JohnXu22786/rss-digest
JohnXu22786★ 0TypeScript最后同步: 2026-08-20
RSS/Atom digest plugin for DeepSeek Harness (dsh bundle): subscribe, fetch on schedule, dedupe, LLM summaries, daily Markdown briefings.
README 摘要
dsh-rss-digest English · 简体中文 RSS/Atom aggregation, smart summarization, and daily Markdown briefings — a first-party-style dsh bundle (DeepSeek Harness, "everything is a plugin"). The plugin manages feed subscriptions with local persistence, polls feeds on a schedule, deduplicates stories (exact + near-duplicate), summarizes them with the harness's LLM (with a deterministic extractive fallback when the model is unavailable), and delivers a daily Markdown digest into live conversations and/or files. It also ships a standalone CLI that shares the same core. - dsh integration : bundle spec ( dsh.bundle + cordis.patch.yml ), model-facing tools via ctx.tools , scheduling via the harness timer seam, delivery via agent follow-up messages. See Architecture. - Zero-friction core : the fetch/parse/dedupe/store/digest core has no dependencies at all — only the dsh integration layer imports dsh packages. Features - Subscriptions — add / remove / list / enable / disable RSS 2.0, Atom, and RSS 1.0 (RDF) feeds; persisted in a single versioned JSON document with atomic writes and corruption quarantine. - Scheduled fetching — configurable poll interval, startup cycle, per-request timeout, size cap…
在 GitHub 查看完整 README →分类
:rocket: The Ultimate Image Uploader for Efficient Creators. Supports Obsidian, Typora, VS Code etc. and 60+ image hosting services (S3, GitHub, Cloudflare R2, Imgur, Aliyun OSS...). Paste, upload, done.
★ 27,005
liustack/modlensThe first vision plugin for DeepSeek Harness, and the vision bridge for every text-only coding agent. Paste an image, get structured JSON evidence (OCR, layout, semantics). | 全网最强 DeepSeek Harness 外挂视觉插件,为 DeepSeek、GLM 等纯文本模型外挂视觉能力,粘贴图片即得结构化 JSON 证据(OCR、版面、语义)。
★ 3,516
Tiger3807861189/J-Space-Cognition-Suite-V3.6J-Space Cognition Suite V3.6 - AI cognitive-enhancement Skills based on Anthropic's J-space global workspace research. | 哔哩哔哩:Tiger380 (UID 3494375382321675) — https://space.bilibili.com/3494375382321675
★ 3,015