Plugins

AgentTeams multi-agent teams.

UltraCode-style multi-agent orchestration: a generatable, savable, governable, observable, resumable workflow layer.

DeepSeek Harness Cordis tools for All in Flash, powered by All in Luna

Shared multi-agent task board (create/claim/transition/query) over a Cordis service key.

Deep Mnemon integration: local three-tier memory (Runtime Memory, retrievable Documents, supervised Memory Spaces).

Cross-session agent-to-agent messaging for DeepSeek Harness — address another session by name and deliver a message into its inbox.

Loopback-first multi-agent message relay: HMAC-authenticated broker plus dsh plugin (relay_send/recv/peers/history), zero-dependency CLI and Python clients, wire protocol v1.0.

Research agent suite: long-horizon goal control with auditable evidence chains, cron scheduling, multi-agent expert teams, self-evolving research memory (FTS5 + RRF recall), project workspaces, and a custom workspace UI.

Evidence-first operating kit: six read-only tools (capability catalog, staged workflow plans, packaged skill reader, bounded local memory search, repository release audit, release checklist) and five packaged skills - plans and audits, never remote writes.

Hook DeepSeek Harness into a Hermes pipeline: dispatch-spec template, model-tier routing, orchestrator-run quality gates, git single-writer rule, as a SKILL.md pack (bundle installable).

Persistent rooms for independent DSH Agent sessions, with explicit membership, direct and broadcast messages, tracked tasks, and a shared Web timeline.

Cross-session task queue with handoff notes: sessions and subagents push, claim, complete and cancel tasks on a shared file-backed queue, and leave a handoff summary for whoever picks up next.

RigorQuant preset + skill pack: unattended walled multi-agent research for empirical and computational mathematics (economics, finance, portfolio), with a four-part pre-implementation check battery and a jacobian/Lean escalation lane.

Asynchronous, LLM-summarized context relay between DSH Sessions and authorized Agent Team Rooms, with instant snapshots and scheduled digests.

Same-runtime cross-Session discovery and communication for DeepSeek Harness

Multi-agent spatiotemporal memory graph with cross-session persistence and importance-gated recall.

ShiGuang Memory Engine (SGME) bridge: multi-agent shared long-term memory via HTTP — L0/L1/L1.5/L2 distillation, scenario-based injection, unified search, and proactive care signals (memory_search / wiki_search / signal_pull / signal_claim / signal_ack), installable as `dsh-sgme`.

TaskSwarm (蜂群) — DeepSeek Harness 上的多智能体任务编排插件：waves/lanes 并行执行、git worktree 隔离、任务包与跨模型评审、崩溃可恢复 | Multi-agent task orchestration for DeepSeek Harness: waves/lanes parallel execution, git worktree isolation, task packets, cross-model review, crash recovery