dsh-memory-gate
Retrieved ≠ injected: CBDC-gated memory for DeepSeek Harness — decides how memory is USED (use/verify/ignore decisions, feedback learning, full audit); local SQLite + FTS5, bounded, no extra model call
107 results
Retrieved ≠ injected: CBDC-gated memory for DeepSeek Harness — decides how memory is USED (use/verify/ignore decisions, feedback learning, full audit); local SQLite + FTS5, bounded, no extra model call
Explicitly governed shared memory spaces for DeepSeek Harness sessions
Work Continuity for DSH — goal/decisions/checkpoints/next-steps as explicit WorkState, decoupled from generic memory
DSH 长期记忆插件:记忆库 + 会话蒸馏自动沉淀 + 设置面板,越用越懂你。守藏(Shoucang)单插件,panel + scheduler + 内嵌记忆技能。
dsh-memory — cited memory over DSH's lossless session log: post-session distillation into human-auditable markdown files, a compact recall index, memory_read/memory_expand tools, and a dsh-memory CLI
Evidence-backed working memory for DeepSeek Harness: a cited ledger of what already worked in this workspace, built from the session log you already have
DSH-Plugin: durable agent memory core — mem_save / mem_search / mem_health tools backed by the DSH storageDomain (durable, survives restarts), plus a 記憶 view tab.
Four-layer long-term memory for DeepSeek Harness (L0 conversation → L1 atoms → L2 scenes → L3 persona) with auto-recall and auto-capture — adapted from TencentCloud/TencentDB-Agent-Memory
dsh-experience-flywheel · DSH 经验飞轮插件 — agent cross-session experience memory + dual-acceptance gates (auto query/inject via agent/pre-step middleware; exit-1 gate scripts)
Hermes-style bounded curated memory for DeepSeek Harness (out-of-tree plugin)
Install iHow Memory as a local-first shared memory plugin for DeepSeek Harness.
Evidence-first long-term project memory for DeepSeek Harness
vibeweaver 技能的 DeepSeek Harness 插件封装:渐进披露契约段 + 机械门禁(assert_artifacts 证据检查)+ 编码任务自动激活 + 回合守卫。
Task-isolated, privacy-first memory for DeepSeek Harness
Cloud-backed cross-session memory for DeepSeek Harness: structured entries + vector retrieval persisted to S3-compatible object storage (AWS S3 / MinIO / R2 / OSS), with local cache projection, approval-gated writes and auditable trails
Forgetting engine for AI agents — memory TTL, decay, eviction, audit. The opposite of memory programming.
Gated GA-style layered memory for DeepSeek Harness: hard-injected L1, working checkpoint, settlement to Skills/L1/L2 — no silent auto-retain.
Automatic TMCRA recall, injection, and role-separated writeback for DeepSeek Harness
DeepSeek Harness bundle that registers the session-summarize skill pack on ctx.skills.
MCP client hub (stdio / Streamable HTTP / SSE) with skill, command, memory and prompt management for the DeepSeek Harness Web GUI
Local-first automatic Wiki and Skill distillation for DeepSeek Harness
WikiBridge:DSH 与 Obsidian vault 的知识库桥接 —— 约束工具(wiki_search/read/write)+ 自动词典检索 + 持久化配置
Edit DeepSeek Harness global AGENTS.md instructions and memory directly in Web settings.
Local Markdown wiki as long-term memory for DeepSeek Harness — ported from llmwiki