Plugins
Browse, filter, and install DeepSeek-Harness plugins.
241 plugins found
loopx (dsh-loopx-plugin)
loopx-project/loopx
LoopX, a provider-neutral, local-first state kernel and control plane for long-horizon agents: keeps Goal, Todo, gate, evidence, quota, recovery, and handoff state above DeepSeek Harness, while the plugin bootstraps the CLI and skills, admits bounded same-session continuation, and adds a loopback GoalBar for the exact bound loop.
loopx (dsh-loopx-plugin)
huangruiteng/loopx
LoopX, a provider-neutral, local-first state kernel and control plane for long-horizon agents: keeps Goal, Todo, gate, evidence, quota, recovery, and handoff state above DeepSeek Harness, while the plugin bootstraps the CLI and skills, admits bounded same-session continuation, and adds a loopback GoalBar for the exact bound loop.
dsh-image-gen
shanliuling/dsh-image-gen
Native conversational image generation for DeepSeek Harness: ask the agent to create an image, and it handles generation and keeps the result directly in the conversation.
echocat-skill-panel-3.0
vderr/echocat-skill-panel-3.0
Reports which skills each turn invoked (loaded by the model, typed as /name, or none) and manages the local skill directory: install from a pasted repository, folder, SKILL.md or zip address, set a Chinese display name in the skill meta.yaml, and remove a skill while keeping a backup.
dsh-echocat-skill-panel
vderr/dsh-echocat-skill-panel
Reports which skills each turn invoked (loaded by the model, typed as /name, or none) and manages the local skill directory: install from a pasted repository, folder, SKILL.md or zip address, set a Chinese display name in the skill meta.yaml, and remove a skill while keeping a backup.
mneme (dsh-mneme)
slow-stack/mneme
The memory that dreams — cross-session memory for DeepSeek Harness: recalls you across sessions, auto-consolidates in its sleep (autoDream), freezes conflicting memories for your review, and keeps a replayable audit trail. Offline-first local semantic search over SQLite with human-editable Markdown mirrors, an entity graph, an interactive memory panel, plus an external API and CLI.
dsh-mneme (dsh-mneme)
slow-stack/dsh-mneme
The memory that dreams — cross-session memory for DeepSeek Harness: recalls you across sessions, auto-consolidates in its sleep (autoDream), freezes conflicting memories for your review, and keeps a replayable audit trail. Offline-first local semantic search over SQLite with human-editable Markdown mirrors, an entity graph, an interactive memory panel, plus an external API and CLI.
dsh-win32
sjh9714/dsh-win32
Diagnoses and repairs DeepSeek Harness on native Windows around the official persistent PowerShell and Workspace Write stack, creates the desktop shortcut, and keeps earlier Git Bash and BusyBox presets behind an explicit legacy setup. No WSL.
dsh-mneme
modusensus/dsh-mneme
The memory that dreams — cross-session memory for DeepSeek Harness: recalls you across sessions, auto-consolidates in its sleep (autoDream), freezes conflicting memories for your review, and keeps a replayable audit trail. Offline-first local semantic search over SQLite with human-editable Markdown mirrors, an entity graph, an interactive memory panel, plus an external API and CLI.
dsh-agency-agents
michengai/dsh-agency-agents
Adds a summonable domain-expert roster that runs as subagents while the parent session keeps the task and final answer.
dsh-omi-voice
polinnizhong/dsh-omi-voice
In-chat read-aloud for DeepSeek Harness: tap to read, pause and resume AI replies with natural Doubao TTS voices (BYOK), reading only the final answer with code, tables and diagrams filtered; local engine, plugin keeps no API key.
dsh-lark
omdsh-dev/dsh-lark
Lark/Feishu bot channel for DeepSeek Harness: each chat drives its own agent, and tool approvals, model questions, and plan reviews return as cards answered by a button or a reply. Switch workspace and model from the chat (`/cd`, `/model`, `/new`), and run several bots that keep separate sessions and can hand turns to each other in one group.
TinyTitan (dsh-tinytitan)
pummelchen/tinytitan
Keeps a local TinyTitan model server reachable from the harness: refreshes the llm-pi-ai route from the installed models and mounts a compaction backend that does not think.
fn-os-apps (dsh-codebuddy-plugin)
tnnevol/fn-os-apps
Tencent CodeBuddy model provider for DeepSeek Harness that signs in with browser OAuth instead of an API key, lists the CodeBuddy model catalog with the context, output, tool-calling, reasoning and image capabilities of each model, keeps multiple accounts with automatic failover to the next usable one, shows remaining quota in the composer with a token and credit usage panel, and completes automatable CodeBuddy growth tasks per account with an execution log. Install from npm with `dsh plugin --profile web add @tnnevol/dsh-codebuddy`.
dsh-nested-followups
sluminositys/dsh-nested-followups
Keep branching from any completed answer at any depth while the main session stays untouched.
dsh-opencode-palette
featherhunter/dsh-opencode-palette
Ports all 38 opencode themes (33 TUI + 4 desktop 2.0 + system) into DeepSeek Harness: data-driven pipeline (JSON → color resolve → DSH override), per-browser persistence, monospace/proportional choice, five code fonts, and a system fallback that keeps typography only.
CiteCiter (citeciter)
kirkchinese/citeciter
Select text in a committed DSH response to open an independent, persistent, read-only multi-turn Topic bound to source-session evidence and project files while the source Agent keeps running.
clutch-dsh (clutch-dsh-worktree)
cerbur/clutch-dsh
Adds a Worktree view to DSH Web UI that groups Sessions by Git worktree while keeping DSH as the source of truth.
dsh-jev-interceptor
asktheway/dsh-jev-interceptor
Classifies pending tool calls with Jev (TypeSafe AI's non-generative decision model) on tools/pre-execute — confident high-risk calls are denied, ambiguous ones escalated to approval — and auto-approves clearly-granted reversible calls on approval/request behind argument-evidence gating. Also subclasses the session-reference resolver so snapshots keep Jev-scored messages instead of dropping oldest-first. Degrades to stock behavior on any provider failure; shadow mode with a /jev-stats command; TypeSafe or OpenRouter endpoints; 64 tests.
dsh-plugin-hub (dsh-provider-usage)
wingsky-1/dsh-plugin-hub
Multi-provider usage stats framework (v2 adapter contract): persistent capsule plus detail panel; DeepSeek official (interval-bookkeeping daily usage derivation with a peak/valley countdown badge, working even without an official usage endpoint) and OpenCode Go built in; any other data source joins by dropping in a single mjs adapter file, hot-swappable from the settings page, with API keys kept on the host.
dsh-plugin-hub (dsh-lan-proxy)
wingsky-1/dsh-plugin-hub
Access the dsh web UI over LAN: HTTP/HTTPS/WS forwarding plus TLS (self-signed or custom certificates); adaptive Brotli/gzip compression for HTTP and permessage-deflate for WebSocket; half-open WebSocket probing keeps mobile clients from going stale after backgrounding; launch-token auto-injection lets LAN devices connect without copying the token; DNS-rebinding protection + loopback-only upstream allowlist.
dsh-plugin-hub (dsh-mcp-manager)
wingsky-1/dsh-plugin-hub
MCP server manager (stdio / streamable-http): per-working-directory project and global config tiers; project-level MCP collapsed into 4 atomic tools through a middleware layer by default (`middleware: all` folds in global servers too, hot-switchable in the settings page); workspace isolation prevents cross-project interference; configs keep `${ENV}` references only, with no plaintext secrets on disk; runtime registration API for other plugins to inject MCP servers.
dsh-ssh-ops
caoyiwei850/dsh-ssh-ops
SSH ops terminal for DSH Web UI: drive a connected server from the main conversation (ssh_connect/ssh_exec/ssh_read/ssh_write/ssh_disconnect) while keeping an interactive xterm.js terminal on the right.
StrataGate-AgentMemory (deepseek-harness)
diqierjia/stratagate-agentmemory
StrataGate gives DeepSeek Harness evolving, local-first long-term memory for user preferences, project decisions, conversations, and tool results across sessions; it layers history with user-tunable time decay, reinforces memories through real answer use, shows workspace-aware usage counts, and keeps recalled evidence traceable to its original messages.