tunacode — security grade SAFE, quality 76/100

Security audit verdict: SAFE · quality 76/100

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 alchemiststudiosDOTai · Agent Tool · ★ 124

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

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

About tunacode

tunacode-cli A terminal-based AI coding agent with a NeXTSTEP-inspired interface. Early stage software — not production ready. Under active development, expect bugs and breaking changes. Features Any model - Works with any OpenAI-compatible API File operations - Read files with hash-tagged lines, create files, and edit existing files with hash-validated references Shell access - Run bash commands with output capture Repository discovery - Use for natural-language code search and repository exploration Session persistence - Resume previous conversations with Themeable UI - CSS-based theming with NeXTSTEP-inspired design Text selection + clipboard copy - Mouse selection works across Rich-rendered chat content; copy with or Agent loop - Powered by [tinyAgent](https://github.com/alchemiststudio

agentaianthropicclaude-codeclideveloper-toolsllmopenai

Quick Facts

Stars124
Forks27
LanguagePython
CategoryAgent Tool
LicenseMIT
Quality Score76.274313580326/100
Open Issues5
Last Updated2026-07-12
Created2025-05-28
Platformsclaude-code, cli, python
Est. Tokens~15k

tunacode alternative? Top 6 similar tools

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

  • claude-code-open by kill136 · ⭐ 158

    Open source AI coding platform with Web IDE, multi-agent system, 37+ tools, MCP protocol. MIT licensed.

  • claude-historian-mcp by Vvkmnn · ⭐ 178

    📜 An MCP server for conversation history search and retrieval in Claude Code

  • claude-emporium by Vvkmnn · ⭐ 82

    🏛 [UNDER CONSTRUCTION] A (roman) claude plugin marketplace

  • claude-code-mastery by TheDecipherist · ⭐ 548

    The complete guide to Claude Code: CLAUDE.md, hooks, skills, MCP servers, and commands

  • agnix by agent-sh · ⭐ 422

    The missing linter and lsp for AI coding assistants. Validate CLAUDE.md, AGENTS.md, SKILL.md, hooks, MCP. Plug

  • oreilly-ai-agents by sinanuozdemir · ⭐ 299

    An introduction to the world of AI Agents

More Agent Tool Tools

Explore other popular agent tool tools:

View all Agent Tool tools →

Popular Python Agent Tools

Frequently Asked Questions

What is tunacode?

tunacode is 🍣 TunaCode AI CLI coding agent with safe git branches, rich tools & multi-LLM support.. It is categorized as a Agent Tool with 124 GitHub stars.

What programming language is tunacode written in?

tunacode is primarily written in Python. It covers topics such as agent, ai, anthropic.

How do I install or use tunacode?

You can find installation instructions and usage details in the tunacode GitHub repository at github.com/alchemiststudiosDOTai/tunacode. The project has 124 stars and 27 forks, indicating an active community.

What license does tunacode use?

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

What are the best alternatives to tunacode?

The top alternatives to tunacode on Agent Skills Hub include claude-code-open, claude-historian-mcp, claude-emporium. 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 Agent Tool tools