An auto-memory plugin for the DeepSeek Harness Web GUI that maintains three layers of context — user-level facts, project notes, and daily logs — with automatic injection and retrieval. It adds daily reflections, a visual panel and settings page, and can inherit historical memory from other AI tools.
A caring memory companion for DSH — three-layer auto memory, proactive calendar reminders, warm AI greetings, per-turn auto-consolidation, and inheritance of memories from other AI tools.
Copy the command below and run it in your DeepSeek Harness terminal.
dsh plugin add github:Aik358/dsh-auto-memory ⚠️ Plugins run with the permissions of your dsh process and may execute code at install time. Review the source repository and its license before installing. Pin the commit hash for reproducible installs. Plugin safety →
Centralized storage (WorkBuddy-style) : all workspace memories live under one root — /.dsh/memory/workspaces/, one subdirectory per workspace (readable by any model in any session via injection + cross-workspace memory recall). Legacy per-workspace .dsh-memory/ folders are auto-migrated on first run after upgrade (the old copies are kept, not deleted).
Auto injection (at the end of the system prompt) : every prompt gets a block (user rules + project notes + reflection digest + recent 1 day of log tails + external memory paths + pending calendar items + writing discipline); it is placed at the very end of the system prompt so the model reads the memory discipline right before replying - Lean by default, details on demand (v0.1.24) : injection stays small — the last 1 day of logs, a reflection digest (achievements section only), and paths for external memory instead of full text. memory read fetches full log/reflection/user/notes/calendar files when needed; sensitive sections (credentials/tokens/secrets) are filtered out of the prompt but kept in the files - Visible memory ops : when the AI updates or searches memory, it says so in plain text in the chat reply (e.g. "Logged X to today's journal", "I checked memory and found..."), not hidden inside tool calls
Auto-Consolidation — memory writes itself after every turn (v0.1.9)
Every finished conversation turn is…
Learn how to choose, install, and use memory plugins.
dsh-auto-memory is a memory plugin maintained by Aik358. An auto-memory plugin for the DeepSeek Harness Web GUI that maintains three layers of context — user-level facts, project notes, and daily logs — with automatic injection and retrieval. It adds daily reflections, a visual panel and settings page, and can inherit historical memory from other AI tools.
Run dsh plugin add github:Aik358/dsh-auto-memory in your DeepSeek Harness terminal. The dsh CLI resolves the plugin from GitHub and installs it into your active profile. For reproducible installs, pin a commit hash: dsh plugin add github:Aik358/dsh-auto-memory#commit.
dsh-auto-memory is a community open-source project released under the BSD-3-Clause license. You can inspect its source and install it for free.
A knowledge-graph memory plugin for AI agents: conversations are distilled into structured triples, compressing context by up to 75% and enabling traceable, searchable, cross-session experience reuse. One memory core, native to DeepSeek Harness, with the OpenClaw plugin entry retained.
View plugin → 
adoresever
LLM-supervised persistent memory for AI agents — graph-based recall and knowledge management.
View plugin → 
mnemon-dev
Memtrace turns your codebase into a live knowledge graph that AI coding agents can query in milliseconds — every function, class, call edge, and version, across every session, without re-reading files or breaking things they can't see.
View plugin → 
syncable-dev