by EternalNight996

Self-built DSH memory plugin: SQLite persistent storage + database-level audit guard (enforceAudit) + audit log. Auto-captures knowledge after conversations, agents recall via memory_recall, supports

by Soren-ABT

Knowledge base & RAG plugin for DeepSeek Harness (DSH): chunking, local embeddings, hybrid search, management panel

by Kytolly

A deepseek-harness plugin, making your agent evolve in customed git repository.

by Contexera

dsh-agent-team gives DeepSeek Harness agents that don't reset: durable Members with their own memory, notes, and skills across sessions, rollovers, and restarts. You set the direction; agents coordina

by hanshanyike

Turn the important things mentioned in conversations into ongoing, follow-up plans. A personal assistant built for deepseek-harness: organize tasks from conversations, track changes, and remind you when needed.

Session KB for DeepSeek Harness: full-text search across all past sessions and recall them as

by modusensus

🧠 The memory that dreams — cross-session memory for DeepSeek Harness. Offline & private, auto-consolidates in its sleep (autoDream), visualized in a memory panel.

by kenz1117

Cross-session long-term memory under the "memory palace" metaphor: dual-scope SQLite stores (user + per-git-origin project), hybrid FTS5 + local-vector retrieval with RRF fusion and recency/proof rank

by 398894496-arch

Second brain for coding agents. Seal the day, distill into Obsidian, hit that page tomorrow. Cursor, Codex, Claude Code, DeepSeek Harness.

by Qinling-Melon-Farmers

DeepSeek Harness (DSH) local-first cross-session project memory: zero bundled runtime deps, bounded cache-friendly Hot Memory, BM25 recall/cache, provenance, lifecycle and bilingual Web GUI; no embedd

by pk14742952-AD

DSH host RSI for local LLMs (currently Qwen3.8 27B): per-use continual self-improvement, counter-reason self-check, critic escalation, and memory retrieval.

by mingzeng21

Connect DeepSeek Harness (dsh) to a local Obsidian vault: search, read, write, move, and trash notes.

by hr98w

Combining Claude Code's Auto Memory with Codex's Session memory consolidation, providing DeepSeek Harness with simple, transparent, and context-friendly long-term memory. Claude Code-inspired Auto Memory meets Codex-inspired Session consolidation, bringing simple, transparent, and

by Roarpeng

Local-first code knowledge graph and context harness for coding agents. MCP + DeepSeek Harness (dsh) plugin.

by 00080000

Read-time project memory plugin for DeepSeek Harness (dsh)

by quqxui

DeepSeek Harness Long-Term Memory Plugin: Four-Channel Retrieval Fusion + Memory Evolution Closed Loop, with Memory Construction and Retrieval Methods from the ICLR 2026 Paper MemGAS. Long-term memory plugin for DeepSeek Harness (dsh).

by gezi-wen

File-based cross-session memory: plain Markdown memory files with automatic retrieval injection, format-compatible with Claude Code's CLAUDE.md and memory files, so migrating is a manual file copy.

by PerryLink

Local document knowledge base for DeepSeek Harness: library_add/remove/list, hybrid semantic+keyword library_search with diversity re-ranking, relevance filtering and lost-in-the-middle avoidance, cit

by JunNanLYS

Long-term memory for DeepSeek Harness: AI automatically remembers who you are, your projects and preferences. New sessions start with relevant context, and life and work memories are automatically separated and do not interfere with each other. Runs with zero configuration and no awareness.

by Scorp1o117

Soul.md persona for DeepSeek Harness | DeepSeek Harness Character Card Plugin

by lemoncat7

Installable DeepSeek Harness knowledge base plugin

by tancheng33

A typed, inference-capable ontology (TBox + ABox) plugin for DeepSeek Harness — durable domain knowledge the agent declares, asserts against, and queries under schema constraints.

by Rxiain

OpenViking Retrieval, Resource Management, Auto-Recall, and Session Memory Plugin for DeepSeek Harness

by webkubor

Let the AI know you. Have the model proactively record your judgment criteria (principles/red lines/work style) for reuse across sessions — it has limited capacity, it forgets, and each entry should be able to explain why it was recorded.