ai-pipeline

High-performance data engine for AI and multimodal workloads. Process images, audio, video, and structured data at any scale

Powerful workflow engine and end-to-end pipeline solutions implemented with native Kubernetes resources. https://cyclone.dev

Community-driven, simple, yet powerful framework for fast, cost-effective distributed Compute over Data.

End-to-end AI short-video production pipeline. FastAPI orchestration + Spring Boot gateway with multi-model failover, circuit breaker, metering, and full-stack observability. AI quality gating: prompt anchoring, CLIP consistency, AV sync auto-rescue.

Genblaze is an open source Python SDK for orchestrating generative AI media pipelines across video, audio, and image providers with built in provenance for every output.

A distributed backend AI pipeline server

ForgeDock — autonomous AI dev pipeline for Claude Code. GitHub as agent memory: issue in, PR out.

NoiseFilter — an AI pipeline that turns long-form content into structured insights and syncs them to Feishu and the web.

565 AI-callable tools across 16 MCP servers. Full-pipeline AAA game asset production. Controls Blender, Substance Suite, Maya, Houdini, and Unreal Engine 5. 50 specialized AI agents. One prompt in, game-ready asset out.

👁️ LLM-native static vulnerability detection. An LLM reads your source like a human auditor, point it at any local folder or repo and get a reviewable vuln report. Auto-enriched prompts, adversarial validation, opt-in fix-verify. Runs on Claude Code / Codex / local OSS. Bug-bounty triage is one mode. Detection-only, read-only.

A fully local, GPU-accelerated pipeline to automatically translate manga/comics. Features YOLO detection, MangaOCR, LLM translation (Qwen), and smart typesetting. No external APIs.

A runnable reference implementation of multi-agent constraint propagation using Caura. 5 specialists share memory via MCP so decisions made upstream automatically govern downstream agents.

Local-first AI workflow orchestration for chaining models, agents, tools, and scripts into repeatable workflows.

ExplaineR is an R package built for enhanced interpretation of classification and regression models based on SHAP method and interactive visualizations with unique functionalities so please feel free to check it out, See ExplaineR paper at doi:10.1093/bioadv/vbae049

LLM-powered pipeline for parsing .eml files, extracting HTML bodies, classifying email attachments as relevant or irrelevant based solely on HTML context, and evaluating results against ground truth using automated metrics.

An AI-powered, fully automated n8n workflow that converts a single text prompt into scroll-stopping YouTube Shorts using dynamic visuals, dramatic TTS narration, and real-time editing — all self-hosted using Docker, Ollama, MinIO, and open-source tools.

Type-safe DAG execution engine for AI workflows

Provider-agnostic AI dev pipeline: clarify → plan → build → review → PR across your repos, mixing LLM providers per stage with your own keys. No vendor lock-in, no markup.

Lets you build smart, AI workflows with a visual interface. Open-source, extensible, and powered by GPT. Perfect for automating content, processes, and integrations.

A local‑first AI pipeline that generates coherent images, videos, stories, dialogues, and spatial audio from an augmented storyboard. It structures prompts, ensures narrative continuity, automates sound spatialization, and provides a reproducible workflow for fast, high‑quality multimedia creation.