dsh-experience-memory
Cross-session graded experience memory with query-gated injection and SQLite storage for DeepSeek Harness.
Install
$ dsh plugin --profile <name> add /path/to/dsh-experience-memory.tgzPlugin 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
- Fail-closed evidence grading classifying memory as verified-tool, verified-user, verified-file, or unverified candidate
- Query-gated context injection with shared byte budget across core domain rules, standing rules, and turn-relevant lessons
- Just-in-time pre-call delivery triggered by declared path, tool, or command anchors (recall_for)
- Model tools for memory recall, recording, feedback tracking, soft forgetting, and statistics inspection
- Slash commands for humans to check status, preview turn injections, run bounded maintenance, and audit legacy memories
- Dual-scope memory hierarchy promoting workspace observations to domain-wide core memory upon cross-workspace validation
- Zero-dependency local persistence utilizing Node-native SQLite and FTS5 full-text indexing
Useful For
- Retaining project-specific quirks, deployment conventions, and non-obvious workspace rules across chat sessions
- Preventing repeated agent mistakes on recurring tasks without polluting prompt token limits when irrelevant
- Selectively anchoring critical constraints to specific CLI commands, tools, or target file paths before execution
- Auditing and migrating legacy memory datastores into structured, verified lessons
Who It Fits
- Developers working on long-running projects with DeepSeek Harness agents
- Engineers requiring verifiable, hallucination-resistant memory retrieval across multiple workspaces
- Harness administrators needing transparent, auditable memory retention and retirement policies
Documented Limitations
- No semantic or vector embedding search; relies solely on FTS5 full-text queries and exact identifier matching
- Pre-call action reminders require memories to explicitly declare recall_for anchors to trigger
- Relies on Node experimental SQLite (node:sqlite) module
- No built-in remote synchronization across different physical machines
- Slash commands depend on the commands service provided by dsh-base
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, 7 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
- Marquez807/dsh-experience-memory
- Registry source
- GitHub · dsh-plugin topic
- Registry classification
- Plugin
- Source checked
- 415c00c · 2026-10-23
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
- 1GitHub stars
- Forks
- 0
- Open issues
- 0
- Last commit
- 2026-10-17
- Last release
- 2026-09-25
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 →Composable, view-based layered memory bundle for DeepSeek Harness with pluggable providers and strategies.
View plugin →LLM-supervised persistent memory and graph-based recall integration bundle for DeepSeek Harness.
View plugin →Second-model AI auto-review for DeepSeek Harness approval requests with fail-closed security.
View plugin →