Плагины

Session-scoped research evidence ledger with sources, linked claims, open questions, and explicit user review; provides a tool, slash command, and conversation panel, with selected-claim Markdown export that omits excerpts, review notes, and local paths by default; does not fetch sources or verify their truth.

DeepSeek Harness 的模型fallback链插件：以更智能、更人性化的方式配置fallback链。当主模型撞限流、额度耗尽，或者5xx超时的时候自动向下改派模型，回合不中断。设置页可视化编排：拖拽排序、按计费或者上下文窗口排序候选模型、失败模型自动冷却、管理多条链的停用和启用。零依赖、无构建步骤、默认不介入任何请求。

Runs git in the Host process so push, pull and fetch work inside the agent sandbox; exposes 8 agent tools (status, diff, log, stage, commit, push, fetch, pull) and 11 slash commands including /git-status, /git-commit, /git-tag and /git-name-set.

Pack a directory into a deterministic tar, read an archive's contents without extracting it, unpack while refusing every member that could reach outside the destination, and verify what came out against what went in by SHA-256. No external dependency — the tar format is written and read in this plugin. Extraction is deliberately more permissive on reading than on writing, because a reader's job is to report what an archive says, while a writer must never emit what it cannot read back. A tar has no central index, so the walk tracks whether it reached the end-of-archive marker: without that, a half-file checksums fine and reads as complete.

Bounded self-managed long-term memory (Hermes-style MEMORY.md / USER.md with hard character limits and a safety scan), a review that runs after every turn and writes plain-language notes or refines an existing skill instead of adding a near-duplicate, a curator that finds and surgically repairs skills the loader would silently discard, cross-session search over past messages, and a learning card above the composer that appears only when there is news and asks before it deletes or rewords a memory.

Cross-workspace worker fleets: one orchestrating session spawns named worker sessions in other project workspaces, queues or steers tasks into them, watches them in the background via a real host job, and collects their reports. Worker completions deliver themselves to the orchestrator's session rather than needing to be polled, so an idle orchestrator still reacts. Escalations and failed workers deliver by steer when the orchestrator is mid-turn and by queue when it is idle; a turn that ends without a report counts as a failure and the worker is replaced after a configurable limit. The roster persists to disk and each worker session carries a durable title, so a restart neither loses the fleet nor spawns duplicate sessions. Ships five agent presets at full plugin parity with the standard preset.

Registers the project-cross-migration skill for DSH: five-layer agent project migration (conversations, memory, persona, tools, environment) with entry validation, JSONL integrity checks and readable restore. 1,418-message real migration verified across three platforms; pure Python stdlib, MIT.

White noise player: lays a layer of background sound (rain, streams, campfire, café) while AI codes, for flow and focus. Supports multiple playback modes (sequential / shuffle / single-loop / intermittent) and AI automatic background music download from Wikimedia Commons (CC0/PD/CC-BY).

Atomic OS interaction layer for DeepSeek Harness. A stable verb set replaces shell string concatenation — explicit argv, byte-exact encoding/BOM/EOL handling. Native Windows & POSIX implementations, zero runtime deps, MIT.

DeepSeek Harness plugin: a model-facing `chrome` tool that drives the installed Google Chrome over CDP — screenshots returned as images, DOM/text/eval, console & network diagnostics, real input events. Runs in the Host, so no per-call approval and no bash sandbox limits.

Floating approval window for DeepSeek Harness that appears when you leave the app and hands the request back to the native card when you return. Windows-only (WPF via PowerShell). Independent fork of zeta987/dsh-notify-zeta (MIT); do not run alongside the upstream.

Auto-continue plugin for DeepSeek Harness (DSH): automatically resumes a turn that ended on a rate limit (429), an exhausted quota, an empty response, or your own configured error codes — with a per-session consecutive-failure limit, a one-click quick swi

DSH slash command /commit: stages all changes, summarizes the staged diff with the session model, and commits; no browser UI required, with a local fallback when the model call fails.

多个AI Agent各干各的，消息靠你手动搬？建一个飞书群把它们拉进来，自动认领、自动交接。直连互@与Gateway路由双路线，兼容OpenClaw/AutoClaw/CherryStudio等8个框架，含8条实测踩坑，MIT

Pesquisa web em tempo real para o DeepSeek Harness via API Tavily, com rotação atómica e resiliente de um agrupamento de chaves (rate limit 429, cota mensal 432/433, revogação 401) e contingência keyless — sem nunca interromper o agent loop.

Enhances the native right-sidebar Files tab rather than replacing it: each row gets an @ reference button that inserts the canonical path mention into the composer, plus a size column, a sortable modification-time column, and a status dot for untracked, unstaged and staged files. Below the tree a git bar shows the branch with ahead/behind counts and expands upward into the 20 most recent commits, with a repository selector when a workspace has independent repositories in subdirectories. A header search box walks the workspace recursively and can open a result or expand the tree at it, preview tabs offer reveal-in-tree and one-click @, the tree is keyboard navigable with ARIA tree semantics, and a right-click entry on the Files tab switches back to the native tree at runtime.

Configurable Git commit and pull request prompt instructions for DeepSeek Harness

Agnes AI image/video generation tools (agnes_image / agnes_video) for DSH (DeepSeek Harness). Built-in cross-process RPM rate limiting, 429 backoff and local ffmpeg GIF conversion.

Motor-design AI assistant plugin: requirement parsing → parameter identification → candidate matrix → Top10 verification. L0 is a millisecond-level broad filter (pure JS, zero solver dependency) that ranks candidates and emits the handoff payload for the L1/L2 precision tools; usable as a local agent preset and Cordis plugin. L1 (RMxprt) and L2 (Motor-CAD) are reserved in this version — the level gate fails fast above l0.

Structured git tools for DeepSeek Harness agents: status, diff, log, branch, commit and stash. Output is pinned with ten `git -c` overrides so a user pager, colour or quotepath setting cannot reshape what the agent reads; every invocation is an argv array, so no shell ever parses an argument; and the mutating actions go through the harness approval service, refusing rather than proceeding when no approval service is mounted.

Version-control workbench for the DSH Web sidebar: local changes grouped by type, per-file and multi-file staging, preview-confirmed commit / update / push, and a failure dialog that shows the raw Git output instead of a four-second toast.

Model-driven context compaction for DeepSeek Harness. The agent decides when and what to compress, commits durable session-log replacements, and ships reversible tool-result compression with byte-exact hash retrieval.

A full-page console panel opened from the sidebar, with eight tabs: an overview; a session list read from the sessions service (title, directory, running state, updated time, with filters); installed bundles and Loader entries from pluginInventory and pluginManager, with per-bundle enable switches; a plugin market listing public topic:dsh-plugin repositories from the GitHub search API; a model and provider editor that writes the llm-pi-ai settings namespace through remote.settings.mutate (switch a session model, add or edit providers and their model lists, and store API keys via remote.credentials, merging over the stored profile so fields the form does not expose survive an edit); MCP and skills tabs; and a usage tab that reads the host's loopback /api/dsh-usage/overview document. Services are declared through ctx.inject, so a deployment that omits one mounts without the console rather than crashing.