EverMind-AI/EverOS
C2One portable memory layer for every AI agent: local-first, Markdown-native, user-owned, and self-evolving across apps, tools, and workflows.
★ 13k+ · EverMind-AI/EverOS source on GitHub · this plugin in the registry
EverMind-AI/EverOS is a DeepSeek Harness plugin rated C2 — one powerful capability or sensitive behavior. It executes system commands, starts a network server, reads credential-class env vars.
A skill, not an installable plugin — ships SKILL.md with no plugin manifest
What it can do
| Capability | Flag | Evidence |
|---|---|---|
| executes system commands | exec | ×4 in authored code, e.g. use-cases/claude-code-plugin/hooks/scripts/utils/sdk-filter.js:8, use-cases/claude-code-plugin/hooks/scripts/utils/sdk-filter.js:8 |
| starts a network server | net_server | ×1 in authored code, e.g. use-cases/claude-code-plugin/server/proxy.js:97 |
| reads credential-class env vars | token_env | EVERMEMOS_API_KEY, EVERMEM_API_KEY, EVERMIND_API_KEY, EVEROS_CLOUD_API_KEY, OPENAI_API_KEY, UPSTASH_REDIS_REST_TOKEN |
Outbound domains
api.evermind.ai openrouter.ai
Environment variables it reads
EVERMEM_CWD EVERMIND_API_KEY UPSTASH_REDIS_REST_URL UPSTASH_REDIS_REST_TOKEN EVEROS_CLOUD_API_KEY EVEROS_CLOUD_UPSTREAM EVERMEM_GROUP_ID EVERMEM_PROXY_PORT PORT OPENAI_API_KEY
How to read this
Levels measure capability surface and transparency, not maliciousness. A C3 plugin can be entirely legitimate — a desktop shell genuinely needs subprocesses. The point is that you can see this before installing. See the levels explained and how dsh plugins work.
Findings come from static analysis of shipped code; nothing is executed. Think a flag is wrong? Open an issue — every flag cites the file and line it came from.