
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.
Install Mnemon
Installs straight from git: plain JavaScript that needs no build step, so no build allowance is required.
The one-line version
dsh plugin --profile my-profile add github:mnemon-dev/mnemonThis bundle is not on npm, so it installs straight from git. Its build output is already committed to the repository (or it needs no build at all), so it loads without a build step.
From GitHub — artifacts are already committed, nothing is built locally
# 1. add the bundle to a profile — --profile my-profile points at $DSH_HOME/profiles/my-profile
dsh plugin --profile my-profile add github:mnemon-dev/mnemon
# 2. verify: the bundle should show up as a layer in the resolved config
dsh --profile my-profile --dump-config
# 3. boot the profile
dsh --profile my-profilePin a commit — github:mnemon-dev/mnemon#<commit-sha> — if you want the code you reviewed to be the code you keep getting.
Before you run it
- A plugin runs with your permissions once loaded: it can read your files, use your credentials and reach the network. Tool approvals do not sandbox it.
- Installing from git resolves a moving branch. Pin a commit —
github:mnemon-dev/mnemon#<commit-sha>— so the code you reviewed is the code you install.
Prerequisites
- API key
- Not required.
- Network access
- Not required at runtime.
- Language
- Go — a git install pulls this source, not build output.
Install check
Every field the verdict was derived from, so you can re-derive it yourself
| Field checked | Result | Weight | What the spec says about it |
|---|---|---|---|
| lifecycleScripts | pass | info | no install-time scripts |
| dsh.bundle | pass | fatal | package.json declares a `dsh.bundle` layer |
| dsh.bundle.patch file | pass | fatal | patch file present at `cordis.patch.yml` |
| npm registry | missing | warn | `@mnemon-dev/dsh-mnemon` is not published to npm |
| build requirement | pass | info | plain JavaScript — loads from source without a build |
- Verdict reason
- git-only but needs no build
- package.json read
- package.json
- Rules applied from
- docs/user/develop/basic/publish.md
- Checked at
- 2026-08-15
From the README
Excerpt as published by the author, plain text, unedited
**English** | [中文](docs/zh/README.md) **LLM-supervised persistent memory for AI agents.** LLM agents forget everything between sessions. Context compaction drops critical decisions, cross-session knowledge vanishes, and long conversations push early information out of the window. Mnemon gives your agent persistent, cross-session memory — a four-graph knowledge store with intent-aware recall, importance decay, and automatic deduplication. The `mnemon` memory path remains one local binary with zero API keys and one setup command. Mnemon ships one executable with two separate surfaces. Memory stays at the `mnemon` root; [Agency Preview](docs/AGENCY.md) lives at `mnemon agency ...` and adds durable, project-local responsibility and effect admission to an existing Pi agent. Agency does not repl
Topics
GitHub topics on this repository
More in Knowledge Graph Persistent Memory
Ranked by similarity inside the cluster, not alphabetically
Dsh Mnemon
omdsh-dev
Cross-agent, local-first persistent memory plugin for DeepSeek Harness (DSH), powered by Mnemon. It shares long-term memory across Mnemon-enabled agents and adds runtime memory, searchable project documents, semantic recall, knowledge graph, and a Sidebar UI.
Nowledge Mem Deepseek Harness
nowledge-co
Nowledge Mem community plugin bundle for DeepSeek Harness
Dsh Memory
U-Illll
Memory retrieval plugin for DeepSeek Harness (dsh): wiki double-link memory graph with 9 tools — hybrid search, read, link-scan, remember, forget, compile, health-check, resident retriever subagent
Dsh Mindforge
opok-ops
Encrypted 4-layer lifelong memory for DeepSeek Harness - powered by MindForge
Dsh Knowledge Graph
cwbcheng
DSH Cordis plugin: turn any source text into an AI knowledge graph (facts/inferences/concepts/definitions/examples/counter-examples/rules) with two-way linking between the graph and the original text.
Graph Memory
adoresever
Openclaw记忆插件Knowledge Graph + Memory;Knowledge Graph Context Engine for OpenClaw — extracts structured triples from conversations, compresses context 75%, enables cross-session experience reuse