Feeds every dsh prompt into the local agent-feedback-loop feedback-memory pipeline — captures dissatisfaction, reviews it offline into reflections, and attaches the compiled recurrence-rule context ba

Notes-backed context compression for DeepSeek Harness: replaces LLM-summarized compaction with a model-written persistent notebook plus recoverable raw history, so the rollover boundary itself costs z

Coordinates bounded project recall from compatible memory and learning providers, with shared settings and provider lifecycle management.

A private inner life for your agent - diary written to a path that rotates daily, index never stores the path

On-demand memory for DeepSeek Harness: session logs are distilled into layered markdown (a summary, an index and per-topic files), and a mem_query tool returns only the matched entries rather than the

Karpathy LLM Wiki pattern knowledge base for DSH: wiki-write/wiki-search skills, zero-dependency pipeline (lint/index/mnemon memory sync/quality feedback), minimal lifecycle plugin injecting schema +

Keeps DSH agents from forgetting your requirements during long tasks. It saves important conditions and completion evidence locally, brings them back after context compaction or session resume, and st

Layered long-term memory for DeepSeek Harness: each turn injects a persona frame plus a relevance-ranked memory index while full transcripts stay on disk and are expanded on demand, so the vault never

Audit each finished assistant turn with an independent reviewer model and steer the agent to fix failed output, with at most 2 review rounds per turn and SOP-folder standards injected as an extra revi

No description yet

Post-compaction premise-drift guard: injects a one-shot notice when a compaction summary drops a critical literal anchor.

Vector + graph memory backend: observe/remember/search/recall tools against a local memoria server, fusing HNSW semantic recall, FTS5 keyword search, and knowledge-graph signals via RRF ranking, with

A /remember command that writes facts into the AGENTS.md instruction hierarchy dsh already loads, plus a Memory tab showing which instructions the loader kept within its byte budget.

The memory that dreams — cross-session memory for DeepSeek Harness: recalls you across sessions, auto-consolidates in its sleep (autoDream), freezes conflicting memories for your review, and keeps a r

DSH Workspace Long-term Memory: index-based briefings save tokens, end-of-round relevant recall, memory tools read/write on demand, version chain and health check, automatic refinement at round end (with draft approval), and visual viewing and management in the settings panel.

by WYR-233

Read-only enhancer for a file-based long-term memory library (markdown cards in git): a memory_find search tool, a small budgeted memory digest injected into the system prompt, and a settings page wit

by AllenWES365

Project-isolated long-term memory for DeepSeek Harness: each project keeps its own bank, and one aggregate view sees them all.

Bridges the agent to a persistent OKF memory vault over MCP stdio: a Python server (SQLite FTS5 + Markdown) with 10 tools for searching and storing decisions, facts, learnings, conventions, profiles a

BM25 keyword-based memory recall.

General-purpose knowledge base for DSH: import md/txt/json/yml/docx/pdf, folder management, FTS5 full-text search (BM25), and a Web management UI.

Bounded self-managed long-term memory (Hermes-style MEMORY.md / USER.md with hard character limits and a safety scan), a review that runs after every turn and writes plain-language notes or refines an

Cross-session long-term memory: captures durable facts from each turn, auto-associates them by shared entity and tag, and recalls with BM25 plus spreading activation over the link graph.

Notes taken from DeepSeek Harness conversations: quotes whole replies or selected passages, keeps highlights rendered at their original position in the session, attaches editable Markdown notes, tags

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)