dsh-memory-layer
A local-first, trigger-driven cross-session memory layer for DeepSeek Harness backed by single-file SQLite.
Install
$ dsh plugin --profile web add github:KLRSL/dsh-memory-layerPlugin 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 cross-session memories locally in a single SQLite database file using WAL mode
- Triggers context recall based on active working directory, recent tool calls, and error codes
- Prioritizes memories deterministically by type (workflow > error > decision > fact)
- Automatically promotes repeated trigger events into sequential workflow chains
- Enforces strict injection limits of up to 8 entries or 1200 characters per context injection
- Applies five deterministic compaction rules with tombstone deletion and audit logging
- Provides memory management tools and CLI commands (/memory add, query, compact, dump)
- Integrates with Harness approval gates for write permissions
Useful For
- Persisting project-specific workflows and recurring troubleshooting steps across CLI sessions
- Remembering past command errors and resolutions to prevent repeating known mistakes
- Maintaining user preferences and architectural decisions locally without external vector databases
Who It Fits
- DeepSeek Harness users needing deterministic, local-first long-term memory
- Developers seeking lightweight cross-session context retention without telemetry or extra servers
Documented Limitations
- Does not support vector embeddings, semantic search, or cloud sync by design
- Context injection is capped at a maximum of 8 entries and 1200 characters
- Requires Node.js >= 22.19.0 and DSH >= 0.1.1-rc.2
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, 3 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.
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
- KLRSL/dsh-memory-layer
- Registry source
- GitHub · dsh-plugin topic
- Registry classification
- Plugin
- Source checked
- e0b27cd · 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
- 6GitHub stars
- Forks
- 0
- Open issues
- 0
- Last commit
- 2026-10-05
- Last release
- 2026-09-20
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 →LLM-supervised persistent memory and graph-based recall integration bundle for DeepSeek Harness.
View plugin →Knowledge graph memory and context engine for DeepSeek Harness with cross-session recall.
View plugin →Composable, view-based layered memory bundle for DeepSeek Harness with pluggable providers and strategies.
View plugin →