OMC-style multi-agent orchestration for DeepSeek Harness: 29 omd-* skills and 12 /omd-* slash commands over the plan-execute-review-verify pipeline and team/autopilot/ralph modes.

Synchronizes DSH profiles and local plugin source archives through WebDAV and S3-compatible storage, with encrypted snapshots, conflict-aware recovery, and explicit self-updates.

Runs a prompt on a cron-like interval; every run opens a fresh session and the run history is kept.

by 988hj7tczd-oss

Preset workflow template library: 12 reusable orchestration script templates with wf_template_list / wf_template_search / wf_template_run / wf_template_validate tools and static template validation.

Multi-agent meeting negotiation over the LAN: each person runs their own assistant, and assistants find each other via mDNS and negotiate meetings, weekend outings and bubble tea votes through A2A mes

Plan Checkup for DeepSeek Harness: checks each step of a plan with Jev or a local LLM before you approve it, and marks the results on the plan review card.

DeepSeek-led background orchestration of Codex and DSH subagents, with existing conversation handoff, Markdown history, quota pauses, and bounded decision retries.

Chinese multi-agent workflow with per-role model fallback, versioned Mermaid task plans, independent Agent and Jev reviews, persistent expert collaboration, and pure-function calculation tools.

by nuaaweixinye

GME Test Generator workflow tools for DeepSeek Harness (dsh): pick interfaces, generate and repair tests through a local Python backend, poll progress, and decide with consent.

Free-interval session reports with AI-narrated daily/weekly digests over any date range, plus every-N-days scheduled reminders with system notifications (macOS / Linux).

Per-workspace project kanban board: nine kanban_* model tools for agent-driven planning plus a browser board UI, with disk persistence, undo, templates, and archiving.

Drop-in enhanced fork of the official workflow tool: a verbatim fork of the stock tool plus a persisted saved-workflow library (workflow_save / workflow_list / workflow_get / workflow_delete / workflo

Extends the composer model selector menu with a third Context window row, preset capacities (64K–2M), custom input, provider-wide sync, and adaptive compaction guard.

Project Development Mode preset plus an in-chat development board for DeepSeek Harness: the lead conversation clarifies requirements and delegates to an Agent Team, and the floating board tracks each

by 121212165

dsh plugin: compiles a rough need into a versioned task book, then hands it to any AI window losslessly via a read-back handshake (/forge /relay /ack /answer /forge-list)

Installs an Orchestrator agent preset that plans and dispatches to model-pinned specialist subagents (explorer, oracle, librarian, designer, fixer, council), with named model profiles switched via an

by kira905

DSH plugin: self-maintained task board for the DSH web GUI (fork of upstream 0.3.4, detached). A card is a real DSH session, and a human confirms completion rather than the runner. | DSH plugin: self-maintained task board — one

Gated four-stage video pipeline: brief, script, assets and compose, turning one sentence into a narrated explainer with ComfyUI workflows or image/video APIs and FFmpeg assembly.

Ranked subagent delegation: role-based model routing with failover, per-route reasoning effort, model-transparent labels, fork delegation, and a visual route editor.

No description yet

Zagent — unified three-role self-improvement loop with three operators. Data-RSI (daily cross-sectional cleaning: winsorize → cross-sectional standardization → median fill, plus experience extraction)

A Codex-style right side panel for the DSH Web UI — session artifacts browser (live file tree, scan include, preview, reveal) plus a side chat that forks the current session with a model picker, human

No description yet

by ZhenHuangLab

Policy-driven Git sync for DSH settings and profile configuration, with secret-aware projections, conflict review, and per-line apply controls.