Install
$ dsh plugin --profile web add @achasoft/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
- Stores project memories, architectural decisions, sprint context, and rules in a local DuckDB database (.dsh/memory.db)
- Injects mandatory and forbidden rules directly into the system prompt on every model request
- Supports hybrid keyword (BM25F) and OpenAI-compatible vector embeddings for semantic recall
- Provides a dedicated Web Client tab to browse, search, edit, archive, and audit memories and rules
- Supplies model-facing tools for searching, storing, recalling memories, and managing session summaries
- Enforces strict trust boundaries separating user-defined rules from agent-generated notes and subagent actions
Useful For
- Preserving architectural decisions, conventions, and sprint goals across long-running or repeated agent sessions
- Enforcing strict project constraints and mandatory conventions via system prompt injection that survives context compaction
- Allowing autonomous agents to log session summaries and recall past context via tool calls
- Importing existing instruction files such as CLAUDE.md or AGENTS.md into structured project rules
Who It Fits
- DeepSeek Harness developers working on long-term or complex codebases
- Teams needing persistent, shareable project conventions and architectural memory for AI coding agents
- Users needing semantic search and session tracking within the DSH Web Client
Documented Limitations
- Requires DuckDB node bindings supported on standard macOS, Linux, and Windows architectures (no compilation at install time)
- DuckDB takes an exclusive lock per file, preventing concurrent multi-process writes to the same memory database
- Semantic vector search requires an optional OpenAI-compatible embeddings endpoint; otherwise falls back to keyword-only search
- Subagent writes created by earlier versions are not retroactively filtered out of opening session contexts
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 2 runtime, 30 development, 9 peer, and 0 optional dependencies.
package.json declares DSH bundle metadata.
GitHub reports the repository license as MIT.
A root package.json was captured and can be inspected by the registry.
package.json declares a prepare lifecycle script that may run during relevant package installation workflows.
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
- navid-kianfar/dsh-memory
- Registry source
- GitHub · dsh-plugin topic
- Registry classification
- Plugin
- Source checked
- 6645652 · 2026-09-15
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
- 0GitHub stars
- Forks
- 0
- Open issues
- 0
- Last commit
- 2026-09-15
- Last release
- No release detected
Related DSH Plugins
Ranked by overlapping capabilities, use cases, plugin type, categories, and DSH profile.
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 →Lingshu long-term auditable memory system and cognitive graph for DeepSeek Harness.
View plugin →Native SQLite-backed task management and project board bundle with Web UI and Agent workflow tools for DeepSeek Harness.
View plugin →