mnemon-dev/mnemon

C3

LLM-supervised persistent memory for AI agents — graph-based recall, cross-session knowledge, single binary. Works with DeepSeek Harness, Claude Code, OpenClaw, and any agent runtime.

★ 500+ · mnemon-dev/mnemon source on GitHub · this plugin in the registry

mnemon-dev/mnemon is a DeepSeek Harness plugin rated C3 — powerful capability combined with sensitive behavior. It patches the dsh runtime, executes system commands, base64 decoding in build output only.

Installable plugin — declares a dsh.bundle manifest

What it can do

CapabilityFlagEvidence
patches the dsh runtimeruntime_patch./cordis.patch.yml
executes system commandsexec×16 in authored code, e.g. testdata/memory/pi/mnemon-before-164.ts:1, testdata/memory/pi/mnemon-before-164.ts:1
base64 decoding in build output onlybase64_decode_bundled×1 in build output only, e.g. web/dist/assets/cytoscape-G6xtpWZq.js:331

Tool registrations

0 static tool registration point(s).

Outbound domains

react.dev

Environment variables it reads

MNEMON_DATA_DIR PI_CODING_AGENT_DIR

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.