Plugins

Long-term memory for DeepSeek Harness, read-only as of 0.1.0: a scribe_recall tool that reads a plain-markdown memory room, path rules that refuse directory traversal, Unicode smuggling and NTFS alternate data streams, and a bounded index whose truncation is always reported rather than silent.

Persona engine for DeepSeek Harness: one config.json drives the AI's self-name (per model, per tier), how it addresses you, relationship stance, character text, per-item work contracts with individual toggles, thinking-chain language, appearance and reply tone (both opt-in and per-model overridable), and long-term memory gated by human confirmation - the AI can only append proposed candidates, a human confirm line flips them into effect, and the log is physically append-only and replayable. Confirmed entries are injected as a quoted data-not-instructions block; entries tagged with a kind can instead be routed to arbitrary files on confirmation and never reach the prompt. Three prompt sections re-evaluate from disk on every assembly, so edits apply on the next step with no restart. Persona presets are shareable JSON snapshots (imports and exports SillyTavern character cards, v2/v3 read, v2 written) and deliberately never carry memory. Zero runtime dependencies, no network, no shell; any error degrades to an empty section rather than a broken session. Ships blank - installing changes nothing until you write something.

Conversation outline panel for the DSH web surface: user questions as root nodes (index, time, tool count and text volume per turn) with the Markdown headings of assistant replies hanging beneath them, plus level slider, search scope, bookmarks, copy and export as Markdown, section jump, keyboard navigation, a right-edge density rail and per-session reading-position memory. Read-only UI: it never touches prompts, tool results or provider traffic, and writes nothing outside its own localStorage keys.

loci second-brain sidebar tab: hybrid search, cited Q&A, day-grouped memory browsing and quick capture over a local loci knowledge base; proxies `loci serve-http` same-origin from dsh-better-sidebar, no core fork.

Skill that fact-checks a claim against the open web rather than model memory: it splits the claim into independently checkable fact points, routes each point to the primary-source ladder for its domain (policy, academic, medical, financial, disaster and accidents, food safety, science, education, sports, entertainment, judicial, and more), searches domestic and international ecosystems in parallel, fetches primary pages, grades sources by type, re-searches with debunking keywords, and reports conclusion-first with a full URL and citation position behind every statement, keeping unverified and undecidable points separate from confirmed ones. Three factual judgements can be routed to a TypeSafe Jev (System One) decision model when a key is configured, falling back to the skill's deterministic rules when it is not; a model verdict can only lower a confidence tier.

Deterministic cross-session transcript retrieval for DeepSeek Harness: the model-facing `recall` tool searches past session logs with explicit scope control

Make the AI remember how you think, not what you said: actively captures your principles, redlines, and working habits across sessions — with memory capacity, graceful decay, and human-readable reasoning for every entry. 0.7.0 brings an intuitive persona portrait with evidence tracing.

Local relationship-memory workbench with a confirmation gate: every AI write — extracted memories and newly created contacts alike — lands in a pending queue until the user confirms it in the GUI; materials are archived verbatim with quote-level provenance checks on AI extraction, and confirmed memories aggregate into per-contact timelines, gift occasions and reciprocity views. Ships a native relationship agent preset for conversation capture; JSON storage by default with an optional SQLite backend, zero production dependencies.

Cross-session memory for your dsh agent: remembered, recalled, and re-verified instead of assumed.

Installer and configuration base for a five-plugin DSH assistant suite: probes the Python, WPS and workspace environment, installs the sibling plugins shipped in the same repository, and generates the workspace baseline (instruction layer, memory seed, skills, settings); it also contributes its own settings section and its own host-side setup and check logic.

Distills session work into background observations and reflections to preserve context across compaction.

Quick-open palette for the Web GUI: Ctrl+P fuzzy-searches an in-memory index of the session workspace (about 51k entries, median query 5 ms) with per-segment path anchoring, dir: and file: prefixes, Tab directory drilling and :line jumps, opens the picked file in the native right sidebar, and drops a file reference into the conversation draft with Ctrl+Enter. Also adds in-file find (Ctrl+F) and a selection-to-reference action to the built-in file preview.

Read-only enhancer for a file-based long-term memory library (markdown cards in git): a memory_find search tool, a small budgeted memory digest injected into the system prompt, and a settings page with library overview, health-check status and toggles.

Memory archive and prompt viewer for DeepSeek Harness: read back what compaction folded out of context - browse past sessions or Tavern playthrough archives (summary, original text, state) with full-text search - and inspect the prompt each turn actually sent, listing every assembled system section with its order, character count, offset, hash and mutability, plus an assembly map, registry export, and honest diagnostics when a section is empty or its log cannot be read. Optionally provisions a roleplay agent preset.

Per-project memory for DeepSeek Harness. Three Markdown files per workspace — PROJECT.md, DECISIONS.md and SESSIONS.md — are auto-created on the first step of any session in that workspace, re-read from disk and re-injected only when they change (and re-injected if compaction dropped them), and written back by classification through a memory_checkpoint tool, with a bounded end-of-turn nudge when a turn did work but recorded nothing. memory_read and memory_search read the live log and the archive, the latter over a zero-dependency BM25 index. The session log is capped at 200 entries with the overflow moved to SESSIONS-archive.md — never injected, but visible, readable and searchable, and restorable one entry at a time. Settings page: a workspace list with a path filter, read-only tabs for the three memory files plus the archive, reload, export/import of one workspace's memory as a JSON bundle, a two-step clear, a panel that rewrites or removes the AGENTS.md instruction block, and a PROJECT.md staleness reminder. A composer status chip shows that workspace's sync state and creates the files on click. Zero dependencies — no vector store, no embeddings, and no model calls.

Shared engineering skills, a read-only memory-bank dashboard with SQLite audit guidance, and workflow request previews for DSH.

Feeds every dsh prompt into the local agent-feedback-loop feedback-memory pipeline — captures dissatisfaction, reviews it offline into reflections, and attaches the compiled recurrence-rule context back to the turn, never blocking a prompt. Requires the agent-feedback-loop runtime; running agent-feedback-loop install afterwards wires existing dsh profiles automatically.

Coordinates bounded project recall from compatible memory and learning providers, with shared settings and provider lifecycle management.

On-demand memory for DeepSeek Harness: session logs are distilled into layered markdown (a summary, an index and per-topic files), and a mem_query tool returns only the matched entries rather than the whole index. Nothing is injected per turn, there are no dependencies, and every entry keeps a source pointer back to the conversation it came from.

Layered cross-session memory for DSH that pushes only what changed. The first round injects every active entry, later rounds push only added / updated / removed ones, and nothing at all is injected when nothing changed. Facts and decisions carry semantic keys (one active truth per key), the model may only write to an inbox that a human promotes, an entry can carry a review date that raises a one-time reminder when it comes due, search is relevance-ranked with Chinese matched by bigram, and a sidebar tab tells the lifecycle story instead of just listing files — entries are grouped into awaiting confirmation / in use / archived, viewable by type, tag or date, and the tab can promote a candidate, withdraw or archive a standing entry, restore an archived one and delete a candidate, alongside the global and workspace instruction files and the current injection size. A zero-dependency CLI ships with it, so the store is usable without DSH.

Layered memory for DSH whose agent-facing surface is 10 tools: high-privilege writes (memory_add, memory_delete, memory_import), rumination controls (memory_ruminate, _cancel, _status), and a memory graph (memory_search_graph, memory_expand_graph_node), built over an L0-L3 distillation pipeline that recalls and injects relevant memories before each model step.

Adds a multi-user settings panel to the DSH web client: usage-mode selection, member management with online status and device binding, and switching or sharing of per-member memory and knowledge bases.

Cross-session memory for DeepSeek Harness: agents save, search and update user preferences, facts and project decisions; important entries are injected into later sessions, and a Settings section lists, edits, archives or deletes them.

Cross-project experience recall for DeepSeek Harness: when the running work matches something your memory store already learned elsewhere, that lesson is injected before the next step. Runs fully locally, judged by a local small model.