Turn one photo into an animatable 3D model, plus a Mac video editor your AI edits alongside you

The Lens

img2threejs takes a reference image and rebuilds the object in it as procedural Three.js code, using primitives and shaders instead of a downloaded mesh. It is an agent skill, not a library or a CLI: you install it into Claude Code, Codex, or OpenCode and the agent runs the pipeline. MIT licensed. The design is the interesting part. Deterministic Python scripts, standard library only with no external dependencies, handle validation, quality gates, and code generation, while the model's tokens go only to the visual judgment steps: look at the image, assess it, review the render. That split is why it stays token-efficient, and it is a pattern more agent skills should copy. Web developers who need 3D objects and would rather not model them or license assets are the audience, mostly solo and small teams. Subjects get classified as object, character, or hybrid, and characters route through a separate anatomy-aware track rather than being refused outright. The skill costs nothing beyond the agent subscription you already have. The catch: it is strongest on hard-surface objects, and the project says so itself. Characters come out as stylized reconstructions, not photoreal likeness, and the projection-first likeness work is still on the roadmap rather than shipped. Credit where it is due, the skill is built to report low confidence and say the fidelity is not reachable from one image instead of confidently handing you something wrong.

The Lens

Palmier Pro is a native macOS video editor with AI wired directly into the timeline. The editor itself is open source under GPLv3 and free to use with no login. Where it gets interesting: you can generate video and images from models like Kling and Seedance right inside your edit, and it hooks into AI agents (Claude, Codex, Cursor) over MCP so an assistant can edit the project alongside you. There's not much to "host" here, it's a desktop app you install and run. The setup catch is hardware: it's Apple Silicon only and requires macOS 26 (Tahoe), so it won't run on older Macs or anything non-Apple. The core editing, the MCP server, and the agent chat are all in the open source build. The free editor is a capable tool on its own. The generative AI features are the paid part: those run closed source and need a login and a subscription. So the split is clean, free editing forever, pay only when you want in-timeline generation. Solo creators and developers curious about agent-driven editing: the free build is worth a look. If you'd lean on the AI generation daily, price the subscription against how much you'll actually use it. The catch is that the headline feature, the AI generation, is exactly the piece that's closed and paid. The open source part is a solid editor; the "built for AI" magic is a subscription. That's a fair way to monetize, just know going in that "open source AI video editor" is half the story.

The Lens

RAGFlow is a retrieval-augmented generation engine built around deep document understanding, and it has grown into an agent platform sitting on top of that. It still handles the messy parts of RAG that other frameworks hand-wave past: PDFs with tables, slides, spreadsheets, scanned images, mixed-language docs, now with MinerU and Docling parsing. On top of that it added agent memory, an MCP server, and delivery into chat channels like Discord, Telegram, and Feishu. Apache 2.0. Self-hosting is a real project, not a `docker run`. You need 4-plus CPU cores, 16-plus GB RAM, 50-plus GB disk, and Docker. The compose file spins up the RAGFlow service plus a search backend (Elasticsearch, or their in-house Infinity vector DB) and MinIO for blob storage. The template-based chunking is still the killer feature: you can see and tweak how documents are segmented before they ever hit the index. Solo developers and small teams that want full control of their RAG pipeline can self-host this and feel good about it. Larger teams, or anyone without infra time, should look at RAGFlow Cloud, which gives you the same engine without the ops. The catch is operational weight. If you just need to chat with a few documents, LlamaIndex or LangChain over a simple vector store ships faster. Pick RAGFlow when document parsing quality, citation grounding, and now agent workflows over your own documents are the thing you are actually buying.

The Lens

LangGraph defines AI agent workflows as graphs, where nodes are processing steps and edges are conditional transitions. Each node is a step (call the LLM, run a tool, check a condition), and edges define what happens next. The graph model matters because real agent workflows aren't linear. An agent might need to: research, then decide if it has enough info, loop back to research if not, then draft a response, then review it, then either revise or submit. LangGraph makes these branching, looping workflows explicit and debuggable. It builds on LangChain but works independently. Supports any LLM provider. State management is built in: each graph execution has persistent state that nodes can read and write. Human-in-the-loop patterns (pause execution, wait for approval, resume) are first-class features. The star velocity tells you where the market is heading. Agent frameworks are the hottest category in open source AI right now. The catch: the abstraction adds complexity. For simple "call an LLM with tools" flows, LangGraph is overkill. The OpenAI or Anthropic SDKs handle that directly. The LangChain ecosystem moves fast and breaks things; APIs change between versions. And debugging graph execution requires understanding the framework's internals, not just your business logic.