replicate

replicate

Explained projects

replicate-langchain: langchain-replicate: The adapter that learns Replicate at runtime
Workflow Automation
replicate-langchain: langchain-replicate: The adapter that learns Replicate at runtime
A deep dive into the IBM Granite Community bridge that resolves models, versions, and deployments on the fly, then normalizes messy tool calls into LangChain’s clean abstractions.
9 min read · Apr 7, 2026
replicate/cog-flux-kontext: The Shortcut Stack Behind Fast Image Editing
Self-Hosted AI
replicate/cog-flux-kontext: The Shortcut Stack Behind Fast Image Editing
A Cog wrapper turns FLUX.1 Kontext into a production API with compile warm-up, FP8 layers, and TaylorSeer caching that preserve the scene while changing the prompt.
8 min read · Apr 7, 2026
replicate/qwen-image-lora-trainer: The End of the Trigger Token
Local LLM Inference
replicate/qwen-image-lora-trainer: The End of the Trigger Token
A deep dive into the trainer that turns Qwen-Image personalization into plain-English prompt engineering, and what that reveals about modern LoRA workflows.
12 min read · Apr 7, 2026
replicate/skills: The Repo That Replaces the SDK With Instructions
Coding Agents
replicate/skills: The Repo That Replaces the SDK With Instructions
A tiny skill file, an MCP bridge, and live schema checks turn AI agents into self-updating Replicate users.
8 min read · Apr 7, 2026
Image Editing Arena: Making Image Models Agree Long Enough to Compare Them
3D Generative AI
Image Editing Arena: Making Image Models Agree Long Enough to Compare Them
A Cloudflare Worker, a schema shim, and a cost-aware UI turn incompatible image-editing models into a controlled side-by-side test.
7 min read · Apr 7, 2026
getting-started-openai-realtime: The Browser Becomes the Robot Arm
Voice & Multimodal AI
getting-started-openai-realtime: The Browser Becomes the Robot Arm
A thin Cloudflare Worker keeps the keys safe, WebRTC keeps the voice loop fast, and client-side tool calls turn speech into immediate action.
10 min read · Apr 7, 2026
replicate/getting-started-vinext: The Next.js Starter That Isn’t Running Next.js
Open-Source Replacements
replicate/getting-started-vinext: The Next.js Starter That Isn’t Running Next.js
It keeps the App Router feel, routes AI inference through Replicate, and shows how vinext and Cloudflare Workers can carry the stack without the usual Node-heavy assumptions.
8 min read · Apr 6, 2026
replicate-mcp-code-mode: When MCP Stops Picking Tools and Starts Writing Code
Coding Agents
replicate-mcp-code-mode: When MCP Stops Picking Tools and Starts Writing Code
Replicate’s experimental server swaps endpoint sprawl for a two-step workflow: search the docs, write TypeScript, execute it in a local Deno sandbox.
8 min read · Apr 6, 2026
replicate/cog-ltx-video-0.9.7-distilled: The Repo That Makes Video AI Deployable
Self-Hosted AI
replicate/cog-ltx-video-0.9.7-distilled: The Repo That Makes Video AI Deployable
A Cog wrapper for LTX Video that hides cold starts, GPU memory pressure, and awkward geometry rules behind a clean API.
8 min read · Apr 6, 2026
`replicate/cursedsit.com`: The AI sitcom that learned to act like TV
Voice & Multimodal AI
`replicate/cursedsit.com`: The AI sitcom that learned to act like TV
How a synthetic show becomes a seamless channel by trimming dead air, looping clips, and broadcasting through Replicate, Fly.io, and Cloudflare.
9 min read · Apr 6, 2026
cloudflare-ai-gateway-replicate-test: The One Header That Makes Replicate Feel Synchronous
Self-Hosted AI
cloudflare-ai-gateway-replicate-test: The One Header That Makes Replicate Feel Synchronous
A tiny Bash script hides a bigger lesson about AI infrastructure. Put a gateway in front of an async model API, layer auth cleanly, and the whole system starts to feel native.
6 min read · Apr 6, 2026
cog-official-openai-clip: The 12-Second Way to Ship CLIP
Local LLM Inference
cog-official-openai-clip: The 12-Second Way to Ship CLIP
A production-minded wrapper around OpenAI’s multimodal model, where the real problem is not inference. It is getting a 3.4GB model to wake up fast, stay cached, and return useful embeddings through a tiny Cog API.
12 min read · Apr 6, 2026
replicate/goo-logo: When a Logo Becomes a Living Shader
3D Generative AI
replicate/goo-logo: When a Logo Becomes a Living Shader
A tiny Cog package hides a headless OpenGL pipeline, an embedded logo, and a clean way to ship animated brand visuals as one deployable machine.
7 min read · Apr 6, 2026
replicate-model-classifier: The Librarian for a Model Zoo
Self-Hosted AI
replicate-model-classifier: The Librarian for a Model Zoo
A Cloudflare Worker feeds Claude schemas and real examples, maps Replicate models onto Hugging Face tasks, and caches the answer like a fact.
10 min read · Apr 6, 2026
cog: The Death of the Hand-Written ML Dockerfile
Self-Hosted AI
cog: The Death of the Hand-Written ML Dockerfile
How a Go-based expert system and a high-performance Rust orchestrator eliminated "CUDA hell" and standardized machine learning deployment.
8 min read · Apr 2, 2026