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 major7apps · MCP Server · ★ 80
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is pensyve safe to install? View the security audit →
Pensyve Universal memory runtime for AI agents. Framework-agnostic, protocol-native, offline-first. Without memory With Pensyve Your agent stops being amnesiac. Decisions, patterns, and outcomes persist across sessions — and the right context surfaces when it's needed. Why Pensyve How Pensyve solves it
| Stars | 80 |
| Forks | 11 |
| Language | Rust |
| Category | MCP Server |
| Quality Score | 65.8026394278954/100 |
| Open Issues | 19 |
| Last Updated | 2026-09-13 |
| Created | 2026-03-18 |
| Platforms | mcp, rust |
| Est. Tokens | ~27k |
Looking for a pensyve alternative? If you're comparing pensyve 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.
Memory that remembers the story not just the facts. File System Memory and Three layer sentence graph for AI
Local-first persistent agentic memory powered by Recursive Memory Harness (RMH). Open source must win.
🦀 Prevents outdated Rust code suggestions from AI assistants. This MCP server fetches current crate docs, use
Python library for building with LLMs. One interface across 11 providers (OpenAI, Anthropic, Gemini, DeepSeek,
Local, LLM-free memory for AI agents. A single offline Rust binary — deterministic and auditable — that learns
Persistent memory for AI coding agents
Explore other popular mcp server tools:
pensyve is Universal memory runtime for AI agents. It is categorized as a MCP Server with 80 GitHub stars.
pensyve is primarily written in Rust. It covers topics such as agent-memory, ai, ai-agents.
You can find installation instructions and usage details in the pensyve GitHub repository at github.com/major7apps/pensyve. The project has 80 stars and 11 forks, indicating an active community.
The top alternatives to pensyve on Agent Skills Hub include vektori, Ori-Mnemos, rust-docs-mcp-server. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
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: