b2-labs

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.

Claude Skill for Backblaze B2 Cloud Storage management from the terminal. Manage buckets, list and search files, audit storage usage, detect stale or large objects, review security posture, and safely clean up data using natural language. Built on the Agent Skills specification and compatible with Claude Code and other skills-based agents.

MCP server for Backblaze B2 Cloud Storage: a focused, safe 40-tool surface (17 native B2 SDK, 19 S3 data-plane, 4 analytics) for any MCP-compatible AI client, currently incubating in Backblaze-Labs

A curated list of AI video generation APIs, SDKs, and tools including text-to-video, video editing, multimodal generation, diffusion models, and generative AI platforms. Covers commercial services, open source models with APIs, and production-ready infrastructure for developers building video applications.

Demonstrates uploading files from JavaScript in the browser to Backblaze B2 using both the B2 Native and S3-Compatible APIs

Starter kit for vibe coders building apps with file uploads and object storage. This full-stack dashboard template integrates with Backblaze B2 Cloud Storage and includes secure upload flows, file browsing, and basic storage management.

Production-ready AI SaaS starter kit: a Next.js 16 + FastAPI monorepo with Supabase auth, Stripe billing, text-to-image AI generation (NVIDIA NIM flux.1-dev), an admin console, and a Backblaze B2 file manager — an MIT-licensed, agent-optimized template that skips auth, billing, and storage boilerplate.

Code samples showing how to include data stored in Backblaze B2 in a RAG application

Backblaze-maintained TypeScript and JavaScript SDK for B2 Cloud Storage, currently incubating in Backblaze-Labs

A curated list of AI image generation APIs, SDKs, and tools including text-to-image, image editing, diffusion models, generative art systems, and multimodal AI platforms. Covers commercial services, open source models with APIs, and scalable infrastructure for developers building visual applications.

Backblaze-maintained B2 Cloud Storage GitHub Action, currently incubating in Backblaze-Labs

A curated list of AI audio generation APIs, SDKs, and tools including text-to-speech, speech synthesis, music generation, voice cloning, sound design, and generative AI platforms. Covers commercial services, open source models with APIs, and production-ready infrastructure for developers building audio applications.

A curated list of AI agent infrastructure: memory stores, vector databases, execution sandboxes, MCP servers, tool registries, observability, and evaluation tools for building and running autonomous agents.

Browser-based AI image background removal app using Transformers.js and the RMBG-1.4 model, storing original and cutout images in Backblaze B2 Cloud Storage — no GPU or backend required.

A curated list of physical AI tools: robotics foundation models, world models, simulators, teleoperation, sim-to-real, and embodied AI datasets for robot learning and autonomous systems.

Open-source AI shorts generator: turn one long video into vertical 9:16 clips with burned-in captions. Transcribes with Whisper, uses an LLM to pick the best moments, renders with ffmpeg — every source, transcript, and clip stored on Backblaze B2. Next.js + FastAPI sample app.

Docling RAG ingestion pipeline on Backblaze B2 — parse PDFs, DOCX, PPTX and HTML into clean Markdown and token-aware chunks written back to B2 over the S3-compatible API. Next.js + FastAPI, on-device models, no second API key.

Shared Hugging Face cache for teams. Sync local HF cache to Backblaze B2 or S3, eliminate repeated downloads, and enable fast, consistent model access across machines and CI.

AI image generation prompt flow example app focused on prompt engineering and prompt optimization, comparing models GPT Image, DALL-E, Gemini Nano Banana, and Google Imagen. Shows how image prompts are structured, refined, and evolved from input to final output, with clear prompt lineage for learning and experimentation.