Roampal
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<0.0001) |
| Poison resilience | -4.2 pts after 1,135 adversarial memories |
| No-memory baseline | 6.0% (model has zero LoCoMo knowledge) |
| Architecture vs model | Architecture: +23 pts. Model swap (GPT-4o-mini): 1.5-2.5 pts |
- System learns through natural conversation, not transcript ingestion
- Absorbs 1,135 poison memories with spoofed trust signals, retaining 72.4% accuracy
- Wilson scoring hurts retrieval at every stage (p<0.001) — removed from ranking
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<0.0001 |
- Cross-encoder: +17.8 Hit@1 over cosine (p<0.0001)
- Tag routing (two-lane): +6.1 Hit@1 clean, +7.5 poison (p<0.0001)
- Wilson: -4.3 Hit@1 in every configuration
- Nursery slot: zero benefit (p=1.0)
Full methodology in roampal-labs
Quick Start
- Download from roampal.ai and extract
- Install Ollama or LM Studio
- Right-click
Roampal.exe→ Run as administrator - Download a model in the UI → Start chatting!
Your AI starts learning about you immediately.
Table of Contents
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.
Settings → Integrations → Connect → Restart your tool
7 tools available: search_memory, add_to_memory_bank, update_memory, archive_memory, get_context_insights, record_response, score_memories
Architecture
┌─────────────────────────────────────────────────────────┐
│ 5-TIER MEMORY │
├─────────────┬─────────────┬─────────────┬──────────────┤
│ Books │ Working │ History │ Patterns │
│ (permanent) │ (24h) │ (30 days) │ (permanent) │
├─────────────┴─────────────┴─────────────┴──────────────┤
│ Memory Bank │
│ (permanent user identity/prefs) │
└─────────────────────────────────────────────────────────┘
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
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 |
Documentation
| Document | Description |
|---|---|
| Architecture | 5-tier memory, retrieval pipeline, technical deep-dive |
| Benchmarks | LoCoMo evaluation, TagCascade results |
| Release Notes | Latest (v0.3.3): multimodal image input, dynamic capability + context detection, ChromaDB phantom-handling closing issue #8, atomic config writes, Harmony token cleanup |
Important Notices
AI Safety: LLMs may generate incorrect information. Always verify critical information. Don't rely on AI for medical, legal, or financial advice.
Model Licenses: Downloaded models (Llama, Qwen, etc.) have their own licenses. Review before commercial use.
Support
- Discord: https://discord.gg/F87za86R3v
- Email: roampal@protonmail.com
- GitHub: https://github.com/roampal-ai/roampal/issues
- Author: Logan Teague
Pricing
Free & open-source (Apache 2.0 License)
- Build from source → completely free
- Pre-built executable: $19.99 one-time (saves hours of setup)
- Zero telemetry, full data ownership
Made with love for people who want AI that actually remembers