phi — security grade SAFE, quality 68/100

Security audit verdict: SAFE · quality 68/100

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 pulseaiclub · MCP Server · ★ 465

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

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

About phi

English | 中文 A lean, high-performance terminal coding agent harness in Go — a sibling to Pi. Docs: pulseaiclub.github.io Fast and small — 15 MB release binary, 21 MB idle RSS, 31 ms to first frame; no Node / Electron / Python runtime Sub-agents — spawn isolated jobs and watch the full run unfold in the TUI / job logs, without stuffing every tu

aiai-agentclaudeclaude-codeclicodexcodex-clicoding-agentdeepseekdeepseek-harness

Quick Facts

Stars465
Forks17
LanguageGo
CategoryMCP Server
LicenseMIT
Quality Score68.430783887529/100
Open Issues3
Last Updated2026-09-20
Created2026-08-03
Platformsclaude-code, cli, codex, go, mcp
Est. Tokens~21k

Compatible Skills

These tools work well together with phi for enhanced workflows:

  • DeepSeek-Code-Whale — semantic(0.43)+complementary+same_lang+similar_pop+shared_platform (65%)
  • Whale — semantic(0.43)+complementary+same_lang+similar_pop+shared_platform (65%)
  • dsh-cc-tui — semantic(0.57)+complementary+similar_pop+shared_platform (60%)
  • keen-code — semantic(0.28)+complementary+same_lang+similar_pop+shared_platform (60%)
  • lazyagent — semantic(0.24)+complementary+same_lang+similar_pop+shared_platform (58%)

phi alternative? Top 6 similar tools

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

  • agent-deck by asheshgoplani · ⭐ 928

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

  • codemap by JordanCoin · ⭐ 689

    a project brain for your AI. Give LLMs instant architectural context without burning tokens

  • hcom by aannoo · ⭐ 490

    Let AI agents message, watch, and spawn each other across terminals. Claude Code, Codex, Antigravity CLI, Curs

  • chief by MiniCodeMonkey · ⭐ 471

    Build big projects with Claude. Chief breaks your work into tasks and runs Claude Code in a loop until they're

  • golembot by 0xranx · ⭐ 320

    Any Agent × Any Provider × Anywhere. Connect Cursor, Claude Code, OpenCode, or Codex to Slack, Telegram, Disco

  • kasetto by pivoshenko · ⭐ 202

    📼 Declarative AI agent environment manager, written in Rust

More MCP Server Tools

Explore other popular mcp server tools:

View all MCP Server tools →

Popular Go Agent Tools

Frequently Asked Questions

What is phi?

phi is a coding agent, rpc plugin, sub-agents, hashline edits, and mcp. It is categorized as a MCP Server with 465 GitHub stars.

What programming language is phi written in?

phi is primarily written in Go. It covers topics such as ai, ai-agent, claude.

How do I install or use phi?

You can find installation instructions and usage details in the phi GitHub repository at github.com/pulseaiclub/phi. The project has 465 stars and 17 forks, indicating an active community.

What license does phi use?

phi is released under the MIT license, making it free to use and modify according to the license terms.

What are the best alternatives to phi?

The top alternatives to phi on Agent Skills Hub include agent-deck, codemap, hcom. 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