M

mnemon-dev/@mnemon-dev/dsh-mnemon

“Designed for DeepSeek Harness memory workflows.”

OverviewREADME

TL;DR

Install the full dsh-mnemon integration from the Mnemon repository.

30 days of GitHub stars

+86 stars

+13.7% observed change

Oct 15+0 stars630 totalOct 16+2 stars (estimated)632 totalOct 17+2 stars (estimated)634 totalOct 18+2 stars (estimated)636 totalOct 19+2 stars (estimated)638 totalOct 20+3 stars641 totalOct 21+2 stars (estimated)643 totalOct 22+3 stars (estimated)646 totalOct 23+4 stars (estimated)650 totalOct 24+4 stars (estimated)654 totalOct 25+3 stars (estimated)657 totalOct 26+3 stars (estimated)660 totalOct 27+3 stars (estimated)663 totalOct 28+2 stars (estimated)665 totalOct 29+3 stars (estimated)668 totalOct 30+3 stars (estimated)671 totalOct 31+3 stars (estimated)674 totalNov 1+3 stars (estimated)677 totalNov 2+4 stars (estimated)681 totalNov 3+3 stars (estimated)684 totalNov 4+4 stars (estimated)688 totalNov 5+1 stars689 totalNov 6+3 stars (estimated)692 totalNov 7+3 stars (estimated)695 totalNov 8+3 stars (estimated)698 totalNov 9+3 stars (estimated)701 totalNov 10+8 stars709 totalNov 11+4 stars713 totalNov 12+3 stars716 total

Oct 14Oct 28Nov 12

Also in this category

4 items

V

Memory

vectorize-io/hindsight

Hindsight, agent memory that learns: long-term project memory with auto recall and retain, knowledge pages, deep reflection, and per-repo memory banks.

★ 60.3K

V

Memory

volcengine/OpenViking

OpenViking memory and context bundle for DeepSeek Harness: pre-step auto-recall and profile injection, session capture, `viking://` URI guarding, and recall/write memory tools backed by an OpenViking server.

★ 42K

M

Memory

MemTensor/MemOS

Local-first memory plugin for DeepSeek Harness: layered L1/L2/L3 memory with automatic capture, manual memos_* retrieval tools, and a built-in memory viewer.

★ 12.4K

A

Memory

agentscope-ai/ReMe

Connects DeepSeek Harness to ReMe's local-first, self-evolving personal knowledge base: automatically captures completed main-agent conversations as user-owned Markdown memory, searches conversations and source material through reme_search with BM25, optional embeddings, and wikilink expansion, and schedules daily memory consolidation.

★ 3.8K