@fleetingecho/dsh-handoff
Self-maintaining handoff.md per working directory + git branch for DeepSeek Harness, stored under ~/.agent/agent-handoff (shared with pi-handoff).
385 results
Self-maintaining handoff.md per working directory + git branch for DeepSeek Harness, stored under ~/.agent/agent-handoff (shared with pi-handoff).
Lifecycle orchestration engine for AI agent teams on DeepSeek Harness with task-scoped Git worktrees, state-gated delivery transitions, and off-context memory.
A reusable DeepSeek Harness bundle for evidence-driven memory, orchestration, benchmark operations, repository audits, and plugin release workflows.
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
DSH Web 右下角系统状态悬浮窗:CPU(x%/y)、内存、磁盘占用,1 秒刷新
Native knowledge context for DeepSeek Harness
Agent-driven long-term memory for DeepSeek Harness: scoped memory (global + per-workspace), layered entries (fact/knowledge/episodic), time-bucket compaction (day→week→month→year), associative recall (related chains) + memory_relate navigation (multi-hop BFS closure), auto recall injection on user messages (CJK bigram search, tail append), agent-decided content.
Thread session memory for dsh — lossless event capture + status-card injection (dsh plugin, standalone repo).
Memory protocol enforcement plugin for DeepSeek Harness — forces memory_weave before tool calls, auto-ingests session turns, injects memory context into agent steps. Bridges the opencode-memory MCP server with a hard protocol gate.
Native, per-workspace long-term memory for DeepSeek Harness: facts and profiles on DSH's own storage-domain, cross-session recall through session-query FTS, approval-gated writes, and cited provenance — no external server, no extra runtime dependency.
DSH插件,以Observational Memory方式管理上下文
Codex-like persistent memory for DeepSeek Harness: auto-injected memory summary, raw memory tools, and per-session rollout summaries distilled into a bounded global memory file.
记忆搬家:把 Claude / ChatGPT / Claude Code 的历史记忆搬进 DeepSeek Harness —— 带逐字证据,逐条批准 | Move your Claude & ChatGPT memory into DeepSeek Harness (DSH), with verbatim evidence and one-by-one approval
人脑式上下文压缩逻辑 — DeepSeek Harness 上下文压缩统一协同层: 集成 dsh-argp / dsh-compaction-instant / dsh-headroom / dsh-sgme / dsh-memory-vault / dsh-mcp-lens / dsh-context-doctor,提供统一配置、工具协调与验证机制。适配 DSH 0.1.5。
Project-level persistent memory plugin for deepseek-harness — auditable Markdown memory files with load / upsert / finalize / forget tools.
Maestro harness sync — merge memories and sessions across machines (publishable)
Work Continuity for DSH — goal/decisions/checkpoints/next-steps as explicit WorkState, decoupled from generic memory
Claude Code CLI as an LLM provider for dsh (DeepSeek Harness): live model list, per-session resume, approval relay, images, a memory/rewind/changes panel, and workspaces on remote SSH boxes
微光 (Lume) — DSH Desktop 增强插件:Codex 风格自适应任务执行协议 + 人设系统(聊天记录蒸馏具名角色、长期记忆、风格纠偏自动捕获)
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。
Explicitly governed shared memory spaces for DeepSeek Harness sessions
Codex-style per-session memory for DeepSeek Harness: qualified sessions auto-distill into per-session drafts (rollout_summaries); manual add/change/forget runs only on explicit user request; layered disclosure (summary + registry); idempotent integration watermark. / 一会话一草稿记忆插件:合格会话自动提炼草稿;手动增/改/忘仅在显式请求时执行;分层披露(总纲+注册表);幂等整合水印。
DSH skill_manage: agent-managed procedural memory. Create/patch/edit/disable/delete skills in ~/.dsh/skills (user scope) or <projectRoot>/.dsh/skills (project scope), with validation, delete guards (agent-created marker, pin, path confinement), disable/enable via disable-model-invocation, and an English trigger-discipline system prompt section. Built on top of skill-filesystem's hot-reload watcher.
Unified DeepSeek Harness plugin: role-based subagent routing + per-agent evolution — prefercmd/memory as knowledge allow/deny lists, so repeated tasks start from proven commands and save tokens