Implementing Traceable Knowledge Graph Memory for DeepSeek Harness with graph-memory
Graph-memory is a DSH memory-type plugin maintained by adoresever, which extracts dialogues into TASK/SKILL/EVENT knowledge graphs, supporting cross-session semantic recall and local SQLite storage. This article introduces its core capabilities, directory page installation commands, source tarball installation steps, gm_* tools and vector retrieval configuration, as well as the plugin permissions, beta version, and the application boundaries of the 75% context compression benchmark.
Read MoreUsing memtrace-public to add codebase structure memory to DeepSeek Harness
# memtrace-public This codebase is compiled into a structured knowledge graph that supports millisecond-level queries, covering functions, classes, call edges and versions, for DeepSeek Harness to use across sessions without repeatedly reading files. Maintained by syncable-dev, the community repository is categorized under the "Memory" category, and it had 454 stars as of August 18, 2026. The indexing is implemented via local Rust + Tree-sitter; the Harness plugin package `dsh-plugin-memtrace` is licensed under MIT, while the core indexer is under a proprietary EULA and is currently in private beta. This article cross-checks the installation commands, MCP tools, Skills, licenses and telemetry boundaries against the GitHub repository page.
Read MoreUsing Graph-Memory to Equip DeepSeek Harness with Traceable Knowledge Graph Memory
Graph-memory is an MIT-licensed open-source memory plugin maintained by adoresever. It extracts conversations into TASK/SKILL/EVENT triples and uses SQLite knowledge graphs for cross-session recall. The community installation command is `dsh plugin add github:adoresever/graph-memory`. The current version 1.6.0-beta.1 has not been published on npm yet, and the DSH acceptance path in the README uses a local tarball. About 75% of the compression comes from the limited workflow comparison, which is not a universal guarantee. The Pro visualization feature has not been delivered yet.
Read MoreAdd persistent memory to DeepSeek Harness agent using mnemon
Mnemon is a persistent memory for LLM supervised agents maintained by mnemon-dev: it uses local SQLite four-graph storage, the host model determines what to remember, and the binary is responsible for indexing and recall. The community directory categorizes it under "Memory" and marks it as featured. This article verifies the installation commands, DSH configuration entry, CLI usage, and the relationship with dsh-mnemon according to the directory page and GitHub.
Read MoreGraphify: Convert code bases, documents and SQL into queryable knowledge graphs to replace traditional vector RAG
Graphify, which has been consistently ranking on GitHub Trending in early August 2026, allows users to build locally queryable knowledge graphs from code, documents, SQL schemas, PDFs and more via the /graphify Skill. It uses tree-sitter AST for deterministic parsing at the code layer and does not rely on vector databases. The edges are labeled EXTRACTED/INFERRED for interpretability. This article introduces its differences compared to vector RAG, the steps to install and integrate it with Claude Code/Cursor, as well as its query, path and explain usages.
Read MoreGraphify: An Agent Skill for Translating Code Repositories, Documents and Schemas into Queryable Knowledge Graphs
Graphify, which trended on GitHub Trending in early August 2026, constructs queryable knowledge graphs from code, documents, SQL schemas, PDFs and more via local AST powered by tree-sitter and Leiden community detection, and integrates with Agent tools including Claude Code, Cursor and Codex through the `/graphify Skill`. This article verifies its Trending background and official capability boundaries, makes a comparison with vector RAG, and provides hands-on steps for installation via uv, Skill registration and querying via query/path/explain, to assist with context engineering选型 in large codebase scenarios.
Read MoreMCP Server codebase-memory-mcp: Enabling AI Agents to Truly "Remember" Your Codebase
In July 2026, the GitHub Trending hot project codebase-memory-mcp (produced by DeusData) indexes codebases into persistent knowledge graphs via the MCP protocol. It supports parsing 158 programming languages and provides 15 MCP tools, enabling agents such as Claude Code and Cursor to replace file-by-file exploration with structured queries. According to official benchmark tests, the token consumption for structural queries can be reduced by about 120 times, and indexing for Linux kernel-level repositories can be completed in approximately 3 minutes. This article introduces its Hybrid LSP semantic enhancement, core tools, installation method and applicable scenarios.
Read More