paxm — security grade SAFE, quality 67/100

Security audit verdict: SAFE · quality 67/100

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 pax-beehive · MCP Server · ★ 433

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

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

About paxm

PAXM Stop re-explaining your project to every new coding-agent session. PAXM carries decisions, conventions, and working context into later Codex, Claude Code, OpenCode, Pi, and MCP sessions. Start locally with SQLite and no account, API key, embeddings, or extra memory-layer model calls. Change memory providers later without rewiring every agent. Install for Codex · Install the CLI · See the result · Docs · 中文 What changes after installation In one session, record a decision: In a later session, Codex, Claude Code, OpenCode, Pi, or an MCP client can recover it: With passive integration enabled, paxm recalls relevant context before t

agent-memoryai-agentsclaude-codecodexgolanglocal-firstmcpopencodesqlite

Quick Facts

Stars433
Forks21
LanguageGo
CategoryMCP Server
LicenseApache-2.0
Quality Score67.0712616241469/100
Open Issues3
Last Updated2026-08-28
Created2026-07-09
Platformsclaude-code, codex, go, mcp
Est. Tokens~19k

Compatible Skills

These tools work well together with paxm for enhanced workflows:

  • lazyagent — semantic(0.31)+complementary+same_lang+similar_pop+shared_platform (61%)
  • mainline — semantic(0.30)+complementary+same_lang+similar_pop+shared_platform (60%)
  • lazyagent — semantic(0.28)+complementary+same_lang+similar_pop+shared_platform (60%)
  • oc-go-cc — semantic(0.27)+complementary+same_lang+similar_pop+shared_platform (59%)
  • graymatter — semantic(0.26)+complementary+same_lang+similar_pop+shared_platform (59%)

paxm alternative? Top 6 similar tools

Looking for a paxm alternative? If you're comparing paxm 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.

  • memorix by AVIDS2 · ⭐ 791

    Open-source cross-agent memory layer for coding agents via MCP. Compatible with Claude Code, Codex, Cursor, Wi

  • agent-deck by asheshgoplani · ⭐ 928

    Terminal session manager for AI coding agents. One TUI for Claude, Gemini, OpenCode, Codex, and more.

  • OpenContext by 0xranx · ⭐ 729

    A personal context store for AI agents and assistants—reuse your existing coding agent CLI (Codex/Claude/OpenC

  • vestige by samvallad33 · ⭐ 628

    Cognitive Deterministic Memory Security OS for Agentic AI. Deterministic root-cause retrieval that reaches bac

  • Ori-Mnemos by aayoawoyemi · ⭐ 324

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

  • maestro by ReinaMacCredy · ⭐ 232

    Local-first coordination for human and agent work: durable work, decisions, dispatches, evidence, and prompt-f

More MCP Server Tools

Explore other popular mcp server tools:

View all MCP Server tools →

Popular Go Agent Tools

Frequently Asked Questions

What is paxm?

paxm is Persistent, provider-neutral memory for Codex, Claude Code, OpenCode, Pi, and MCP coding agents.. It is categorized as a MCP Server with 433 GitHub stars.

What programming language is paxm written in?

paxm is primarily written in Go. It covers topics such as agent-memory, ai-agents, claude-code.

How do I install or use paxm?

You can find installation instructions and usage details in the paxm GitHub repository at github.com/pax-beehive/paxm. The project has 433 stars and 21 forks, indicating an active community.

What license does paxm use?

paxm is released under the Apache-2.0 license, making it free to use and modify according to the license terms.

What are the best alternatives to paxm?

The top alternatives to paxm on Agent Skills Hub include memorix, agent-deck, OpenContext. 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