A

agentic-os-org/@agentsight/dsh-plugin

“Designed for DeepSeek Harness memory workflows.”

OverviewREADME

TL;DR

AgentSight observability plugin for DeepSeek Harness.

30 days of GitHub stars

+43 stars

+6.9% observed change

Oct 15+0 stars619 totalOct 16+3 stars (estimated)622 totalOct 17+2 stars (estimated)624 totalOct 18+3 stars (estimated)627 totalOct 19+2 stars (estimated)629 totalOct 20+1 stars630 totalOct 21+2 stars (estimated)632 totalOct 22+2 stars (estimated)634 totalOct 23+2 stars (estimated)636 totalOct 24+2 stars (estimated)638 totalOct 25+2 stars (estimated)640 totalOct 26+2 stars (estimated)642 totalOct 27+2 stars (estimated)644 totalOct 28+2 stars (estimated)646 totalOct 29+2 stars (estimated)648 totalOct 30+2 stars (estimated)650 totalOct 31+2 stars (estimated)652 totalNov 1+2 stars (estimated)654 totalNov 2+1 stars (estimated)655 totalNov 3+2 stars (estimated)657 totalNov 4+2 stars (estimated)659 totalNov 5+0 stars659 totalNov 6+0 stars659 totalNov 7+1 stars660 totalNov 8+1 stars661 totalNov 9-1 stars660 totalNov 10+2 stars662 totalNov 11+0 stars662 totalNov 12+0 stars662 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