Search
@leaflow/sdk
GitHub Actions
Leaflow 平台 API 的 TypeScript SDK
relayrun
avaya03
Run a Relay session against a repository on your own machine — everyone with the link watches the agent work, one person drives.
...more@vornrun/connector-slack
jcanizalez7
Trigger workflows from Slack messages, thread replies and channel members, and post, reply or react from a step.
@riligar/hoster-cli
ciro-maciel
CLI to deploy static sites to Hoster
puppeteer-nest
GitHub Actions
Puppeteer integration for NestJS 12 with a Cloudflare Browser Rendering-style API
proxya-anty
proxya
Drive the Proxya Anty anti-detect browser from Node. Fingerprints are applied inside a patched Chromium, and the DevTools Runtime agent is not left switched on — so a script-driven session is not read as automated.
...moreplaywright-clipboard-testing
GitHub Actions
Playwright fixture and custom matchers for clipboard testing and assertions.
universcan
jomardyan
UniVerscan - Universal Playwright Web Compliance Scanner
partialjson
Parse incomplete or partial JSON, e.g. from a streaming LLM response
saber-risk
Xiaodong Liu, Mingqian Feng
SABER: Scaling-Aware Best-of-N Estimation of Risk for LLM safety evaluation
Youtube Scout
AgriciDaniel
Claude Code skill: one topic in, one ranked YouTube research workbook out. Searches YouTube Data API v3, ranks by views, engagement, momentum or breakout, and writes Videos, Channels, Summary, Comments and Transcripts sheets with hooks and replay hotspots. Appends into an existing social ads sheet.
...moreMy Academic Skills
SPYfighting
Research skills for Claude Code, Codex, and OpenCode.
@coderabbitai/openai-chat-tokens
hasit-coderabbit
Estimate the number of tokens an OpenAI chat completion request will use
tombstone-erase
Poojan Patel
Track where a data subject's data actually went (chunks, embeddings, caches, fine-tuned weights), erase it everywhere, and hand back a receipt that says what was checked and what was not.
...moremodelscout-llm
Jagan Jijo
Find local AI models that fit your hardware, with memory and speed estimates.
vui-tts
Vui Nano — a small, context-aware text-to-speech model trained on real conversations. 219M active params (305M total), Apache 2.0, voice cloning, streaming, runs on CPU. Ships with a full real-time voice assistant (WebRTC, ASR, local LLM, OpenAI Realtime API compatible).
...moreboruna
escapeboy
Boruna: a deterministic, capability-safe programming language and framework for LLM-native applications