LLM-supervised persistent memory for AI agents β graph-based recall and knowledge management.
graph-memory
β FeaturedA knowledge-graph memory plugin for AI agents: conversations are distilled into structured triples, compressing context by up to 75% and enabling traceable, searchable, cross-session experience reuse. One memory core, native to DeepSeek Harness, with the OpenClaw plugin entry retained.
Plugin facts
Screenshots
Install this DSH plugin
Copy the command below and run it in your DeepSeek Harness terminal.
dsh plugin add github:adoresever/graph-memory β οΈ Plugins run with the permissions of your dsh process and may execute code at install time. Review the source repository and its license before installing. Pin the commit hash for reproducible installs. Plugin safety β
More about this plugin
Loaded by the DSH/Cordis plugin lifecycle, not simulated through an MCP side channel. Integrates Session, Tool, Agent Loop, Prompt Assembly, LLM, and Credentials seams.
Related guides
Learn how to choose, install, and use memory plugins.
About this plugin: graph-memory
What is graph-memory?
graph-memory is a memory plugin maintained by adoresever. A knowledge-graph memory plugin for AI agents: conversations are distilled into structured triples, compressing context by up to 75% and enabling traceable, searchable, cross-session experience reuse. One memory core, native to DeepSeek Harness, with the OpenClaw plugin entry retained.
How do I install graph-memory?
Run dsh plugin add github:adoresever/graph-memory in your DeepSeek Harness terminal. The dsh CLI resolves the plugin from GitHub and installs it into your active profile. For reproducible installs, pin a commit hash: dsh plugin add github:adoresever/graph-memory#commit.
Is graph-memory free?
graph-memory is a community open-source project released under the MIT license. You can inspect its source and install it for free.
Related plugins
memtrace-public
β 454Memtrace turns your codebase into a live knowledge graph that AI coding agents can query in milliseconds β every function, class, call edge, and version, across every session, without re-reading files or breaking things they can't see.
dsh-memory-evolve
β 153Cross-session long-term memory plus background self-evolution for DeepSeek Harness β five memory tracks, git-aware branching, self-review and a skill manager.