@liustack/modlens
Plug-in vision for text-only LLMs, powered by the free Antigravity CLI
201 results
Plug-in vision for text-only LLMs, powered by the free Antigravity CLI
HarmonyOS NEXT skill bundle for DeepSeek Harness
SeekTTY, a pluggable DeepSeek-colored terminal surface for DeepSeek Harness
dsh-passwords: a server-grade gateway that turns DeepSeek Harness into a multi-tenant platform — remote access + automatic HTTPS, per-subuser permissions & quotas, sandbox enforcement, first-run setup, SQLite auth with at-rest encryption, rate-limit and audit log (bilingual zh/en UI)
公文全流程处理工具 - GB/T 9704 格式检查/修复/内容优化/模板生成/版式注入
Agent toolkit that helps coding agents use Huawei Cloud Skills, KooCLI, APIs, SDKs, and future MCP capabilities safely and accurately.
Claude Science-style research workbench for DeepSeek Harness: ReAct research-loop engine (research_* tools), versioned artifacts with provenance (artifact_* tools), SSH remote-compute engine for long bioinformatics jobs on workstations/HPC (remote_* tools), and 11 science skills for genomics / pathogens / bioinformatics. Ships the tiered cross-provider model router via the companion dsh-model-tier bundle.
DSH plugin health checker: scan plugin repos for manifest protocol / patch format / build pitfalls / hub registration, zero-dependency read-only diagnostics
DeepSeek Harness dual-face plugin: Codex-style file references (@path), fully bundled document→Markdown (MarkItDown engine, 20+ formats), mature image handling (read_image for multimodal routes, automatic vision descriptions for text-only models), read_document tool.
Deep Research orchestrator extension for DeepSeek Harness: an adaptive cybernetics/information-theory deep_research tool on the official workflow engine, reusing built-in web_search/web_fetch.
FormatForge for DeepSeek Harness: forge any file format (pdf/docx/xlsx/pptx/eml/toml/...) into AI-readable structured data. v1.0.0 (PRODUCTION-READY, protocol frozen): 协议冻结(v1.x 向后兼容)+ v0.14.0 全部 7 项 P0+P1 + 5 项 audit 修复(4 bug + 1 性能)。测试基线 567 passed。Thin
DSH plugin health checker: scan plugin repos for manifest protocol / patch format / build pitfalls / hub registration, zero-dependency read-only diagnostics
Free web search for DeepSeek Harness: 10 engines (Bing/DuckDuckGo/AnySearch/SearXNG/Exa/Tavily/Keenable keyless) + time filtering + platform search + web_fetch, with web settings UI.
AI-native web scraping and JavaScript reverse-engineering platform powered by DSH, Patchright/CDP, semantic recovery, and verifiable Solvers
LSP action surface for DeepSeek Harness: diagnostics, formatting, completion, code actions, symbols, signature help, inlay hints, and rename tools over language servers, plus the editor action protocol (lsp.actions.*) that makes the plugin the IDE integration backend
DeepSeek Harness plugin bundle: optimize raw instructions into professional Role / Task / Context / Format prompts through the harness llm service
Floating macOS-glass DeepSeek usage panel for the DSH web UI: live official balance + token usage (today, session, 24 h smooth trend, per model) without opening platform.deepseek.com/usage. · DSH 毛玻璃用量面板:官方余额 + Token 用量
Normalize redundant sandbox requests and malformed justifications in DeepSeek Harness tools
Kuikly DeepSeek Harness plugin that turns your AI agent into a Kuikly cross-platform app development expert
Structural code intelligence for DeepSeek Harness (dsh) — gives the agent codegraph and codegraph_index tools to find where a symbol is declared, what calls it, and what a change reaches, from a tree-sitter index it builds itself. Compatible with the codegraph CLI's on-disk format.
Hover LaTeX formulas in the DeepSeek Harness Web UI to copy the TeX source or export the formula as a standalone SVG.
A reproducible science workbench plugin for the DeepSeek Harness: agent-driven cells, inline figures with feedback/rerun, manifest provenance, and environment snapshots.
DeepSeek Harness-native publicity toolkit: turn any long-form source into a source-grounded, platform-native promotion matrix.
低成本视频理解工具:B站链接/BV/本地视频 → 信息层(ASR+场景+对象轨迹+YOLO)→ 摘要+问答。问题驱动动态路由分层(L0/L1/L2)、语义层复用、预算上限。采用 Python 引擎:核心层需 faster-whisper / opencv / yt-dlp(约 200-300MB),可选语义层另需约 2GB 的 torch / transformers / ultralytics,内置 doctor --fix 一键建 venv 并装齐两者。