of Contents
- Benchmark Results
- Key Features
- MCP Integration
- Architecture
- Supported Models
- Documentation
- Pricing
---
Key Features
**Memory That Learns**
- Outcome tracking: Scores every result (+0.2 worked, -0.3 failed)
- Smart promotion: Good advice becomes permanent, bad advice auto-deletes
- Cross-conversation: Recalls from ALL past chats
**Your Knowledge Base**
- Memory Bank: Permanent storage of preferences, identity, goals
- Books: Upload .txt/.md docs as searchable reference
- Pattern recognition: Detects what works across conversations
**Privacy First**
- 100% local: All data on your machine
- Works offline: No internet after model download
- No telemetry: Your data never leaves your computer
---
MCP Integration
Connect Roampal to **Claude Desktop, Cursor**, and other MCP-compatible tools.
**7 tools available**: search_memory, add_to_memory_bank, update_memory, archive_memory, get_context_insights, record_response, score_memories
Full MCP documentation →
---
Architecture
**Core Technology:**
- TagCascade Retrieval: Tag-routed search + cross-encoder reranking (ONNX)
- Outcome-Based Learning: Memories adapt based on feedback
- Sidecar LLM: Background model summarizes exchanges, extracts facts and tags
Architecture deep-dive →
---
Supported Models
Works with any tool-calling model via Ollama or LM Studio:
| Model | Provider | Parameters |
|-------|----------|------------|
| Llama 3.x | Meta | 3B - 70B |
| Qwen 2.5 | Alibaba | 3B - 72B |
| Mistral/Mixtral | Mistral AI | 7B - 8x22B |
| GPT-OSS | OpenAI (Apache 2.0) | 20B - 120B |