dsh-moa
Mixture of Agents (MoA) multi-model collaboration and synthesis engine for DeepSeek Harness.
Install
$ dsh plugin --profile web add @goodandready/dsh-moaPlugin 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
- Integrated /moa slash command with preset autocompletion and dynamic preset routing
- Adaptive clarification questionnaire gate for underspecified or ambiguous prompts
- Isolated disk sandbox workspaces (.moa/candidate-N/) for parallel candidate proposals
- Frontier judge evaluation, peer critique rounds (Consilium), and automatic winner file promotion
- Built-in diff viewer, live token/cost tracking, automated test gate verification, and optional Live Canvas preview
Useful For
- Generating complex multi-file software features with diverse candidate architectures and judge synthesis
- Performing thorough peer-reviewed code audits and vulnerability detection
- Synthesizing modular code solutions combining strengths across multiple LLM providers
Who It Fits
- DeepSeek Harness developers seeking multi-model consensus and code synthesis
- Software engineers tackling ambiguous or architecturally complex tasks
- AI workflow designers requiring automated multi-agent critique and testing gates
Documented Limitations
- Prompts in refinement mode may include project files (up to ~16k characters), which requires keeping secrets out of non-dotfile source files
- Requires configured API keys or providers for proposer and judge models to execute parallel runs
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, 6 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
- GooDAnDReaDY/dsh-moa
- Registry source
- GitHub · dsh-plugin topic
- Registry classification
- Plugin
- Source checked
- 6a51554 · 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
- 9GitHub stars
- Forks
- 0
- Open issues
- 0
- Last commit
- 2026-10-22
- Last release
- 2026-10-22
Related DSH Plugins
Ranked by overlapping capabilities, use cases, plugin type, categories, and DSH profile.
Persistent multi-model agent teams with dynamic DAG orchestration, run monitoring, and token insights 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 →Second-model AI auto-review for DeepSeek Harness approval requests with fail-closed security.
View plugin →Full office suite integration for DeepSeek Harness supporting spreadsheets, docs, slides, bases, and canvases.
View plugin →