graph-memory
Traceable, searchable cross-session memory for DeepSeek Harness — conversation knowledge as typed graph nodes (TASK/SKILL/EVENT) and typed edges.
DeepSeek Harness 的可追溯、可检索跨会话记忆：把对话知识沉淀为带类型的图节点（任务/技能/事件）与关系边。
How to install
dsh plugin add graph-memory git clone https://github.com/adoresever/graph-memory ~/.claude/skills/graph-memory npx -y graph-memory About
Graph Memory One memory core, native to DeepSeek Harness, with the OpenClaw plugin entry retained. Compaction answers “how much of this conversation still fits?” Graph Memory answers “which past knowledge is worth recalling now?” Reusable conversation knowledge becomes typed nodes: TASK: goals, execution, and outcomes; SKILL: validated reusable methods; EVENT: errors, fixes, decisions, changes, and facts. Typed edges such as USED_SKILL, SOLVED_BY, REQUIRES, PATCHES, and CONFLICTS_WITH preserve relationships. A new question retrieves a relevant local subgraph instead of replaying the complete h…
Recommendation signals
Meta
- License
- MIT
- Language
- TypeScript
- GitHub stars
- 576
- mo. downloads
- –
- Last push
- 2026-08-27
- Created
- 2026-03-10
Links
Basic safety check
- Findings
- None
- Sources
- curated:awesome-dsh-plugin.com, curated:awesome-dsh-plugin/awesome-dsh-plugin
- Topics
- claude-code, codex, deepseek, deepseek-harness, dsh, dsh-plugin, dsh-plugins, knowledge-graph, memory, openclaw, openclaw-plugin, opencode
Related plugins
firecrawl-mcp-server
firecrawl/firecrawl-mcp-server
🔥 Official Firecrawl MCP Server - Adds powerful web scraping and search to Cursor, Claude and any other LLM clients.
get-shit-done
gsd-build/get-shit-done
A light-weight and powerful meta-prompting, context engineering and spec-driven development system for Claude Code by TÂCHES.
hivemind
activeloopai/hivemind
Hivemind turns your traces into reusable skills across agents