dsh-experience-map
Evidence-governed experience memory and structured reuse workflow for DeepSeek Harness.
Install
$ dsh plugin --profile web add [email protected]Plugin 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
- Automatic suggestion detection and grouping from completed harness tasks
- Six structured Experience kinds: Procedure, Diagnostic, Strategy, Preference Policy, Fact, and Causal candidates
- Preflight environment validation and deterministic hard-gated candidate matching
- Configurable local hybrid recall using MiniSearch lexical ranking or optional local multilingual E5 embeddings
- Explicit plan inspection, approval gates, and minimal one-time context injection
- Authoritative readback verification and settlement lifecycle tracking
- Integrated web workspace tab in the harness UI, headless CLI runner, and dedicated management commands
Useful For
- Preventing the agent from rediscovering steps for solved, repeatable development and diagnostic workflows
- Enforcing strict evidence binding and human approval before reusing past procedures
- Managing structured operational memory across sessions with local-first privacy
Who It Fits
- DeepSeek Harness developers and power users wanting repeatable agent workflows
- Teams requiring auditable, evidence-backed agent memory and strict execution boundaries
Documented Limitations
- Requires DeepSeek Harness 0.2.0-rc.2 (version 0.1.0-beta.6) or 0.1.5-rc.2 (version 0.1.0-beta.3)
- Automatic execution and automatic admission are disabled by default (shipped at shadow evaluation level)
- Optional dense vector retrieval requires manual installation and setup of @huggingface/transformers
- Causal records remain candidates and do not infer general causality without validated evidence
- Does not backfill historical sessions completed while the plugin was inactive
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 1 runtime, 44 development, 26 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
- alcheme-labs/dsh-experience-map
- Registry source
- GitHub · dsh-plugin topic
- Registry classification
- Plugin Bundle
- Source checked
- 4535926 · 2026-10-17
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
- 6
- Last commit
- 2026-10-02
- Last release
- No release detected
Related DSH Plugins
Ranked by overlapping capabilities, use cases, plugin type, categories, and DSH profile.
Native SQLite-backed task management and project board bundle with Web UI and Agent workflow tools for DeepSeek Harness.
View plugin →Persistent multi-model agent teams with dynamic DAG orchestration, run monitoring, and token insights for DeepSeek Harness.
View plugin →Second-model AI auto-review for DeepSeek Harness approval requests with fail-closed security.
View plugin →Session lifecycle manager for DeepSeek Harness with search, restore, idle cleanup, and diagnosis.
View plugin →