Install
$ dsh plugin --profile <profile> add ./packages/dsh-memory-bundlePlugin 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
- CJK and Unicode extension full-text search using FTS5 trigram tokenization and short-query fallback
- Hybrid memory retrieval combining sqlite-vec vector search and lexical FTS5 via RRF ranking
- Cross-session core memory storage with KV-cache-safe system prompt injection
- Tool execution result deduplication by hashing outputs to conserve input tokens
- Lossless compaction locator appending exact source event sequences and spill paths to summaries
- Self-evolving and model-managed skills with background reflection loops
- Provenance auditing and slash-command-based pinning (/skill-pin, /memory-pin) protected against LLM modification
Useful For
- Searching through extensive Chinese-language conversation and code review sessions in DSH
- Persisting cross-session project conventions, environment configurations, and lessons learned
- Preventing model context inflation through hash-based deduplication of repeated CLI/tool outputs
- Protecting critical user instructions and custom skills from unauthorized model overwrites
Who It Fits
- DeepSeek Harness users working in Chinese or mixed CJK environments
- Developers seeking persistent cross-session memory without breaking prompt KV caching
- Engineers requiring auditable, human-pinned rules and autonomous skill evolution in DSH
Documented Limitations
- Requires DeepSeek Harness host versions between >=0.1.5-rc.3 and <0.3.0
- Not yet published directly to npm registry; currently requires local or Git clone installation via dsh plugin add
- Production vector embeddings require external dependencies like @huggingface/transformers or transformers runtime
- Slash commands require interactive host profiles and are not executable in headless profiles without command adapters
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, 0 peer, and 0 optional dependencies.
GitHub reports the repository license as MIT.
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
- QIANLING-0831/dsh-memory-plus
- Registry source
- GitHub · dsh-plugin topic
- Registry classification
- Plugin Bundle
- Source checked
- 18cb60b · 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.
Repository Activity
- GitHub stars
- 12GitHub stars
- Forks
- 3
- Open issues
- 1
- Last commit
- 2026-10-10
- Last release
- 2026-09-30
Related DSH Plugins
Ranked by overlapping capabilities, use cases, plugin type, categories, and DSH profile.
Lingshu long-term auditable memory system and cognitive graph for DeepSeek Harness.
View plugin →Knowledge graph memory and context engine for DeepSeek Harness with cross-session recall.
View plugin →Persistent semantic memory layer for DeepSeek Harness backed by Markdown and Milvus.
View plugin →LLM-supervised persistent memory and graph-based recall integration bundle for DeepSeek Harness.
View plugin →