← DeepSeek Harness Plugins
DeepSeek Harness PluginManifest Valid

graph-memory

Knowledge graph memory and context engine for DeepSeek Harness with cross-session recall.

VisionUI & ProductivityDeveloper ToolsBrowser & WebSecurity & PolicySkills & WorkflowsRemote Execution
644GitHub Stars97ForksUpdated2026-10-01

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
Graph Memory is a native DeepSeek Harness memory plugin and context engine that manages historical context by preserving recent conversation turns, archiving older history into a local SQLite knowledge graph, and automatically recalling source-backed question/answer pairs across sessions.

Key Capabilities

  • Context window management keeping configurable newest-N completed conversation turns
  • Lightweight SPO triple and turn summary extraction into a local SQLite knowledge graph
  • Query-time PageRank, local label propagation (LPA), and vector search with FTS5 fallback
  • Automatic cross-session and cross-project recall with exact source question and answer evidence
  • Includes DSH maintenance and inspection tools: gm_status, gm_search, gm_record, gm_stats, gm_maintain, and gm_retry_extraction
  • Quarantines malformed extractions without blocking foreground agent execution

Useful For

  • Preventing context window bloat and token cost explosion during long agent sessions
  • Cross-session knowledge retention and experience reuse for recurring development tasks
  • Structured memory retrieval using hybrid vector embeddings and graph navigation

Who It Fits

  • DeepSeek Harness users running extended or multi-turn agent workflows
  • Developers seeking persistent cross-session memory without sending raw history back every turn

Documented Limitations

  • Requires Node.js 22.13.0 or higher
  • Structured extraction depends on model contract adherence (failures are quarantined)
  • Embeddings require an external OpenAI-compatible embedding endpoint (falls back to FTS5 if unconfigured)

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, 6 development, 3 peer, and 0 optional dependencies.

info
Dsh Bundle Declared

package.json declares DSH bundle metadata.

info
License Declared

GitHub reports the repository license as MIT.

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
adoresever/graph-memory
Registry source
GitHub · dsh-plugin topic
Registry classification
Plugin
Source checked
5841b19 · 2026-10-12

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.

Repository Activity

GitHub stars
644GitHub stars
Forks
97
Open issues
18
Last commit
2026-10-01
Last release
2026-03-18
For maintainers

Maintaining this plugin?

This listing is generated from public repository data. If you maintain this project, you can review the information and share this listing with your users if you find it useful.

Add to README
Listed on DSHPlugin.app