roampal — security grade SAFE, quality 62/100

Security audit verdict: SAFE · quality 62/100

No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →

by roampal-ai · MCP Server · ★ 125

Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h

🔒 Is roampal safe to install? View the security audit →

About roampal

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. Re

ai-assistantai-memorychromadbdesktop-appllmlm-studiolocal-ailocal-llmmcp-servermodel-context-protocol

Quick Facts

Stars125
Forks21
LanguagePython
CategoryMCP Server
Quality Score61.8102667174116/100
Last Updated2026-05-12
Created2025-10-26
Platformsmcp, python
Est. Tokens~551k

Compatible Skills

These tools work well together with roampal for enhanced workflows:

  • SuperPowersWUI — semantic(0.19)+complementary+rare_topics+same_lang+similar_pop+shared_platform (61%)
  • codec — semantic(0.27)+complementary+rare_topics+same_lang+similar_pop+shared_platform (59%)
  • Deus — semantic(0.35)+complementary+same_lang+similar_pop+shared_platform (57%)

roampal alternative? Top 6 similar tools

Looking for a roampal alternative? If you're comparing roampal with other mcp server tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.

  • lilbee by tobocop2 · ⭐ 57

    The whole local AI stack in one executable: it runs and manages local AI models across every GPU, and it's a s

  • Ori-Mnemos by aayoawoyemi · ⭐ 324

    Local-first persistent agentic memory powered by Recursive Memory Harness (RMH). Open source must win.

  • guaardvark by guaardvark · ⭐ 228

    The self-hosted AI studio: local video, image, music, voice, LoRA training, coding swarms, RAG and screen agen

  • omega-memory by omega-memory · ⭐ 218

    Persistent memory for AI coding agents

  • memcord by ukkit · ⭐ 73

    🧠 Self-hosted, privacy-first MCP server for long-term AI memory — save, search & summarize Claude/ChatGPT cha

  • ctxvault by Filippo-Venturini · ⭐ 60

    Local memory infrastructure for AI agents. Store knowledge and skills in isolated vaults you compose, control

More MCP Server Tools

Explore other popular mcp server tools:

View all MCP Server tools →

Popular Python Agent Tools

Frequently Asked Questions

What is roampal?

roampal is Memory that learns what works.. It is categorized as a MCP Server with 125 GitHub stars.

What programming language is roampal written in?

roampal is primarily written in Python. It covers topics such as ai-assistant, ai-memory, chromadb.

How do I install or use roampal?

You can find installation instructions and usage details in the roampal GitHub repository at github.com/roampal-ai/roampal. The project has 125 stars and 21 forks, indicating an active community.

What are the best alternatives to roampal?

The top alternatives to roampal on Agent Skills Hub include lilbee, Ori-Mnemos, guaardvark. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.

How this security grade is produced

Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.

The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.

Sources & who's responsible:

View on GitHub → Browse MCP Server tools