dsh-ariadne
Visual decision workbench and step-by-step execution graph tool for DeepSeek Harness.
Install
$ dsh plugin --profile web add github:Zayzz-pixel/dsh-ariadne#v0.3.0Plugin 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
- Interactive session map to explore ideas, branch out sub-topics, and track decision status
- Focus Dock preserving working context, next steps, and separate private user notes
- Generation of structured Final Plan execution graphs (Task, Decision, Checkpoint nodes)
- Step-by-step node execution workflow with replayable session events and artifact tracking
- Project-level multi-session aggregation via storage domain
- Export capabilities for Markdown, JSON, and JSON Canvas 1.0 specifications
Useful For
- Brainstorming and structuring complex architectural or product decisions with an AI agent
- Turning open-ended discussion threads into actionable step-by-step execution plans
- Managing structured workflow checkpoints that require explicit human approval before proceeding
- Exporting structured brainstorming maps and execution logs to Markdown or Canvas formats
Who It Fits
- DeepSeek Harness web users
- Software architects and project planners
- Developers seeking human-in-the-loop controlled agent execution graphs
Documented Limitations
- Targets DSH version 0.1.1-rc.2 web profile and requires Node.js >= 18
- Execution is strictly single-node sequential per run; intra-graph parallelism, loops, and subgraphs are not yet supported
- Hard limit of up to 30 nodes per execution graph
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, 0 development, 10 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
- Zayzz-pixel/dsh-ariadne
- Registry source
- GitHub · dsh-plugin topic
- Registry classification
- Plugin
- Source checked
- fdbd1b0 · 2026-09-03
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
- 2026-09-01
- Last release
- 2026-09-01
Related DSH Plugins
Ranked by overlapping capabilities, use cases, plugin type, categories, and DSH profile.
Persistent multi-model Agent teams and bounded DAG workflows with GUI controls for DeepSeek Harness.
View plugin →Composable three-tier memory control plane for DeepSeek Harness with runtime context, searchable documents, and pluggable long-term memory.
View plugin →A standalone, local persistent-memory system for AI agents, with DeepSeek Harness support provided through the separate dsh-mnemon plugin.
View plugin →Local-first AI agent runtime and DSH plugin bundle providing sandboxed sessions, MCP tools, audit logs, and session replay.
View plugin →