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 CherryHQ · MCP Server · ★ 51
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is stella safe to install? View the security audit →
English | 中文 Stella — AI partners for every person ⚠️ Under Heavy Development — Stella is not stable. APIs, config formats, and behavior may change without notice. Not recommended for production use. Stella gives every person an AI partner that remembers them, works through trusted tools, and shows up where they already chat. Use Stella as a teammate at work, a manager for home routines, or a private assistant for personal projects. Each user-agent relationship has its own memory, workspace, tools, schedules, and sandbox boundaries, so Stella can understand different people without flattening everyone into one profile. Under the hood, Stella is a multi-tenant, multi-user, multi-agent system. Each agent can have its own role, model, skills, tools, schedules, workspace, and sandbox policy. Deploy Stella where you want, use your own model API keys, and talk to her from Telegram, QQ, Feishu, WeChat, the Web UI, or the terminal. Why use Stella Remembers each person. Memory is scoped per user per agent, so Stella understands different people differently. Works through agents. Create agents for coding, writing, operations, family routines, research, and support. Acts safely.
| Stars | 51 |
| Forks | 9 |
| Language | Go |
| Category | MCP Server |
| License | AGPL-3.0 |
| Quality Score | 68.058694938499/100 |
| Open Issues | 152 |
| Last Updated | 2026-09-11 |
| Created | 2026-03-05 |
| Platforms | cli, go, mcp |
| Est. Tokens | ~16k |
These tools work well together with stella for enhanced workflows:
Looking for a stella alternative? If you're comparing stella 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.
A memory-first AI agent that remembers why decisions were made — not just the last message. Runs local (Ollama
Self-hosted framework for orchestrating fleets of specialist AI agents — ensemble reasoning and a full agentic
Local-first AI memory archive. Import ChatGPT, Claude, and Grok exports, generate semantic embeddings, and sea
Smart multi-agent conversational assistant with LangGraph orchestration, Human-in-the-Loop, enterprise-grade o
Open-source control plane and runtime for organisational agents: shared company context & brain
🦈 2-line install personal AI assistant. 11 AI runtime surfaces (Claude, Codex, Cursor, Gemini, Grok, Antigrav
Explore other popular mcp server tools:
stella is AI partners for every person: multi-user, multi-agent memory, trusted tools, schedules, sandboxed workspaces, and chat.. It is categorized as a MCP Server with 51 GitHub stars.
stella is primarily written in Go. It covers topics such as ai-agent, ai-assistant, ai-partner.
You can find installation instructions and usage details in the stella GitHub repository at github.com/CherryHQ/stella. The project has 51 stars and 9 forks, indicating an active community.
stella is released under the AGPL-3.0 license, making it free to use and modify according to the license terms.
The top alternatives to stella on Agent Skills Hub include zeph, captain-claw, mychatarchive. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
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: