Adam (YC W25) – Open-Source AI CAD: VALIDATE, 72/100 | Ideas Lab

AI-powered text-to-CAD tool that generates parametric 3D models through natural language, targeting makers and engineers who find traditional CAD software slow to learn.

The pain

CAD software has a steep learning curve. Fusion 360, SolidWorks, and FreeCAD require months to master. Engineers spend 40% of design time on mechanical grunt work, repositioning parts, adjusting dimensions, creating variations. Non-technical makers are locked out entirely. Parametric design (the ability to tweak dimensions and regenerate) exists in expensive tools but requires deep CAD knowledge.

The gap

No accessible tool bridges natural language to parametric CAD output. Existing AI tools generate static meshes (Meshy, Tripo3D) with no dimension control. Traditional CAD has no AI assistance. The gap is specifically: text → parametric code → interactive sliders → exports. Adam fills this by treating CAD as code generation, similar to how Copilot treats software.

Build angle

Start with makers and hobbyists (3D printing, robotics communities). They have real projects, low switching costs, and will evangelize. Build network effects through shared designs. Monetize through: (1) premium model access (Claude vs Gemini), (2) commercial export licenses, (3) enterprise CAD integration (Fusion 360 plugin). The open-source core keeps adoption high; the closed commercial layer captures value. Expand to constraint-driven modeling (build123d/CadQuery) to handle professional mechanical design, then pursue enterprise sales.

Strengths

Technical execution is solid: browser-based compilation, multi-model support, parameter extraction via regex is clever and fast
Addresses real friction in CAD workflows, parametric design is genuinely useful and currently locked behind expensive software
Open-source foundation creates distribution moat and community contribution potential
Clear export paths (STL, SCAD, OBJ, GLB, DXF) mean output is immediately useful in downstream tools
YC backing and founder credibility reduce execution risk
Model-agnostic architecture means they can swap in better LLMs as they emerge without rewriting core logic

Risks

Market size uncertainty: How many people actually want to design CAD via text? Makers may prefer visual tools; engineers may distrust AI-generated code for critical parts
Monetization is unclear: Open-source + free tier makes it hard to capture value. Enterprise CAD vendors (Autodesk, Dassault) have entrenched workflows and won't integrate easily
Quality ceiling: OpenSCAD is CSG-based (constructive solid geometry). Complex mechanical designs need constraint-driven modeling. The roadmap mentions build123d/CadQuery but that's non-trivial to integrate
Competitive response: Autodesk, Fusion 360, and others will add AI features. They have distribution, brand trust, and existing CAD knowledge bases. Adam's advantage erodes quickly
User retention: First-time users may generate one model, then abandon. Stickiness depends on building a design community or integrating into professional workflows, both are hard
Liability: If someone uses AI-generated CAD for a structural part that fails, who's liable? This could limit enterprise adoption

Fly Labs Method

Is the pain real, is there a gap, is it the right time, can one person build it.

72

Value Equation

Dream outcome and how likely it feels, against the time and effort it costs.

68

One-Person Business

Curiosity pull, identity fit, and a path from free value to paid for a solo creator.

75

Viral Frameworks

Hook strength, shareability, and how cheaply it can be tested.

70

Builder Lens

Evidence the problem exists, timing, defensibility, and a model that fits on a napkin.

78

Five lenses, one composite. How scoring works

The angle

Start with makers and hobbyists (3D printing, robotics communities). They have real projects, low switching costs, and will evangelize. Build network effects through shared designs. Monetize through: (1) premium model access (Claude vs Gemini), (2) commercial export licenses, (3) enterprise CAD integration (Fusion 360 plugin). The open-source core keeps adoption high; the closed commercial layer captures value. Expand to constraint-driven modeling (build123d/CadQuery) to handle professional mechanical design, then pursue enterprise sales.

No market research recorded for this idea yet.

Semble – Code search for agents that uses 98% fewer tokens than grep

Hey HN! We (Stephan and Thomas) recently open-sourced Semble. We kept running into the same problem while using Claude Code on large codebases: when the agent can't find something directly, it falls back to grep, reading full files or launching subagents. This uses a lot of tokens, and often still misses the relevant code. There are existing tools for this, but they were either too slow to index on demand, needed API keys, or had poor retrieval quality.Semble is our solution for this. It combines static Model2Vec embeddings (using our latest static model: potion-code-16M) with BM25, fused via RRF and reranked with code-aware signals. Everything runs on CPU since there's no transformers involved. On our benchmark of ~1250 query/document pairs across 63 repos and 19 languages, it uses 98% fewer tokens than grep+read and reaches 99% of the retrieval quality of a 137M-parameter code-trained transformer, while being ~200x faster.Main features:- Token-efficient: 98% fewer tokens than grep+read- Fast: ~250ms to index a typical repo on our benchmark, ~1.5ms per query on CPU (very large repos may take longer)- Accurate: 0.854 NDCG@10, 99% of the best transformer setup we tested- MCP server: drop-in for Claude Code, Cursor, Codex, OpenCode- Zero config: no API keys, no GPU, no external servicesInstall in Claude Code with: claude mcp add semble -s user -- uvx --from "semble[mcp]" sembleOr check our README for other installation instructions, benchmarks, and methodology:Semble: https://github.com/MinishLab/sembleBenchmarks: https://github.com/MinishLab/semble/tree/main/benchmarksModel: https://huggingface.co/minishlab/potion-code-16MLet us know if you have any feedback or questions!

AI

BUILD

85FL score

Postgres extension for BM25 relevance-ranked full-text search

Last summer we faced a conundrum at my company, Tiger Data, a Postgres cloud vendor whose main business is in timeseries data. We were trying to grow our business towards emerging AI-centric workloads and wanted to provide a state-of-the-art hybrid search stack in Postgres. We'd already built pgvectorscale in house with the goal of scaling semantic search beyond pgvector's main memory limitations. We just needed a scalable ranked keyword search solution too.The problem: core Postgres doesn't provide this; the leading Postgres BM25 extension, ParadeDB, is guarded behind AGPL; developing our own extension appeared daunting. We'd need a small team of sharp engineers and 6-12 months, I figured. And we'd probably still fall short of the performance of a mature system like Parade/Tantivy.Or would we? I'd be experimenting long enough with AI-boosted development at that point to realize that with the latest tools (Claude Code + Opus) and an experienced hand (I've been working in database systems internals for 25 years now), the old time estimates pretty much go out the window.I told our CTO I thought I could solo the project in one quarter. This raised some eyebrows.It did take a little more time than that (two quarters), and we got some real help from the community (amazing!) after open-sourcing the pre-release. But I'm thrilled/exhausted today to share that pg_textsearch v1.0 is freely available via open source (Postgres license), on Tiger Data cloud, and hopefully soon, a hyperscalar near you:https://github.com/timescale/pg_textsearchIn the blog post accompanying the release, I overview the architecture and present benchmark results using MS-MARCO. To my surprise, we were not only able to meet Parade/Tantivy's query performance, but exceed it substantially, measuring a 4.7x advantage on query throughput at scale:https://www.tigerdata.com/blog/pg-textsearch-bm25-fu

AI

BUILD

85FL score

Consus (YC F24) – LLM gateway for companies handling sensitive data

Hey Hacker News! I'm Eric, the founder of Consus. We route all AI requests to ITAR restricted and controlled unclassified information (CUI) compliant infrastructure. Consus itself satisfies ITAR restrictions, and we recently completed our FedRAMP equivalency audit against the 410 FedRAMP High controls. FedRAMP High is the U.S. government’s strictest security baseline for cloud services handling sensitive unclassified data. A breach of this data could cause severe or catastrophic harm. Achieving FedRAMP equivalency, or authorization, is required before processing CUI information.Demo: https://youtu.be/6MYxJe6P4oYAerospace and defense is experiencing rapid growth. Unfortunately, most companies are struggling to use AI because of necessary data protections & compliance risk. These companies can move even faster if they could use the AI tools that most other industries take for granted.I spent most of my career prior to Consus in aerospace & defense. I launched national security payloads at SpaceX, and was an early employee at Castelion. I’ve watched first hand how compliance red-tape makes it difficult for companies to adopt new technologies and trust vendors that touch their sensitive data. For example, I worked with a satellite manufacturer that doesn’t allow any AI tools, even for non-sensitive work.Even as AI has become extremely useful over the past 9-12 months, I was surprised by how many aerospace & defense companies refused to touch it. They could see how it could be helpful, but they were scared about model providers training on their data, violating an ITAR rule, or risk losing new business because of a failed cyber assessment. These are all rational fears.There were a lot of ways to solve some/all of these problems, but we focused on building a compliant AI inference layer that can "plug" into any AI tool or workflow. Just as OpenRouter integrates with most tools, Consus can connect to tools like ChatGPT or Clau

AI

BUILD

85FL score

All AI ideas