local-cocoa — security grade SAFE, quality 66/100

Security audit verdict: SAFE · quality 66/100

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 synvo-ai · Agent Tool · ★ 58

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

🔒 Is local-cocoa safe to install? View the security audit →

About local-cocoa

🍫 Local Cocoa: Your Personal Cowork, Fully Local 💻 []() []() []() []() 💻 Local Cocoa runs entirely on your device, not inside the cloud. 🧠 Each file turns into memory. Memories form context. Context sparks insight. Insight powers action. 🔒 No externals eyes. No data leaving. Just your computer learning you better, helping you smarter. 🎬 Live Demos | :

ai-agentsai-memoryai-toolscontextual-ailarge-language-modelsllmmultimodal-large-language-modelsvlm

Quick Facts

Stars58
Forks9
LanguageTypeScript
CategoryAgent Tool
LicenseMIT
Quality Score65.8058965687887/100
Last Updated2026-03-24
Created2026-01-03
Platformsnode
Est. Tokens~2744k

Compatible Skills

These tools work well together with local-cocoa for enhanced workflows:

  • Ori-Mnemos — semantic(0.23)+complementary+rare_topics+same_lang+similar_pop+shared_platform (58%)
  • mulch — semantic(0.23)+complementary+rare_topics+same_lang+similar_pop+shared_platform (57%)
  • ai-maestro — semantic(0.18)+complementary+rare_topics+same_lang+similar_pop+shared_platform (56%)
  • promptdesk — semantic(0.28)+complementary+same_lang+similar_pop+shared_platform (55%)

local-cocoa alternative? Top 6 similar tools

Looking for a local-cocoa alternative? If you're comparing local-cocoa 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.

  • claudepro-directory by JSONbored · ⭐ 217

    HeyClaude (formerly Claude Pro Directory) is a searchable collection of pre-built AI skills, agents, MCP serve

  • MinerU-Skill by Nebutra · ⭐ 94

    AI-Native document parser: PDF, Office & images → clean Markdown with LaTeX, tables & OCR. Zero-dependency CLI

  • multimind-sdk by multimindlab · ⭐ 93

    Your SDK solves all of this. One interface. Unified logic. Local + hosted models. Fine-tuning. Agent tools. En

  • roampal-core by roampal-ai · ⭐ 50

    Outcome-based persistent memory MCP server for Claude Code and OpenCode. Good advice promoted, bad advice demo

  • Awesome-LLM-Papers-Comprehensive-Topics by shure-dev · ⭐ 223

    Awesome LLM Papers and repos on very comprehensive topics.

  • omega-memory by omega-memory · ⭐ 218

    Persistent memory for AI coding agents

More Agent Tool Tools

Explore other popular agent tool tools:

View all Agent Tool tools →

Popular TypeScript Agent Tools

Frequently Asked Questions

What is local-cocoa?

local-cocoa is A local AI assistant running on your device. It turns your files into actionable memory.. It is categorized as a Agent Tool with 58 GitHub stars.

What programming language is local-cocoa written in?

local-cocoa is primarily written in TypeScript. It covers topics such as ai-agents, ai-memory, ai-tools.

How do I install or use local-cocoa?

You can find installation instructions and usage details in the local-cocoa GitHub repository at github.com/synvo-ai/local-cocoa. The project has 58 stars and 9 forks, indicating an active community.

What license does local-cocoa use?

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

What are the best alternatives to local-cocoa?

The top alternatives to local-cocoa on Agent Skills Hub include claudepro-directory, MinerU-Skill, multimind-sdk. 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