Skillget

roampal

mcp
Security Audit
Pass
Health Pass
  • License — License: NOASSERTION
  • Description — Repository has a description
  • Active repo — Last push 0 days ago
  • Community trust — 115 GitHub stars
Code Pass
  • Code scan — Scanned 12 files during light audit, no dangerous patterns found
Permissions Pass
  • Permissions — No dangerous permissions requested
Purpose
This is an AI memory tool that integrates via an MCP server. It learns from conversational feedback over time, retaining what works and discarding what doesn't to improve local LLM interactions without requiring users to repeat themselves.

Security Assessment
The project states it is completely private and runs 100% locally. It relies on local AI providers like Ollama or LM Studio, meaning data should not leave your machine. The automated code scan reviewed 12 files and found no dangerous patterns, hardcoded secrets, or requests for dangerous system permissions. Since it actively processes and stores user prompts, memories, and conversational outcomes, it handles conceptually sensitive data, but it keeps this workflow strictly on your local infrastructure. Overall risk: Low.

Quality Assessment
The project is highly active, with its most recent code push happening just today. It has built a solid early community, boasting 115 GitHub stars. The repository includes a detailed README featuring transparent benchmark results and clear setup instructions. The only minor drawback is that the automated check returned a "NOASSERTION" license status, likely due to a GitHub metadata parsing quirk, even though the README explicitly states the tool uses the standard Apache 2.0 license.

Verdict
Safe to use.
SUMMARY

Memory that learns what works.

README.md

Roampal

Status
Python 3.10+
Built with Tauri
Multi-Provider
License

Memory that learns what works.

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.

Roampal - AI Chat with Persistent Memory

85.8% non-adversarial on LoCoMo (1,986 questions). +23 pts over raw ingestion. Absorbs 1,135 poison memories losing only 4 pts. (Paper)

GitHub Stars

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

  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

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

Full MCP documentation →

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

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

Documentation

Document Description
Architecture 5-tier memory, knowledge graphs, technical deep-dive
Benchmarks LoCoMo evaluation, TagCascade results
Release Notes Latest: TagCascade Retrieval, Sidecar LLM, ONNX CE, Two-Lane Injection

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

Pricing

Free & open-source (Apache 2.0 License)

  • Build from source → completely free
  • Pre-built executable: $9.99 one-time (saves hours of setup)
  • Zero telemetry, full data ownership

Made with love for people who want AI that actually remembers

Reviews (0)

No results found