dsh-memory
Long-term spatiotemporal memory and white-box intelligence infrastructure for DeepSeek Harness agents.
Install
$ dsh plugin --profile web add @furongjun1999/dsh-memoryPlugin 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.
Key Capabilities
- Cross-session long-term memory graph with 5-layer hierarchy and timeline recall
- Zero-LLM white-box knowledge reasoning and continuous self-validation
- Automated memory extraction from user sessions with credential redaction
- Self-evolving knowledge flywheel for inducting, distilling, and learning patterns
- Roleplay engine with immutable self-anchors and specialized value rules
- Runtime MCP tool registration and Python subprocess self-healing bridge
- Host watchdog scripts for auto-restarting DeepSeek Harness processes
Useful For
- Maintaining persistent agent state and memory across multiple DeepSeek Harness sessions
- Executing deterministic, explainable white-box reasoning without incurring extra LLM token cost
- Auditable AI agent interactions with strict guardrail charter compliance
- Long-context roleplay with strict out-of-character (OOC) prevention
Who It Fits
- AGI and AI memory architecture researchers
- DeepSeek Harness developers needing cross-session agent continuity
- Developers requiring auditable, white-box cognitive pipelines
Documented Limitations
- Requires local Python runtime with the aeis package installed
- Relies on Cordis profile configuration and standard DSH session hooks
- Memory persistence and performance depend on local SQLite database storage
DSH Compatibility
Version-specific runtime evidence collected by DSH Plugin. A missing result means we have not tested that combination yet.
Security Signals
Objective signals discovered from package metadata and source inspection. These are not a guarantee that a plugin is safe.
GitHub reports the repository license as MIT.
No root package.json was captured in the latest GitHub snapshot.
Public GitHub source metadata is available for this registry snapshot.
Source & Registry Notes
Public provenance, Registry classification, and the latest source check for this entry, kept separate from runtime verification.
- Source repository
- FuRongJun-1999/dsh-memory
- Registry source
- GitHub · dsh-plugin topic
- Registry classification
- Plugin
- Source checked
- 75f427d · 2026-08-26
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
- 35GitHub stars
- Forks
- 0
- Open issues
- 1
- Last commit
- 2026-08-26
- Last release
- No release detected
Related DSH Plugins
Ranked by overlapping capabilities, use cases, plugin type, categories, and DSH profile.
Three-tier memory control plane for DeepSeek Harness with runtime context, project documents, and pluggable long-term memory providers.
View plugin →Local-first control center for DeepSeek Harness balance, token usage, peak/off-peak pricing, multi-account switching, and session controls.
View plugin →Persistent multi-model Agent teams and bounded DAG workflows with GUI controls for DeepSeek Harness.
View plugin →Second-model approval reviewer for DeepSeek Harness that returns structured allow/deny verdicts with fail-closed fallback and session-log auditing.
View plugin →