Install
$ dsh plugin --profile web add github:canyueY/dsh-mnemosyne#mainPlugin 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
- Registers memory tools into DeepSeek Harness including memory_search, memory_context, memory_observe, and memory_feedback
- Manages and supervises the local Python Mnemosyne node service directly from the DSH adapter
- Maintains an evidence-first memory lifecycle distinguishing observations, candidates, and verified memories
- Supports schema evolution (assimilation, accommodation, conflict detection) with preview confirmation
- Incorporates explicit user feedback, action outcomes, and agent self-evaluations with weighted impact
- Blends lexical search with optional semantic scoring via hashed or custom embeddings
Useful For
- Providing long-term evolving memory across sessions for DeepSeek Harness agents
- Preventing silent context overwrite by tracking memory changes, sources, and conflicting evidence
- Tuning agent behavior based on explicit user corrections and task execution feedback
- Maintaining localized project and personal knowledge memory banks with SQLite storage
Who It Fits
- DeepSeek Harness users requiring persistent agent memory and cognitive history
- Agent developers building applications that need traceable, evolvable long-term context
- Researchers exploring cognitive architectures, memory banks, and feedback loops for AI
Documented Limitations
- Requires a working Python environment with dependencies installed to execute the background service
- Default semantic retrieval relies on lightweight hashed embeddings rather than full natural language transformer models unless an external provider is configured
- Requires Node.js 20 or higher as specified in package engines
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.
package.json declares 0 runtime, 0 development, 1 peer, and 0 optional dependencies.
package.json declares DSH bundle metadata.
GitHub reports the repository license as AGPL-3.0.
A root package.json was captured and can be inspected by the registry.
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
- canyueY/dsh-mnemosyne
- Registry source
- GitHub · dsh-plugin topic
- Registry classification
- Plugin
- Source checked
- b891230 · 2026-10-31
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
- 6GitHub stars
- Forks
- 0
- Open issues
- 0
- Last commit
- 2026-10-31
- Last release
- 2026-10-31
Related DSH Plugins
Ranked by overlapping capabilities, use cases, plugin type, categories, and DSH profile.
LLM-supervised persistent memory and graph-based recall integration bundle for DeepSeek Harness.
View plugin →Lingshu long-term auditable memory system and cognitive graph for DeepSeek Harness.
View plugin →Composable, view-based layered memory bundle for DeepSeek Harness with pluggable providers and strategies.
View plugin →Local cross-agent memory and session history recall integration for DeepSeek Harness.
View plugin →