Memory

Lightweight cross-session reflection: at the end of each turn it writes 3-5 reusable facts (tool chain, file paths, config items, pitfalls) as a card in .dsh/reflections/{date}.md, and on a new session it injects the last 3 cards at the end of the system prompt. Extraction uses the real ctx.llm.stream; when no model route is available it falls back to a heuristic built only from the session log and labels the source honestly on the card. No timers, no quarantine, no approval flow; cards are plain Markdown you can edit or delete.

Long-term memory ported from the OpenAI Codex memory pipeline: sessions idle for 6 hours are extracted in the background by a chosen model, then merged by a hidden agent into a Markdown memory folder at most every 6 hours; new agents get the memory summary in the system prompt plus four tools to list, read and search memory and save corrections. Models are chosen on a settings page or with /memories; an optional filter keeps a notes folder out of memory.

Shares one set of Markdown memory files between DSH and WorkBuddy: project memory, user memory and the user profile are injected into the session context, while daily notes stay out of the prompt and are read, appended and archived through the tools. Six tools (status, read, search, append, edit, prune) write back through a cross-process lock, revision check, backup and atomic write, and a panel in the left rail and the right sidebar edits entries, sections and whole files.

Every few turns asks the model whether anything is worth keeping, then sorts the answer into memory, skill or hook.

Turn completed DSH conversations into a local, versioned memory wiki with a sidebar manager, memory map and run logs.

Bridges a memory-nebula store into DSH: a panel inside the Harness UI to search, edit, pin and forget memories, plus three agent tools to check, search and revise them.

Grok-bot-style AI organization in the sidebar: a chief-of-staff agent creates departments, roles and per-department group chats, dispatches each task to child agents running on this machine, and reports finished work back as one assistant message. Its HTTP routes have no DSH access check, and they can create agents and dispatch tasks to them.

Workspace long-term memory for DSH: records rationale, lessons and constraints that files never capture, then injects them into later sessions automatically.

Port of MiMo Code's infinite-context memory: as the window fills it asks the model in the background (the current provider route unless writerProvider/writerModel is set) to write a structured checkpoint and a project MEMORY.md, then, ahead of DSH's native compaction, replaces the visible window with a rebuilt dump of tasks, checkpoint, recent user messages, memory and notes, falling back to a MiMo-style compaction. Memory files live under $DSH_HOME/mimo-context (per session, per project, plus a read-only global one); it adds mimo_* memory, history, checkpoint and rebuild tools and /mimo-* commands, with dream/distill off by default. Needs DSH 0.2.2-rc.1 or a later 0.2.x.

Local-first knowledge base for DeepSeek Harness: workspace Markdown notes with provenance, review status, BM25 search, and four km_* tools.

Makes a DeepSeek Harness agent reason in Simplified Chinese: each turn it appends one runtime-context instruction at the end of the conversation, and it can keep a stable declaration in the system prompt as well. Settings pick Simplified Chinese or off, and whether that declaration is included.

Daily chronicle for DeepSeek Harness: collects session events, closes the previous calendar day after midnight into a Markdown week file (LLM scoring adds a daily summary; rule scoring does not), and extracts durable facts — decisions, conventions, pitfalls — that merge across days and can be superseded. 10 tools, a read-only sidebar panel, rule export, and a standalone Obsidian vault; zero third-party dependencies.

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.

Local-first memory nebula for DeepSeek Harness with graph views, evidence chains, hygiene checks, and offline snapshots. Reads the memory stores of every workspace and of other memory plugins (read-only, for example meow-memory's SQLite) and writes only under $DSH_HOME/memory-nebula. Registers 9 agent tools and a system-prompt section (usage rules every turn, plus not-yet-read neighbouring memories after a few reads); its /export and /share endpoints return the full memory text without authentication on the local server, and an optional standalone engine listens on 127.0.0.1:7890.

Local jot-down notes for DSH: one Markdown file per note, stored under ~/dsh随手笔记 by default (portable home path, no drive-letter assumption). Redesigned card UI, trash bin (deletions restorable for 30 days), custom tag management with stable per-tag colors (create tags ahead of use, delete one everywhere), compact/comfortable density, adjustable font size and line width, flat quick-scan list, full-text search, Markdown preview, autosave, batch deletion, zero-dependency Office text extraction, and AI write-back from conversations. Heavily reworked from dsh-knowledge-lite; pick the old library via the in-app root picker to migrate.

Local long-term memory core for DeepSeek Harness with plain-text notes, a bounded index, five tools, optional host-model consolidation and auditable evidence. It appends every user and assistant message under 32,000 characters to ~/.companion/cold/<date>.jsonl in plain text, with no built-in cleanup, and adds a short index of its notes to every system prompt; the optional model-based consolidation is off by default and, once on, sends those messages to the session's model.

Delivers one required user-role runtime context that makes the agent reason in Simplified Chinese and keep a whale-loli in-thinking persona (calls itself 本鱼, lazy-arrogant tone) in both reasoning and the final reply, while proper nouns, identifiers, paths, commands, URLs and error text stay verbatim; persona, extra proper nouns and context order are configurable. Enabled by default for every agent in the profile, subagents included.

Add one global prompt or persona that is injected into every new DeepSeek Harness conversation.

Native Google Antigravity agents loader and subagent orchestration engine with model selection and Web UI settings integration. Loads agent definitions from ~/.agents/agents and the workspace's .agents/agents; the selected main agent's instructions go into the system prompt, and a matching agent's instructions are prepended to DSH's own subagent and spawn_teammate calls. Settings are written to .agents/agents/settings.json in the workspace.

DSH plugin: persistent local memory powered by @rsrsai/memlite (respire-aligned prompt/recall/wrap-up logic; JSONL causal tree, git sync, data-compatible with Rust memlite; four-view memory browser with conditional writes, receipts and status).

Brain-inspired cognitive architecture for DeepSeek Harness: hippocampal episodic memory, cortical semantic memory, spreading-activation recall, appraisal-based emotion, neuromodulator state, Big Five personality and dual-process judgment.

Context-budgeted local memory for DeepSeek Harness: fixed ~600-token cache-friendly injection (session/daily snapshots), three-stage sleep consolidation, spaced repetition, temporal validity, subagent-driven L0 mental-model rewrite, typed memories (fact/s

Back up and restore dsh-mnemon memory and skill components (memory spaces, project documents, runtime memory, skill files, skill data) to S3-compatible storage or WebDAV.

Evolver for DeepSeek Harness, by EvoMap: recalls a proven strategy behind each prompt, reports its reuse at turn end, and distills verified work outside the conversation.