Search

JavaScript/TypeScript client for the sepp durable job queue

YAML-configured task and flow orchestration engine

Zero-dependency HTTP monitoring, APM metrics, percentile latencies (p50/p90/p95/p99), threshold alert callbacks, Prometheus format exporter, slow request profiler, and real-time embedded web dashboard for Express.js.

The Kuai command-line interface

Application-owned, typed internationalization scopes for Askr.

Gram recipe i18n and unit normalization logic

Every agent session, one board. A local-first task board + searchable librarian for your Claude Code and Codex sessions — live status, full-text search over every transcript, click-to-jump, and one-click resume.

TypeScript types and React hooks for HubSpot Commerce Hub quote templates.

Local bridge for the Vidfarm Trackpad Editor. `vidfarm serve <template_id>` boots the FULL editor on localhost (disk-backed records/storage, free in-process render); edit composition.html on disk (Claude Code, Codex, etc.) and the browser live-morphs it.

Astral Core Management Dashboard + Telegram Bot for @astralcore/sl-aura sessions

CLI and SDK for ShipStatic — deploy static websites, landing pages, and prototypes instantly. The unscoped name for @shipstatic/ship.

TypeScript types + client for the ai-agent-subsystem CRDs (Agent / Station / AgentDefinition). Types are generated from the D source so they cannot drift.

Helpers e fixtures de Playwright compartilhados entre os microfrontends Agrotools (login via athost + navegação de módulo)

coderouter - route Codex/Claude Code traffic across multiple ChatGPT Pro/Claude Max/OpenCode subscriptions and API keys.

Official Python SDK for TokenRouter — the OpenAI-compatible AI gateway

Behavioral regression gate for non-deterministic LLM systems.

Self-contained Liuyao / Six Lines divination Agent Skill with deterministic Wenwang Najia charting, HTML/Markdown output, and fact auditing.

Claude Code & Codex skill: say "share this as a link" and any AI output — chat, artifact, or markdown — becomes a live public URL in ~10 seconds, with document tracking (aggregate view counts). A lightweight DocSend alternative for the simple case. Publishes via the ReportRoom MCP.

Observe and optimize supported inference clients with SmallerModels.

Jupyterlab extension to replace individual jupyterlab_*_code_extension and integrate into one, that offers joint capability, joint settings page and individual right toolbar panels per code assistant, with the ability in settings to decide which code assistant support is on (default - all are enabled)