by moondrop12138

Workspace memory for DeepSeek Harness ported from ZCode: one Markdown memory directory per workspace (a MEMORY.md index plus one file per fact), injected into each main session and refreshed by a back

by Jesse-njx

Cited memory over DSH's lossless session log: distilled facts carry `(sessionId, eventRange)` citations that expand back to the exact original log excerpt.

by kkwings

No project description is available for this repository yet.

by yihefeikong-rgb

Persistent memory for DeepSeek Harness: memory read/write/retrieve tools, per-turn auto-recording, project-scoped recall injection and a management UI, with non-destructive Claude Code memory import.

by 863683348

Local, auditable personal memory for DeepSeek Harness: preferences, project conventions, workflows and error lessons persisted as a changelogged JSON file in the workspace, with onboarding, auto proje

by hzh5021

Warns the session to flush what matters before context compaction kicks in, and rolls a long-term ledger into a frozen archive with a one-line digest per moved section.

User-authored tiered long-term memory for DeepSeek Harness: injected as a system-prompt section, with a Chinese panel to view and edit it. The AI never writes to memory on its own.

by eehcx

DSH adapter for Engram — persistent memory bridge built with Cordis.

by fangqiing

Local Knowledge Base Plugin for DeepSeek Harness: One Markdown per Article, Supporting Full-Text Search, Tags, Hierarchical Directory, Attachments, and Zero-Dependency Office Extraction

by rasyidmmz

Memory bridge between DeepSeek Harness and ai-memory: finalizes DSH sessions so they become wiki pages every other harness ai-memory serves can read.

Memory consolidation tuning for dsh-mneme (autoDream enabled, schema-max output budget, deepseek-chat route) plus the llm-deepseek reasoning-effort fix, an MCP bridge to the auditable seed-society age

by yangyongzhen

Long-term memory injected at session start: preferences/facts/summaries/knowledge in global and per-project scopes, budgeted recall via `agent/pre-step`, durable JSON store.

by yiyunet

A learning plugin that runs in the DeepSeek Harness input area: turning "collect → distill → associate → upgrade → precipitate → reuse" into runtime capabilities featuring interactive guidance, preset management, review-and-ingest, and system health checks. DeepSeek Harness plugin: a four-entry learning workspace.

by 1HelloMan1

Routes chat images to a fixed OpenAI-compatible vision model, returns factual observations to the selected main model, and reuses session-scoped observations across replay, compaction, and restarts.

by Marquez807

Cross-session experience memory for DSH: a lesson reaches the model only with a verifiable source, the relevant ones are injected each turn, and what nobody uses is retired.

by zeropointnine

Compact a session and continue the work in a new one

by ShadowQuill

Conversation Context Bridge — A DSH plugin that performs cross-session context bridging for LLM/AI agent conversations: packages the consensus of one conversation into a portable snapshot, imported into a new conversation with one click (three-layer snapshot / SQLite+FTS5 / AES-256-GCM)

No description yet

Zero-dependency cross-session memory for AI coding agents - lessons on disk, evidence-enforced, auto-injected

Hindsight long-term memory for DeepSeek Harness: injects relevant memories before each turn and retains finished turns to a Hindsight bank.

No description yet

Workspace-isolated durable memory for DSH, with searchable, auditable, correctable, and removable workspace memories plus controlled global memory.

by leetom314

Tiered persistent memory (user/env/project) with per-tier char budgets and semantic query routing; full layers refuse writes instead of silently evicting.

by wu81313-lab

DSH local-folder knowledge base: manual-sync SQLite FTS5 index, Chinese hybrid retrieval (BM25 + CJK bigram + trigram, RRF), explicit-invocation gate, and a Web panel.