B

BotHarness/@botharness/core

“Designed for DeepSeek Harness memory workflows.”

OverviewREADME

TL;DR

BotHarness core: PersonaBot registry, memory, and state.

30 days of GitHub stars

+725 stars

+884.1% observed change

Oct 15+0 stars82 totalOct 16+18 stars (estimated)100 totalOct 17+19 stars (estimated)119 totalOct 18+13 stars (estimated)132 totalOct 19+13 stars (estimated)145 totalOct 20+22 stars167 totalOct 21+20 stars (estimated)187 totalOct 22+23 stars (estimated)210 totalOct 23+23 stars (estimated)233 totalOct 24+32 stars (estimated)265 totalOct 25+36 stars (estimated)301 totalOct 26+29 stars (estimated)330 totalOct 27+28 stars (estimated)358 totalOct 28+35 stars (estimated)393 totalOct 29+33 stars (estimated)426 totalOct 30+30 stars (estimated)456 totalOct 31+26 stars (estimated)482 totalNov 1+31 stars (estimated)513 totalNov 2+36 stars (estimated)549 totalNov 3+25 stars (estimated)574 totalNov 4+34 stars (estimated)608 totalNov 5+4 stars612 totalNov 6+31 stars643 totalNov 7+45 stars688 totalNov 8+25 stars713 totalNov 9+23 stars736 totalNov 10+26 stars762 totalNov 11+27 stars789 totalNov 12+18 stars807 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