v0.3.0 · MIT
Three-tier memory control plane for DeepSeek Harness: persistent runtime context, searchable project documents, pluggable long-term memory, smart routing, supervised agent workflows, WebUI, and headless tools.
v0.3.7 · Apache-2.0
Local-first AI agent runtime with sandboxed sessions, MCP tools, memory, credentials, audit/replay, and a built-in console. Run OpenAI, Anthropic, MiniMax, DeepSeek V4, and OpenAI-compatible models on your infrastructure.
v0.8.1 · MIT
Auditable vision and cross-platform Computer Use runtime for DeepSeek Harness with source-preserving evidence.
v0.2.9 · MIT
AGI 的长期记忆基础设施。让 AI Agent 拥有不可遗忘的自我。跨会话记忆 · 持续学习 · 可审计信任(智能论 v3.2)
v0.9.2 · MIT
DSH 官方公众号收录的 TUI 补位插件:Claude Code 风,鲸鱼顶栏/实时状态/流式思考/双击 Esc 回滚/上下文进度+TPS。npm 一键装。 DSH official WeChat featured TUI plugin — Claude Code style: whale bar, live status, streaming thoughts, double-Esc rollback, context bar + TPS. npm one-click.
v0.2.11 · MIT
DeepSeek Harness plugin for previewable cross-preset session migration. Fixed-schema handoffs preserve state, source-model intent, and unresolved images; the original session stays untouched.
v1.6.0-beta.8 · MIT
Deepseek Harness、Openclaw知识图谱记忆插件。2026年4月受邀发布在清华大学讨论会。Knowledge Graph + Memory;Knowledge Graph Context Engine for OpenClaw — extracts structured triples from conversations, compresses context 75%, enables cross-session experience reuse
v0.2.3 · MIT
A portable memory protocol for AI agents — load it as standing rules; a curation discipline + reference spec + optional cap hook.
v0.6.0 · Apache-2.0
Second-model AI auto-review for DeepSeek Harness approval requests: a read-only reviewer subagent returns structured allow/deny verdicts with reasons, fail-closed by default, fully auditable from the session log (approval/asked -> autoReview/verdict -> approval/decided).
v0.1.0-rc.3 · MIT
Noema long-term memory plugin for DSH: durable, inspectable agent memory with recall tools and a settings page.
v0.4.5 · Apache-2.0
Bounded, layered, approval-gated, auditable cross-session memory for DeepSeek Harness (capability seam: ctx.memory + SQLite provider + memory tool + frozen snapshot injection)
v0.1.0 · MIT
Visual conversation map for DeepSeek Harness — sessions as cards on a whiteboard: drag to arrange, double-click to chat, draw an edge to fork with injected context. ADHD-friendly spatial memory. · DSH 可视化对话地图
v0.8.2 · MIT
Session strata for the DeepSeek Harness Web GUI: the transcript's scrollbar becomes a to-scale, colour-coded map of the whole run — user messages emphasised, clickable anchors, auto-loading history, and a hover deck of every prompt in the session.
v0.1.14 · Apache-2.0
NPM-installable DSH Web plugin for managing archived sessions.
v0.5.2 · MIT
High-reliability Feishu/Lark bridge for DeepSeek Harness — QR one-click auth, multi-mode agents, card-based commands, zero-loss outbox, media in/out, session-log doctor, reusable DSH Web GUI
v0.3.0 · MIT
DeepSeek Harness 桌面版(Windows)· Electron desktop shell for DeepSeek Harness — 双击即用 / double-click to run · 支持选区截图提问、系统托盘、会话管理 / region screenshot, system tray, session manager
— · Apache-2.0
One portable memory layer for every AI agent: local-first, Markdown-native, user-owned, and self-evolving across apps, tools, and workflows.
v0.5.2 · MIT
High-reliability Feishu/Lark bridge for DeepSeek Harness — QR one-click auth, multi-mode agents, card-based commands, zero-loss outbox, media in/out, session logs, reusable DSH Web GUI
v0.2.17 · Apache-2.0
Usage statistics for DeepSeek Harness: aggregated token and cost metering per session, per day, per week, per month and over custom date ranges, with per-model breakdown, peak-hour pricing, durable daily history, a Settings usage panel and the /usage comm