DeepSeek Harness PluginManifest Valid

archgraph

Architecture-graph driven long-term memory and agentic engineering toolchain bundle for DeepSeek Harness.

Terminal & TUIDeveloper ToolsSkills & Workflows

3GitHub Stars0ForksUpdated2026-10-15

Source Homepage

Install

No clear install command was found in the current repository evidence.

Plugin Overview & Capabilities

AI-assisted organization based on the public repository snapshot. The content must be grounded in source evidence and does not replace compatibility or security verification.

source-grounded

ArchGraph is an architecture-graph driven framework for agentic engineering that provides coding agents with durable long-term memory over an ArchiMate 3.2 intent graph via MCP. Packaged as a DeepSeek Harness bundle with Cordis integration (including workspace and wakeup modules), it equips agents with architectural context retrieval, deduplicated mutations, and traceable design updates across sessions.

Key Capabilities

Tiered long-term architectural memory with on-demand recall and session startup restoration
Model Context Protocol (MCP) server integration exposing graph initialization, mutation, and validation tools
Pluggable custom ontology bundles extending or replacing default ArchiMate 3.2 schemas
Semantic GraphRAG recall and Cypher structural querying over Neo4j
DeepSeek Harness bundle integration with dedicated Cordis patch and wakeup/workspace plugins
Deduplicated architecture writes with automated candidate collision checking

Useful For

Providing coding agents with persistent architectural memory and design rationale across coding sessions
Tracing code commits directly back to architectural elements and intent graph specifications
Validating repository changes against structured architecture models and custom ontologies
Federated architecture graph querying across multiple projects

Who It Fits

Software architects and tech leads modeling system architecture for AI workflows
Developers using DeepSeek Harness and coding agents on enterprise codebases
Platform engineering teams setting up persistent agent memory environments

Documented Limitations

Local cross-project reads/writes via workspaceRoot are blocked in DeepSeek Harness because session workspaces are pinned; cross-project access requires the federated channel
Semantic GraphRAG retrieval requires an external Neo4j instance and an OpenAI-compatible embedding endpoint
Requires Node.js runtime version 18 or higher

DSH Compatibility

Version-specific runtime evidence collected by DSH Plugin. A missing result means we have not tested that combination yet.

Not tested yetNo runtime compatibility tests have been published yet.

Security Signals

Objective signals discovered from package metadata and source inspection. These are not a guarantee that a plugin is safe.

Dependency Counts

package.json declares 1 runtime, 2 development, 0 peer, and 0 optional dependencies.

info

Dsh Bundle Declared

package.json declares DSH bundle metadata.

info

License Declared

GitHub reports the repository license as Apache-2.0.

info

Package Manifest Available

A root package.json was captured and can be inspected by the registry.

info

Source Available

Public GitHub source metadata is available for this registry snapshot.

info

Source & Registry Notes

Public provenance, Registry classification, and the latest source check for this entry, kept separate from runtime verification.

Source repository: derekhu0002/archgraph
Registry source: GitHub · dsh-plugin topic
Registry classification: Plugin Bundle
Source checked: 9dcd2e3 · 2026-10-15

This project is independently indexed from public source information. DSH Plugin is not affiliated with DeepSeek or the plugin author. Always check the author repository before installation.