Reusable AI skills and capabilities for agent workflows
motiveflow
Attached runtimes should include the inbound `message_id` as `in_reply_to` on their outbound `send` frame/request. After the encrypted send publishes, the bridge retains a bounded, 15-minute content-free receipt and exposes it at the bearer-gated loopback
...morehyperion2144
Line-anchored read/edit/batch_edit/grep/undo_last_edit tools for DeepSeek Harness (dsh). Every line is addressed by `<line>:<anchor>` so chained edits skip a re-read; stale or ambiguous anchors are rejected and a fresh `<line>:<anchor>` is served back. Un
...moredawit-io
Reference implementation of the Semantic Surface: a serializable, medium-independent representation of what a user is looking at and what "this" refers to.
...moreGitHub Actions
n8n community node for the Crystal Data API — enrich profiles and get DISC personality insights
snow_eagle
Deterministic, recoverable tool-result compression and cache-aware compaction for DeepSeek Harness
Denis Ineshin <[email protected]>
Tiny AutoEncoders for diffusion on Apple Silicon — live previews + low-memory decode for FLUX, SD, and Qwen-Image.
desch
n8n nodes for everycore Core for Sage 100: sales documents, transactions and articles
halilcinar51
Multi-provider AI office: bring your own Claude/OpenAI/Gemini/Alibaba keys, load-balance across them, resume Claude Code sessions, run batch audits, and join a shared office where tasks run on members' own machines.
...more0xyas
Your terminal, now autonomous. Just say what you want, ineed does the rest.
mljs-bot
UMAP dimensionality reduction
GitHub Actions
Sam AI router provider for the Vercel AI SDK
unrelentingfox
A small systemd-user scheduler for Pi prompts, with room for a generic agent harness in a future release
Stephen Blatt
Local, speaker-attributed transcription for Apple Silicon — who said what, on your Mac, nothing leaves the machine.
ldikay99
Pure-Python, cross-platform scraping toolkit: clean declarative extract, one-call endpoint discovery, browser-fingerprint HTTP, and real network sniffing via CDP. Stdlib only, zero dependencies.
...morethe mlx-beam contributors
Light and modular inference engine, built on MLX.
42min
n8n community node for 42min — scheduling, bookings and booking event triggers
agentlabbusiness
n8n community node for Raposa Aval: pause a workflow until an authorised human approves, with a hash-chained audit record of the decision.
...moreshuzhao1133
GB/T 9704-2012 formatter for Chinese government Word documents. 自动统一 .docx 页边距、字体字号、标题层级、行距、页码、标点与序号；支持 Claude/Codex Skill 和 Python CLI。
...moreraydian
Agent skill for rapidly building pactor Server-Driven UI applications
fastroware
Practical guardrails for AI coding agents. Hold on, think first, code less.
GitHub Actions
DeepSeek Harness plugin: dispatch work to DSH agents from Claude Code / Codex, as native subagents with live progress
webboxescom
Extract any coding-agent session (Claude Code, Codex, Pi) into a compact, verified, provenance-linked handoff that any other agent can continue from.
...moreelizabthpazp
Drop-in "Ask AI about [your product]" badge with monochrome ChatGPT, Claude, Gemini, Google, Perplexity & Grok links. Fully customizable, zero-dependency (React peer only).
...moreGitHub Actions
Subscription-aware model routing for Pi, OpenCode and every OpenAI-compatible coding agent