gini-agent — security grade SAFE, quality 66/100

Security audit verdict: SAFE · quality 66/100

Flagged: opens a tunnel service. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →

by Open-Curiosity · MCP Server · ★ 2.3k

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

🔒 Is gini-agent safe to install? View the security audit →

About gini-agent

Gini Agent Gini Agent is a personal agent that remembers, improves, and runs without forcing you to read a log line. Gini is not just a chat box, CLI, messaging bot, or pile of tools. Chat is an interaction surface. The runtime is the system of record for conversations, runs, tasks, approvals, memory, skills, jobs, tools, traces, audit events, and runtime health. It's also built to be a product, not plumbing. When the agent needs you, it hands you a purpose-built control right where the work is — a secure field, a choice, a sign-in handoff, a confirm-before-send — instead of a prose instruction or a detour. And because every client speaks the same runtime, those controls reach you on your phone as readily as the desktop, so the machine the agent runs on is not where you have to be.

agentagent-runtimeai-agentbunllmlocal-firstmcpnextjspersonal-agenttypescript

Quick Facts

Stars2,259
Forks839
LanguageTypeScript
CategoryMCP Server
LicenseMIT
Quality Score66.1571587075651/100
Open Issues27
Last Updated2026-07-18
Created2026-05-05
Platformsmcp, node
Est. Tokens~17k

Compatible Skills

These tools work well together with gini-agent for enhanced workflows:

  • gini-agent — semantic(1.00)+rare_topics+same_lang+similar_pop+shared_platform (65%)
  • gini-agent — semantic(1.00)+rare_topics+same_lang+similar_pop+shared_platform (65%)
  • clawless — semantic(0.24)+complementary+same_lang+similar_pop+shared_platform (58%)
  • build-claude-code — semantic(0.22)+complementary+same_lang+similar_pop+shared_platform (58%)

gini-agent alternative? Top 6 similar tools

Looking for a gini-agent alternative? If you're comparing gini-agent 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.

  • gini-agent by Sheldenshi · ⭐ 674

    The agent that remembers and learns.

  • gini-agent by Lilac-Labs · ⭐ 664

    The agent that remembers and learns.

  • fulling by FullAgent · ⭐ 2.4k

    Fulling is an AI-powered Full-stack Engineer Agent. Built with Next.js, Claude, shadcn/ui, and PostgreSQL. Use

  • agents by inkeep · ⭐ 1.4k

    Create AI Agents in a No-Code Visual Builder or TypeScript SDK with full 2-way sync. For shipping AI assistant

  • flock by Onelevenvy · ⭐ 1.1k

    Flock is a workflow-based low-code platform for rapidly building chatbots, RAG, and coordinating multi-agent t

  • context-space by context-space · ⭐ 812

    Ultimate Context Engineering Infrastructure, starting from MCPs and Integrations

More MCP Server Tools

Explore other popular mcp server tools:

View all MCP Server tools →

Popular TypeScript Agent Tools

Frequently Asked Questions

What is gini-agent?

gini-agent is The agent that remembers and learns.. It is categorized as a MCP Server with 2.3k GitHub stars.

What programming language is gini-agent written in?

gini-agent is primarily written in TypeScript. It covers topics such as agent, agent-runtime, ai-agent.

How do I install or use gini-agent?

You can find installation instructions and usage details in the gini-agent GitHub repository at github.com/Open-Curiosity/gini-agent. The project has 2.3k stars and 839 forks, indicating an active community.

What license does gini-agent use?

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

What are the best alternatives to gini-agent?

The top alternatives to gini-agent on Agent Skills Hub include gini-agent, gini-agent, fulling. 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