Plugins

Local-first experience library for DeepSeek Harness: error-signature retrieval, pre-step recall hints, failure-to-fix drafts, gap-to-entry closure, and a full-page library view. Ships a sanitized starter library. No model calls, no network.

Adds a native Store section to DSH Settings for catalog search, tag filtering, sorting, installation, and installed-plugin management.

Task planning with experience muscle-memory: condition-reflex recall of past solutions, LLM capability matching, and auto-persisted lessons.

Local-first memory and persona plugin for DeepSeek Harness: four file-backed memory layers (pinned, memory, facts, experience), editable SOUL/MOOD persona, zero-LLM session capture, BM25 recall and a themed mood card; no standalone web panel, Python service, vector database, or API key.

Long sessions get expensive, and the platform compacts the context on its own. This plugin adds an occupancy badge (hover to see how it is computed), writes a handover draft into HANDOVER.md from 45% — files changed, money spent, what recent turns were about — and reminds you once at 60% to wrap up. On compaction it records the reading from just before, so you can check it later. No model calls, nothing added to the conversation; it does not prevent compaction.

Cipher memory platform as a DSH bundle: four memory types (attention, experience, preference, cognitive) sedimented per turn by four memory agents, cross-session deterministic recall injected via systemPrompt.context, insight review kept out of user-facing output, per-session UNNI/LOOP modes with memory-driven auto-continuation, memory search/ingest tools, plus a settings page (SOUL editor) and an AgentPool panel.

Let DSH act as a Locus client to deliver a one-stop Unity development experience. The plugin itself does not depend on Locus: you can install the Locus plugin for your Unity project in the settings interface. Features include operating the Unity Editor through Locus’s native broker; semantic analysis and debugging of C# code; and previewing prefabs and 3D models in the sidebar. Its Unity tools can evaluate C# on the editor main thread and edit assets and scene objects.

Requires dsh-mnemon. Experience-library memory-space provider for dsh-mnemon, with exp_recall / exp_record / exp_feedback / exp_type tools.

FanFrame (繁界, “Fanxing’s realm”) lightly polishes the DeepSeek Harness Desktop UI for a more comfortable everyday experience.

Cross-session experience memory for DSH. Lessons are evidence-graded, injected when the turn is about the same thing, and shown just before an action only when the record declares which call it applies to. A rule that holds whatever the turn is about — "always answer in Chinese" — can be marked **standing** and is then carried every turn: measured on 24 isolated real-model turns, a standing rule is followed 6/6 against 0/18 for the controls (empty store, same record unmarked, unrelated standing record). A guess still cannot become always-on: a standing record needs a verified passage like any other. What nobody looks up is retired, reversibly. Five tools, seven slash commands, zero runtime dependencies.

Recalls lessons recorded in earlier projects: when the running work matches one, the local model decides whether to inject a short note before the next step. Requires a local Ollama model (default qwen3.5:9b) and the dsh-mnemon store with its mnemon CLI; without them it only observes and logs, never injects.

Evidence-governed experience memory for DeepSeek Harness

Turns completed DeepSeek Harness public-content work into a browser-local visual magazine with explicit updates and reviewed one-article sharing.

Experience validation layer for DSH: zero-token collection of tool-failure/retry/search signals, AI refinement into verified skill books (three-layer verification), looked up at task start. Ships 10 trial skills and benchmark data (complex-task success 100% vs 60% bare).

Global experience archive for DeepSeek Harness on Windows: probes local tools (with versions and PATH-first hits), convenient paths, network latency and disk speed; folds per-session stats from session/event; LLM-extracts durable facts; env_profile tool with remember; byte-stable summary injected every turn to speed up sessions and cut token use.

DeepSeek Harness automatically opens browser plugins and includes a built-in WebView2 program to achieve a lightweight desktop experience.

Experience and skill engine with a sidebar console and exp_record / exp_recall / exp_feedback / exp_consolidate / exp_type tools, stored in a local JSON file. Optional Git backup (off until you configure a remote) pushes the library to a remote you choose; GitHub sign-in uses a device code or a token kept in local settings.

What it does while she sleeps, in one card. Two things: (1) tidy the element memory — merge synonyms only when the model agrees, trim descriptions, prune weak links, propose analogies for the user to confirm, with a backup before every write and a 15%-of-library cap per pass; (2) dream — stitch her own past experiences (plus props from the element memory) into a short 3–6 sentence story, leave one line on her desk as a note labelled "this is a dream, not something that happened". The dream lives in its own file and never enters her memory or her personality prompt. Requires @ssamurias/dsh-fish for her event stream and dsh-memory-brain for the element library; model-approved merges and dreams need a local Ollama model (or a paid API key).

Reusable experience for DeepSeek Harness: save a successful task as a structured playbook, recall it later as a native skill, and gate deliveries behind user-confirmed checks that require objective evidence before write actions are allowed.

A persona that grows from experience: remembers what happened, becomes someone from it.

A proactive, human-like personal-assistant kernel for DeepSeek Harness: personal knowledge, stable and situational guidance, follow-through tasks, adaptive check-ins, resource discovery, and reusable experience.

Connects DSH and VS Code for a Claude Code for VS Code style experience, continuing the same workspace and conversation right inside VS Code: install the DSH Coding Agent extension and the plugin discovers and connects automatically on the same Windows machine, or connect manually elsewhere by pasting the copied connection address.

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), Harness-RSI (evolves system prompt / memory / skills), and Model-RSI (evolves alpha training recipes via framework-native walk-forward with 2-day gap and multi-seed). Offline one-command run, GPU auto-detect. Ships one skill.

Persistent Bots and group rooms inside DSH. Each Bot keeps its own model, permission preset, workspace and session across restarts; a Bot can also be backed by an installed local agent CLI (Codex CLI, Claude Code, ACP agents) using that CLI's own login and models. Unaddressed messages can be triaged by the room leader, the room accumulates a shared experience card, and every answer is a run in a durable ledger the sidebar panel replays. New Bots default to the full-access permission (any command, any file; the form asks you to confirm the risk), so choose read-only or workspace-write to confine one; Codex CLI and Claude Code Bots at full access run without their own sandbox or permission prompts.