All Plugins

Enhanced auto-compaction defaults for DeepSeek Harness agent presets: apply tuned threshold/retention budgets and per-model policies with one command, idempotent with backups and rollback.

Vector + graph memory backend: observe/remember/search/recall tools against a local memoria server, fusing HNSW semantic recall, FTS5 keyword search, and knowledge-graph signals via RRF ranking, with automatic turn-end persistence and per-agent namespace isolation.

Cross-session memory vault: remember / recall / forget tools, per-turn prompt injection, and a settings-page entry browser.

Faithful port of the hermes-agent MEMORY.md / USER.md mechanism for DSH: bounded dual-bank memory (2200/1375 chars), a single `memory` tool (add/replace/remove/batch), frozen-snapshot injection per session, nudge reminders, DSH-native JSON storage — zero external dependencies, zero LLM cost.

Bridge into a global Markdown knowledge base shared with the Codex kb.cmd CLI: kb_add/kb_search/kb_show/kb_timeline tools with byte-compatible frontmatter.

Self-maintaining handoff memory per working directory and git branch: records turns, folds them into concise Markdown, and injects the result into future sessions from ~/.agent/agent-handoff, byte-compatible with pi-handoff.

Agent tools for a self-hosted mem0 server: add, search, get, update, delete, history, reset and status memories, with a settings-panel configuration card.

Conversation history recall for DSH: three-layer (literal/fuzzy/semantic) retrieval over every past session's original text, fully local & offline — AI never forgets what you told it. One-command install via `dsh.bundle.patch`, semantic layer runs in a worker thread.

Automatic, local-first cross-session memory for DeepSeek Harness: layered Event/Element cards, evidence-gated recall, and expansion back to original turns and tool results.

Model-authored context pruning for DeepSeek Harness through the official compaction API.

Long-term memory injected at session start: preferences/facts/summaries/knowledge in global and per-project scopes, budgeted recall via `agent/pre-step`, durable JSON store.

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).

Turns local markdown and text documents into a queryable knowledge base with hybrid semantic and keyword search, citation verification, and source injection.

Brings your existing Claude / ChatGPT history into DSH: instant zero-token import of the memories.json inside a Claude export, local Claude Code transcripts with no export needed, and conversations distilled through the model you already configured in DSH. Every memory carries verbatim evidence checked against the source by code — a paraphrase is dropped and counted, and evidence found only in the assistant turns is always routed to review rather than stored.

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

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.

DSH ↔ agentmemory session-memory bridge: mirrors session lifecycle into a local agentmemory daemon (REST), exposes memory_recall / memory_remember tools, and injects a per-session memory context window via agent/pre-step.

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