Search

Self-hosted mail dispatch service with queues, priorities, sender and recipient rate limits, and maglink authentication.

Automated model-building pipeline for X-ray crystallography and cryo-EM

A machine learning models framework from experimentation to production: data, training, evaluation, export, and deploy pipelines for small task-specific language models

n8n community node for the TeamRetro public API

n8n community node for SMB2/SMB3 shares with NTLMv2 support. Proper n8n credentials, list/upload/download/delete/move/mkdir operations, retry logic and clear errors.

n8n community nodes for Nimply.io — schedule, publish, and measure social media content

MLX-VLM is a package for inference and fine-tuning of Vision Language Models (VLMs) and Omni Models (VLMs with audio and video support) on your Mac using MLX.

Incremental PyPI Simple API caching mirror

A tamper-evident, append-only, hash-chained ledger. Dependency-free (stdlib only).

Governed structured-output LLM pipeline: rate limit → spend caps (per-user + global circuit breaker) → cache → provider-chain failover → Zod validation → usage logging → LLM-judge, with a deterministic mock provider for CI.

基于nonebot-plugin-nyaturingtest重构的群聊特化 LLM 聊天机器人，具有 LLM 驱动的记忆系统和表情包功能。

unstorage-sync driver for react-native-mmkv

Durable BullMQ-backed event bus adapter for Slingshot

BullMQ-backed orchestration adapter for Slingshot tasks and workflows

Python SDK for the AI Telecom voice API — place AI phone calls with a phone number and a prompt.

AIRiskGuard Gateway — AI traffic management. Route, protect and monitor every AI API call.

Persistent Node.js filesystem repository adapter for Folio.

GitHub Contents API repository adapter with direct and pull-request publishing for Folio.

ViewEngine Radar (org-scoped AI visibility) CLI as an importable mirage / Cloudflare-Worker command via @mirage-cli/core.

Per-project context-rank index for Claude Code, served from a local daemon.