kept — security grade SAFE, quality 72/100

Security audit verdict: SAFE · quality 72/100

Flagged: sudo usage. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →

by egroup-labs · MCP Server · ★ 118

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

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

About kept

Kept Kept saves your AI conversations as local Markdown files, then gives you a desktop app to search, browse, connect, and reuse them. It works with ChatGPT, Claude, Gemini, Grok, and Kimi. Your archive lives on your machine under , with an Obsidian-compatible vault plus local indexes for full-text search, topics, projects, and graph views. Quick Install MCP server Why Kept AI chats often become working memory: debugging trails, research notes, product decisions, prompts, snippets, and half-finished ideas. Most of that history stays inside vendor UIs. Kept turns it into files you own. Plain Markdown, grouped by provider. Fast local search with SQLite FTS5. Graph and topic views f

chrome-extensionclaude-codeknowledge-graphknowledge-managementlocal-firstmcp-serverobsidian

Quick Facts

Stars118
Forks9
LanguageTypeScript
CategoryMCP Server
LicenseMIT
Quality Score71.5843362359306/100
Open Issues5
Last Updated2026-06-15
Created2026-05-02
Platformsbrowser, claude-code, gemini, mcp, node
Est. Tokens~1029k

Compatible Skills

These tools work well together with kept for enhanced workflows:

  • ctxport — semantic(0.30)+complementary+rare_topics+same_lang+similar_pop+shared_platform (60%)
  • graph-memory — semantic(0.21)+complementary+same_lang+similar_pop+shared_platform (57%)
  • ai-chat-speed-booster — semantic(0.21)+complementary+rare_topics+same_lang+similar_pop+shared_platform (57%)
  • enzyme — semantic(0.27)+complementary+same_lang+similar_pop+shared_platform (55%)

kept alternative? Top 6 similar tools

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

  • omega-memory by omega-memory · ⭐ 219

    Persistent memory for AI coding agents

  • enzyme by jshph · ⭐ 51

    A compile step for knowledge bases. Gives your agent a concept graph of your content — under 20s to index, 8ms

  • octocode by Muvon · ⭐ 477

    Structural code intelligence for AI agents — semantic search, knowledge graphs, and a built-in MCP server in o

  • agent-second-brain by smixs · ⭐ 367

    An always-on second brain you talk to. Voice notes in Telegram → typed, linked knowledge in your Obsidian vaul

  • zettelkasten-mcp by entanglr · ⭐ 164

    A Model Context Protocol (MCP) server that implements the Zettelkasten knowledge management methodology, allow

  • skill-conductor by smixs · ⭐ 160

    Architecture-first skill lifecycle for AI agents. BinEval binary scoring with threshold-blind, cross-family-ca

More MCP Server Tools

Explore other popular mcp server tools:

View all MCP Server tools →

Popular TypeScript Agent Tools

Frequently Asked Questions

What is kept?

kept is Search, archive, and recall your AI conversations. ChatGPT, Claude, Gemini, Grok, Kimi. Local-first, MIT licensed.. It is categorized as a MCP Server with 118 GitHub stars.

What programming language is kept written in?

kept is primarily written in TypeScript. It covers topics such as chrome-extension, claude-code, knowledge-graph.

How do I install or use kept?

You can find installation instructions and usage details in the kept GitHub repository at github.com/egroup-labs/kept. The project has 118 stars and 9 forks, indicating an active community.

What license does kept use?

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

What are the best alternatives to kept?

The top alternatives to kept on Agent Skills Hub include omega-memory, enzyme, octocode. 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