Plugins

Config-only bundle that mounts Ouroboros through the DSH MCP client, exposing 36 interview, Seed, execution, evaluation, and evolution workflow tools in DSH.

Integração profunda com o Mnemon: memória local em três camadas (Runtime Memory, Documents recuperáveis e Memory Spaces supervisionados).

把Claude Code的UltraCode模式带给DSH，把 DSH 的一次性多 Agent 调度，升级为可生成、可保存、可治理、可观察、可恢复的 Workflow 层

Orquestração multiagente no estilo UltraCode: uma camada de workflow gerável, salvável, governável, observável e retomável.

DeepSeek Harness (DSH) plugin: dispatch work to DSH agents from Claude Code / Codex — native subagent progress, in-host worker sessions with per-tier presets, and a multimodal bridge that lends the text-only harness vision and image generation.

Persistent multi-model squads configured in Settings and selected in the Composer, with per-member model/tool policies; the main Agent dynamically plans each send as a bounded DAG with bounded reviewer/repair loops, while Run Center tracks retries and per-member tokens from official Harness usage events.

Ferramentas Cordis do DeepSeek Harness para o All in Flash, desenvolvidas com o All in Luna

Model high-availability failover (quarantine, circuit breaking, probe recovery) and subagent orchestration (fanout/pipeline/supervisor) with bilingual settings UI.

Salas persistentes para sessões independentes de Agent do DSH, com participação explícita, mensagens diretas e de transmissão, tarefas rastreadas e uma linha do tempo compartilhada na Web

Adds persistent execution contracts, recursive work graphs, critical clarification, and evidence gates for long or underspecified Harness tasks.

Retransmissão assíncrona de contexto, resumida por LLM, entre Sessões do DSH e Agent Team Rooms autorizadas, com snapshots instantâneos e resumos agendados

Plugin de provedor opcional para o dsh-skill-pack-security: registra a edição skills/ (zh) ou skills-en/ (en) do pacote em ctx.skills. Ambas as edições vêm embutidas em pack/

Um plugin de meta-agente nativo do modelo para o DeepSeek Harness: o modelo sintetiza workflows específicos da tarefa em tempo de execução a partir de cinco padrões de workflow agêntico (encadeamento de prompts, workers paralelos, roteador, supervisor, ciclo de avaliação) e coordena ferramentas e subagent

Long-task orchestration loop: Codex plans/scores/reviews, DeepSeek executes, Kimi supplements (vision acceptance, summarization, cross-check).

Roteador de modelos em dois níveis para o DeepSeek Harness — roteamento por LLM-Judge, cadeias de fallback multimodelo, failover com backoff exponencial e orquestração em nível de tarefa (adaptação do pi-shift-router para o DSH)

Alternative WorkflowEngine provider for DSH 0.1.0-rc.7 that runs model-written orchestration in fresh QuickJS/WASM runtimes with a JSON-only host bridge and bounded memory, execution time, and child-agent fan-out.

A single project operating map for DeepSeek Harness.

Main-brain orchestration preset: delegation-first persona, root-session execution gate, and portable AI-LAW rule skill.

Declarative task-DAG orchestration for DSH: validates dependency graphs, runs topological task layers in parallel through workflow-backed subagents, and propagates failures deterministically.

Rigorous open mathematics research suite: four agent skills (rigorous-open-math-research, manage-math-research-program, math-research-workflow, lean-verify) for theorem solving with adversarial audit, research program management, pipeline orchestration, and Lean 4 formalization audit; CI-verified tests and mechanical upstream sync.

Discover and verify portable RoleHub roles, pin each exact bundle, then launch its prompt and bundled skills in an isolated, continuable DSH Session with Host-approved tool bindings and optional Agent Team Room attachment.

Plataforma de avaliação de agentes: benchmarks em YAML, orquestração de execuções headless, métricas baseadas em traces e relatórios de execução