v0.3.0 · Apache-2.0
Native Rapid-MLX provider for DeepSeek Harness (dsh) — dsh reads model facts from the server instead of your settings.yaml.
v2.4.13 · SEE LICENSE IN LICENSE
AI Agent runtime authorization & evidence verification — tool-call GuardrailProvider, CCS 7-dimension verification standard, MCP/DSH security scanner, SSRF/command-injection/credential-exfil blocking with Ed25519 signed receipts.
v1.0.7 · MIT
Wallpaper Engine library as the DSH web GUI background — video/web/still wallpapers, rotation lists, search, resource monitor, bilingual UI.
v0.2.6 · MIT
In-GUI skill hub for DeepSeek Harness (dsh): browse the full local skill catalog from the official ctx.skills registry (every root + third-party providers), toggle skills on/off, inspect bodies, surface frontmatter diagnostics, and scaffold new skills — p
— · MIT
AI agent 通用任务治理框架:对齐目标与事实,规划和调度能力,守住授权与风险边界,治理任务执行到真实验收与交付。Governance framework for evidence-driven planning, orchestration, and verified delivery.
v0.5.2 · Apache-2.0
File-diff visualization between checkpoint time nodes for DeepSeek Harness: a read-only timeline + per-file line diff over the dsh-checkpoint-rewind checkpoints storage domain, with preview-first rollback (restore workspace files from any time node, singl
— · Apache-2.0
ANOLISA (Agentic Nexus Operating Layer & Interface System Architecture) | Agentic OS with runtime, security, observability, and Tokenless response compression for lower token usage and cost.
v0.2.3 · no license
Tabbit Browser plugins for Deepseek Harness
v0.1.10 · MIT
对话栏左侧常驻大纲:快速定位每次 user 提问与最后一条 assistant 回复(DeepSeek Harness 插件)。
v0.5.5 · Apache-2.0
Unified DSH checkpoints: session + workspace + config three-state snapshots with one-shot rollback — /checkpoint and /rewind commands, a checkpoint tool, automatic interval snapshots, a Settings page timeline with pairwise diffs, and seed-replay session r
v0.3.2 · MIT
Deep reading & summarization workflow for books/papers/videos/web — plugin parsers, MapReduce deep-read, JSON Schema output, Obsidian-ready (DSH)
v1.0.2 · MIT
Local and remote knowledge bases for DeepSeek Harness, with scoped recall, controlled write-back, and a Web management console
v0.8.0 · MIT
Backup, restore, download and GitHub-sync DeepSeek Harness user data (~/.dsh): /backup, scheduled auto-backup that survives restarts, sha256 checksums, integrity verify, rotation, credential redaction with a local vault (plaintext never leaves the machine
v0.5.0 · Apache-2.0
Claude Code outputStyles-equivalent runtime output-style switching for DeepSeek Harness
v0.2.7 · MIT
MindsEye: model-driven vision tools, structured evidence, and exact cache for DeepSeek Harness
— · MIT
DeepSeek-native AI coding agent for your terminal. Engineered around prefix-cache stability — leave it running.
v0.1.19 · MIT
Solo-style isolated brainstorm branches and Handoffs for DeepSeek Harness
v0.5.2 · MIT
Animated and video live wallpaper for the DeepSeek Harness Web GUI — GIF, animated WebP/APNG and static PNG/JPEG images, plus MP4/WebM video backgrounds, with auto format detection, a dim slider, and UI chrome tone matching.
v0.7.2 · MIT
DeepSeek Harness plugin and bundled Skill for safely evolving Cordis Candidates with Harbor.
v1.9.1 · MIT AND Apache-2.0
Local-first usage, cost, quota, account, and forecast analytics for DeepSeek Harness Web, with coding-subscription OAuth sign-in (Grok Build, Codex, Kimi Code, Claude Code), an optional loopback API gateway, and opt-in local auth/usage monitoring
v0.2.1 · Apache-2.0
Safe delete plugin for DeepSeek Harness (DSH): move files to trash / staging area instead of permanent removal, with restore and purge support.
v0.5.0 · MIT
Cross-session plaintext memory plugin for the DeepSeek Harness — deterministic BM25 recall, human-owned, no embeddings
v0.5.2 · MIT
DeepSeek Harness 插件商店:npm 权威源 + awesome 精选 + 自动雷达(550+ 插件、11 分类、运行级验证),官方 dsh plugin add/remove 一键安装卸载,dsh 原生 UI
— · no license
Open-source self-improving QA agent for software teams. A test harness with memory. Write tests in natural language for web and mobile. agent-qa learns from every run, adapts to UI changes, and catches regressions before you ship.