Plugin

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.

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.

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.

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, with smooth hover-open/close behavior.

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.

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.

Export complete Web Sessions to local Markdown or self-contained HTML, with stable rendered previews, default redaction, and opt-in bounded tool-call details.

Read-only side-by-side comparison of related DeepSeek Harness conversation histories, including messages, tool calls, responses, timing, and usage.

Create/modify/inject test assistant messages and import/repair session.jsonl(.zstd) session logs into new sessions.

Archived conversations list in the sidebar footer with read-only previews of the most recent messages, for sessions the product deliberately keeps hidden and unreopenable.

A GUI subagent-model selector beside the main model seat: pick a model and reasoning effort per session, applied to every in-process subagent.

xAI Grok subscription chat: SuperGrok or X Premium+ OAuth, a displayed model subset, Responses through the Grok CLI proxy, and always-on server-side web_search and x_search.