dsh-db-connector
Database connector bundle for DeepSeek Harness (dsh): SQLite/PostgreSQL/MySQL connections, schema introspection, read-only safety, write approval gate, and a JSONL SQL audit trail.
62 results
Database connector bundle for DeepSeek Harness (dsh): SQLite/PostgreSQL/MySQL connections, schema introspection, read-only safety, write approval gate, and a JSONL SQL audit trail.
Recover deleted/corrupted dsh sessions (session.jsonl.zstd) and memory (memory.db) straight from the raw disk. Battle-tested recovery manual + scripts + a /session-repair command plugin for the dsh web UI.
Capture AI web conversations to local JSON + SQLite, and port selected messages into agent harnesses as live, continuable sessions.
Native knowledge context for DeepSeek Harness
Local, storage-bounded cross-session search for DeepSeek Harness conversations with SQLite FTS5, Chinese segmentation, and message-level jump targeting
DSH ticket management plugin: Epic/Story/Ticket hierarchy backed by SQLite + Markdown
Cross-session persistent cost ledger for DeepSeek Harness: logs every LLM token usage to SQLite and exposes record/query/budget tools. Built-in DeepSeek pricing, overridable via config.
在 DeepSeek Harness 中浏览、搜索并引用 Zotero 文献库:better-sidebar 右侧栏文件树、双击/& 与 /zotero 快速引用、host 直读 zotero.sqlite
Explicitly governed shared memory spaces for DeepSeek Harness sessions
Cross-session long-term memory for DeepSeek Harness: dual-scope SQLite memory graph, hybrid retrieval, provenance audit, and a knowledge flywheel.
DSH ticket management plugin: Epic/Story/Ticket hierarchy backed by SQLite + Markdown
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
Memory Standard Protocol (mm) for the DeepSeek Harness: layered MEMORY.md + deterministic budgets + frozen snapshots + cross-agent markdown/URI interop + session-log digestion. Ships as a dsh bundle (tools: mem_read, mem_write, mem_search, mem_budget, mem_digest) and a standalone CLI.
Out-of-tree DSH bundle for scientific literature search: a Crossref + local SQLite FTS search engine, agent-facing literature tools, and literature-database management under $DSH_HOME/data/literature
DSH 数据库 MCP 桥接插件:零知识凭据管理(密码永不进模型)+ 按 source 的一次性进程执行(无常驻服务、天然并发与多实例安全)+ 自动安装 dbhub 与浏览器状态卡片。
会话全文索引插件:监听 session/event 构建跨会话索引,提供 session_search / session_index_stats 工具,优先使用框架自带 ctx.sessionQuery (SQLite FTS5)
dsh 梦境记忆整合插件:凌晨随机触发,把当天会话/Hindsight 记忆生成叙事化梦境日记(法塔人格),高价值洞察晋升回 MEMORY.md,梦境与晋升记录存 SQLite 并在 web 梦境 Tab 展示。
Per-project long-term memory for DeepSeek Harness, backed by SQLite.
Local-first automatic Wiki and Skill distillation for DeepSeek Harness
为 AI Agent 提供短期记忆缓存、长期知识沉淀、语义检索与持久化存储的统一记忆管理层
Clean Architecture 参考库(agent 审查基线): 8 仓钉版 FTS5 搜索 + 断言清单 + 自动审查台账 + 只读观察窗
Long-term cross-session memory plugin for DeepSeek Harness (L5 + L7 layers): SQLite-backed, FTS5 + optional embedding recall, append-only audit log, single-bundle dual-face packaging.
DeepSeek Harness plugin: local-first web stack — multi-engine keyless search (DuckDuckGo/Bing + optional Exa/DeepSeek/Jina), a SQLite-cached fetch provider, the web_platform_search tool, and history/stats/cache tools. No paid search API or third-party data broker required for the keyless engines.
Memory Fortress for DeepSeek Harness: 5-track layered memory, self-evolution, knowledge graph (SQLite+FTS5), status pill. 本地记忆堡垒:五轨记忆·自我进化·知识图谱·状态灯。