A

adoresever/graph-memory-pro-dsh

“Designed for DeepSeek Harness memory workflows.”

OverviewREADME

TL;DR

Read-only Graph Memory Pro graph view for DeepSeek Harness Web.

30 days of GitHub stars

+25 stars

+3.9% observed change

Oct 15+0 stars649 totalOct 16+1 stars (estimated)650 totalOct 17+1 stars (estimated)651 totalOct 18+2 stars (estimated)653 totalOct 19+2 stars (estimated)655 totalOct 20+0 stars655 totalOct 21+1 stars (estimated)656 totalOct 22+1 stars (estimated)657 totalOct 23+1 stars (estimated)658 totalOct 24+0 stars (estimated)658 totalOct 25+1 stars (estimated)659 totalOct 26+1 stars (estimated)660 totalOct 27+1 stars (estimated)661 totalOct 28+1 stars (estimated)662 totalOct 29+1 stars (estimated)663 totalOct 30+1 stars (estimated)664 totalOct 31+1 stars (estimated)665 totalNov 1+1 stars (estimated)666 totalNov 2+1 stars (estimated)667 totalNov 3+1 stars (estimated)668 totalNov 4+0 stars (estimated)668 totalNov 5+0 stars668 totalNov 6+1 stars669 totalNov 7-1 stars668 totalNov 8+3 stars671 totalNov 9+2 stars673 totalNov 10+2 stars675 totalNov 11-1 stars674 totalNov 12+0 stars674 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