Whiteboard (YC W26) – An open-source IDE for thoughtful software design
Hello! We’re Sid, Alex, Ketan, and Milan. We’re building Whiteboard (https://whiteboard.dev.fast/), an open-source desktop app where humans and agents can architect software together in a common workspace. Here’s our repo: https://github.com/devdotfast/whiteboard.We were missing the feeling of a “whiteboard session” with another dev where you leave with a deep understanding of a system, so we built this app for ourselves. Whiteboard plugs into the tools you already use - e.g. Claude Code, Codex, etc. – and gives your agent an SDK to draw on an in-app canvas to describe its work. We began with an MVP based on HTML artifacts and started rethinking the app as we ran into limitations:1. Built on top of CodeOSS: We found that in pure HTML tools it was hard to connect a spec or diagram to code. In Whiteboard, when you click on visualizations like a sequence diagram, an entity relationship diagram, or a quote from the agent’s trace, you can jump to the underlying code directly. When navigating code, you get keybindings and LSP support from VSCode out of the box. We’ve found this is especially valuable because tradeoffs are often only discovered after a first pass at implementation (re: slop)2. Semantic diff viewer: we wrote a semantic, AST-aware diff viewer in Rust so you can only view the code changes which are relevant to you [1]. We’ve set up some sane defaults: large added functions are summarized as pseudocode, and things like unit tests and large documentation changes are collapsed / hidden. This is all customizable with a WASM-based plugin system.3. Decision Log: We found it difficult to reason about what set of decisions our agents made autonomously. So we built tools for agents to query and link their own traces to the Whiteboard, so you can understand how the requirements that you set were implemented, and understand what decisions your agent made autonomously.Here’s a quick demo video explaining more: https://www
FL score
out of 100
Verdict
high confidence
Competition
No competitor data yet
Trend
No signal yet
An IDE that bridges human architects and AI agents by making agent decisions visible and code changes understandable through semantic diffs and decision logs.
The pain
The gap
Build angle
Strengths
- Team is shipping fast with a working MVP and clear technical decisions (CodeOSS foundation, Rust semantic diff, WASM plugins).
- Addresses a real gap in the AI-assisted development workflow that will only grow as agents become more autonomous.
- Built-in extensibility through SDK and plugin system creates a platform for future integrations.
- YC backing and open-source strategy reduce friction for initial adoption.
- Semantic diff viewer is a genuine technical innovation that solves a specific problem other tools ignore.
Risks
- Market timing risk: AI agents may not become the default development workflow for years, limiting addressable market size.
- Monetization unclear: open-source positioning makes it hard to charge early adopters, and enterprise deals move slowly.
- Competitive pressure from well-funded IDE vendors (JetBrains, Microsoft) who could add agent collaboration features.
- Buildability concern: maintaining CodeOSS fork, Rust semantic diff engine, and WASM plugin system requires sustained engineering effort beyond four founders.
- Adoption friction: developers already invested in Claude Code or Cursor may not switch workflows for better decision visibility.
- Narrow TAM: only useful for developers who (1) use AI agents for architecture and (2) care about understanding agent reasoning, which is a small slice today.
Fly Labs Method
Is the pain real, is there a gap, is it the right time, can one person build it.
- Problem clarity
- 78
- Solution gap
- 75
- Willingness to pay
- 68
- Buildability
- 67
The problem of understanding AI agent decisions during code generation is real and underserved, but willingness to pay and solo buildability face headwinds from the crowded IDE space and technical complexity.
Value Equation
Dream outcome and how likely it feels, against the time and effort it costs.
The value exchange is unclear because the product targets a narrow slice of developers using AI agents for architecture, and the monetization path from open-source to revenue remains undefined.
One-Person Business
Curiosity pull, identity fit, and a path from free value to paid for a solo creator.
The idea solves a specific workflow problem for a small but growing segment, but lacks the broad appeal or network effects needed to become a category-defining tool.
Viral Frameworks
Hook strength, shareability, and how cheaply it can be tested.
The team has strong execution signals and YC backing, but the market timing depends on AI agents becoming the default way developers work, which is still uncertain.
Builder Lens
Evidence the problem exists, timing, defensibility, and a model that fits on a napkin.
A well-scoped tool built by capable founders addressing a real friction point in the emerging AI-assisted development workflow, though the path to defensibility and scale is not yet clear.
Five lenses, one composite. How scoring works
The angle
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
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
GlycemicGPT – Open-source AI-powered diabetes management
I'm a Type 1 diabetic and software engineer. Last year I went months between endocrinologists with no clinician reviewing my data. I'm an engineer, so I built the tool I needed — and now I'm open sourcing it. GlycemicGPT is a self-hosted platform that connects continuous glucose monitors, insulin pumps, and existing Nightscout instances to an AI analysis layer running on your own infrastructure. Data sources:Dexcom G7 (cloud API) Tandem t:slim X2 and Mobi pumps (direct BLE) Nightscout (point it at your existing instance and you're running in minutes)What the AI layer does:Daily briefs summarizing overnight and 24-hour patterns Meal response analysis Conversational chat with RAG-backed clinical knowledge Predictive alerting with configurable thresholds and caregiver escalationImportant: this is monitoring and analysis only. GlycemicGPT does not deliver insulin, does not control your pump, and is not a closed-loop system. It reads your data and gives you insight on top of it. Your clinical decisions stay between you and your care team. Architecture:Self-hosted via Docker or K8S — the GlycemicGPT stack runs entirely on your hardware BYOAI — bring your own AI provider. Use Ollama for fully local operation (no data leaves your hardware), or point it at Claude, OpenAI, or any OpenAI-compatible endpoint if you prefer a hosted model. Data flows directly from your instance to the provider you choose; nothing is routed through any centralized service operated by the project. GPL-3.0, no subscriptions, no vendor lock-inStack:Backend API: FastAPI, Python 3.12, PostgreSQL 16, Redis 7 Web Dashboard: Next.js 15, React 19, Tailwind CSS, shadcn/ui AI Sidecar: TypeScript, Express, multi-provider proxy Android App: Kotlin, Jetpack Compose, BLE Wear OS: Kotlin, Wear Compose, Watch Face Push API Plugin SDK: Kotlin interfaces, capability-based, sandboxedLooking for contributors — especially folks with BLE/Android experience or anyone in the diabetes tech spa
AI
Questions about this idea?
FlyBot reads the scoring and gives you a second opinion on “Whiteboard (YC W26) – An open-source IDE for thoughtful software design”.