Plugins

Auto-supplement QMD semantic search when the model greps/globs a knowledge-base directory: zero-dependency DSH plugin, async injection via next-step, no manual invocation.

Tracks the agent's state as Yogācāra mental factors over a durable seed store, and feeds it back into the prompt as first-person inclination.

Bi-temporal memory backed by a SodaMem daemon: recall is contributed to the prompt while each turn is assembled and every closed turn is ingested, with no tool call and no model call on the read path; each recalled fact cites the turn it came from and carries validity dates, so superseded facts stop being retrieved.

Project memory for coding agents on DeepSeek Harness: similar past edits surface as precedents, out-of-scope edits are blocked, and cognition persists across sessions (47 upstream-verified fixes, gold-free 20-task run).

PLUR memory rendered into the system prompt on each assembly rather than exposed as a tool call, so the block is replaced instead of appended and context stays flat across a session. Fully local hybrid search (BM25 + BGE fused with RRF), plain YAML storage you can edit, per-workspace scoping, and a /plur-memory browser.

Hana-style assistant manager for DSH: visual preset management (cards, yuan personalities, avatar cropping) plus a full Hana memory stack (rolling summaries, layered compilation, SQLite fact store, deep memory).

LLM-driven remember/forget memory: after each turn a model decides what to keep (MemoryDirector), injects relevant memories before each step, dedups, and persists cross-session.

Compaction backend replacing LLM summarization with a deterministic semantic extractor (keeps code/paths/commands, drops chatter) plus 28.4x KV-compression accounting.

Organize folders and sessions into projects with shared PROJECT.md memory and AGENTS.md instructions injected into every session, plus a project tree sidebar.

Session context triage for long DeepSeek Harness sessions: deterministic screeners trim stale, duplicate, failed, and oversized content through the official ctx.compaction seam.

Cross-session event-cue memory for DeepSeek Harness: auto-extracts task/conversation cues and user language habits from every turn into a persistent global cue bank, then re-injects remembered context on topic-switch detection (keyword or vector matching).

Native per-workspace memory on the harness's own seams: facts and a bounded always-on profile on the storage-domain JSON unit, approval-gated writes with `(sessionId, seq)` citations, deterministic recall plus session-query FTS over past sessions — no external server, no custom SQLite.

Memory protocol enforcement plugin: bridges the opencode-memory MCP server, forces memory_weave before tool calls, auto-ingests turns, and injects memory context into agent steps.

PostgreSQL-backed durable memory for DSH agents: MCP memory tools plus a Web panel for reviewing memories and candidates.

Focus board for DeepSeek Harness agents: durable, model-maintained notes in the session workspace that pin the objective, constraints, and decisions across compaction and sessions, with automatic context injection, archive on clear, and an optional web panel.

Session lifecycle CLI: export (md/json/jsonl), archive/restore, trash, search, and stats. Read-only by default; nothing is ever deleted by the engine.

Automatically starts a fresh Web session near the context limit with the last complete turn, and adds an editable additive whale-maid persona with on-demand reload.

Session manager for the DSH Web UI: browse all and archived sessions, restore/unarchive, delete with two-step confirmation, and preview conversation content from the Settings panel.

A floating button beside the chat that opens a searchable list of all questions in the session for quick jumps.

Multi-folder workspace: a durable global linked-folders list plus per-session on-the-fly linking (link_folder/unlink_folder), managed from the Web sidebar with a native folder picker.

Adds a configurable humanized whale-girl maid persona with immersive roleplay, speaking modes, and a lightweight layered memory with query-triggered recall.

Two-phase session captioning: instant keyword titles while the conversation is busy, then cheapest-budget-model refinement plus a one-line summary once it goes idle.

Discover and verify portable RoleHub roles, pin each exact bundle, then launch its prompt and bundled skills in an isolated, continuable DSH Session with Host-approved tool bindings and optional Agent Team Room attachment.

Guards the persisted session-projection cache: per-row JSON degradation so one misbehaving projection unit (e.g. a third-party plugin storing a Map) can never stall session titles or the whole cache again, plus a startup self-heal that backfills missing titles.