Plugins

White-box AGI architecture exploration: metacognition (self-cognition loop), continual learning (knowledge flywheel), world model (condition space, spatiotemporal memory graph), self-improvement (bootstrap discipline), zero-LLM white-box pipeline, and auditable trust guardrails.

Lets a text-only agent watch a live screen or camera feed: every frame is scored by how much the picture changed, only the ones that matter are packed into one numbered sheet with an audio envelope, so the model looks at what actually changed instead of a screenshot every few seconds.

Use ChatGPT (Codex), Claude, and Grok subscriptions as DeepSeek Harness LLM providers, with Settings login, model catalogs, usage, plus image_generate, video_generate, and x_search tools.

Turns a video (a local file, or a Bilibili/yt-dlp link) into one addressable storyboard grid — numbered cells with exact timestamps, per-cell transcript and an audio envelope on the same timeline — and video_zoom re-reads any window at higher resolution, so a text-only model can look at the video instead of reading a summary.

Unofficial Command Code LLM provider: registers a `commandcode` route with a live model catalog and reasoning-effort support.

Read-only Molio knowledge base tools: list vaults, browse the file tree, full-text search and read documents, served over the local Molio daemon HTTP API, which must be running. Published on npm as dsh-plugin-molio.

Molio 知识库插件 for DeepSeek Harness (dsh) — 在任意 dsh 会话中搜索、浏览、读取本机 Molio 知识库

LLM-supervised persistent memory for AI agents — graph-based recall, cross-session knowledge, single binary. Works with DeepSeek Harness, Claude Code, OpenClaw, and any agent runtime.

Exposes OpenCode Zen free models to DeepSeek Harness, with no API key.

Mnemonic layer.

Adds a deepseek-web provider that uses chat.deepseek.com web models in DSH, with browser login capture, PoW request signing, SSE streaming, and prompting-based tool calls.

DeepWatch's capabilities, installable into an existing DeepSeek Harness profile

ThoughtDAG for DeepSeek Harness: turn the current DSH session into an editable thought graph on an infinite canvas.

Configurable OIDC login and token-authorized model access, including LiteLLM and opt-in oidc-llm integration, with a standalone DSH Web backend.

Provides read-only tools for querying authorized WeLink conversations by date or keyword.

Drags the official reasoning-effort row into a continuous track: blue-to-violet fill, a starfield on the higher levels, and the official value text tinted to the current level. Off stays gray; no official text is rewritten.

Second-model auto-review on the approval answerer chain: a read-only reviewer subagent returns structured allow/deny verdicts with reasons, fail-closed by default.

PLUR memory for DeepSeek Harness — engrams injected straight into the prompt, no tool call required

Evolve skills, agents, prompts, code and plugins from inside DeepSeek Harness, with AgentDescent.

The memory that dreams — cross-session memory for DeepSeek Harness: recalls you and your projects across sessions, consolidates memories while idle (autoDream), freezes conflicting memories for your review, and keeps a replayable audit trail. Memory stays on your machine as SQLite with human-editable Markdown mirrors; four-way recall (keyword, vector, BM25, entity graph) and an interactive memory panel ship with it, plus 10 model tools, an MCP server, an external API and a CLI. Summarization and consolidation run on the host model you already configured; with a local embedder, semantic search runs fully offline.

Cross-session memory plugin for DeepSeek Harness with autoDream consolidation: SQLite store, Markdown mirrors, 10 model tools, automatic injection, session summarization, user profile/rules, custom slash commands, vector (semantic) search, and a Web GUI p

Rewrites outgoing /chat/completions requests with an evolved chain-of-thought scaffold (nine-dimension genome, elitist selection with fragment crossover, one deterministic re-evaluation pass), scores answers against a fixed 20-objective baseline, and appends one line per rewrite to live-requests.jsonl in the plugin data root (default <cwd>/.aecot, overridable with AECOT_ROOT).

在 dsh 里装上这个插件即可，无需登录、注册或填 API Key，就能使用包括 Muse Spark 1.3、MiMo V2.6 在内的前沿模型——完全免费，不限量。 All you do is install this plugin in dsh: no login, no sign-up, no API key — the frontier models are just there, Muse Spark 1.3 and MiMo V2.6 among them. Completely free, with no usage cap.

Long-term memory for DeepSeek Harness kept as plain markdown, one fact per file. Every step the `MEMORY.md` index (the project store if there is one, plus a global store under `$DSH_HOME`) goes into the runtime context, so recall does not wait for a file read. The index has a hard cap, 200 lines / 25 KB by default, enforced by `ctx.tools.guard()`: a write that grows an over-cap index is denied, a rewrite that shrinks it passes. A read-only sidebar Memory page lists the notes by type. The plugin never writes memories on its own. An experimental companion mode adds note types for a persona's own life. The same store also works with Claude Code, Codex, Kiro and OpenClaw.