Superset (YC P26) – IDE for the agents era
Hey HN, we’re Avi, Kiet, and Satya. We’re building Superset (https://github.com/superset-sh/superset), an open-source agentic IDE for running coding agents like Claude Code, Codex, OpenCode etc in parallel.Demo: https://www.youtube.com/watch?v=YWDHn7gUwfgTry it: https://superset.sh/We’re three engineers who’ve built and maintained large codebases, and we kept wanting to work on more than one thing at a time. Once CLI coding agents got good enough we found ourselves running several of them in parallel: triaging Github issues, adding a few ui features, reviewing PRs, researching a refactor, etc.The funny part was that we and a lot of our friends had all hacked together similar scripts around git worktrees. Worktrees are a nice primitive for this because each agent can get an isolated copy of the repo, but the workflows around them can feel pretty messy, setting up/tearing down environments and managing dev servers.We first posted here a few months ago when Superset was mostly an open-source terminal for managing git worktrees (https://news.ycombinator.com/item?id=46368739). Since then, it has changed a lot based on feedback from people using it on real codebases, plus contributions from our open-source community. The product has grown into something closer to an IDE for managing agent work across many worktrees, repos, and machines.The biggest thing we learned is that the hard part is not just “run more agents.” It is managing all the state around them: worktrees, ports, terminal sessions, environment setup, diffs, tasks, and PRs. Once you have five or ten agents running, the bottleneck often becomes remembering what each one is doing and actual human review. We added task / issue tracking so work can move from issue → agent → diff → PR → review without losing the context all in Superset. But there's a lot more work to improve this experience over time.We also launched Remote Workspaces, c
FL score
out of 100
Verdict
high confidence
Competition
No competitor data yet
Trend
No signal yet
An IDE that orchestrates multiple AI coding agents in parallel, solving the state management chaos that emerges when running 5+ agents simultaneously on real codebases.
The pain
The gap
Build angle
Strengths
- Timing: Perfectly positioned at the inflection point where agents are capable enough to run in parallel but tooling hasn't caught up
- Founder-market fit: Built by engineers who experienced the pain firsthand; not theoretical
- Organic adoption: Already has open-source community contributions and real usage on codebases
- YC validation: Accepted to P26, suggesting strong founder quality and market timing
- Defensible moat: State management complexity creates switching costs; network effects from open-source community
- Expanding TAM: As agents improve, demand for orchestration will grow exponentially
Risks
- Agent capability dependency: If Claude Code/Codex plateau or don't improve, demand for orchestration diminishes
- Rapid competitive response: GitHub, JetBrains, or cloud IDEs could add multi-agent features quickly
- Monetization unclear: Open-source IDE model makes B2B SaaS conversion challenging; enterprise features not yet defined
- Market education required: Most teams aren't yet running 5+ agents in parallel; adoption curve may be slower than expected
- Integration complexity: Requires deep integration with git, multiple LLM APIs, dev environments, high maintenance burden
- Human review bottleneck: Even with perfect orchestration, human review remains the constraint; may not be a big enough problem to sustain a company
Fly Labs Method
Is the pain real, is there a gap, is it the right time, can one person build it.
Value Equation
Dream outcome and how likely it feels, against the time and effort it costs.
One-Person Business
Curiosity pull, identity fit, and a path from free value to paid for a solo creator.
Viral Frameworks
Hook strength, shareability, and how cheaply it can be tested.
Builder Lens
Evidence the problem exists, timing, defensibility, and a model that fits on a napkin.
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
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
Questions about this idea?
FlyBot reads the scoring and gives you a second opinion on “Superset (YC P26) – IDE for the agents era”.