We built a multi-agent research hub. The waitlist is a reverse-CAPTCHA
Hey HN,Automated research is the next big step in AI, with companies like OpenAI aiming to debut a fully automated researcher by 2028 (https://www.technologyreview.com/2026/03/20/1134438/openai-i...). However, there is a very real possibility that much of this corporate research will remain closed to the general public.To counter this, we spent the last month building Enlidea---a machine-to-machine ecosystem for open research.It's a decentralized research hub where autonomous agents propose hypotheses, stake bounties, execute code, and perform automated peer reviews on each other's work to build consensus.The MVP is almost done, but before launching, we wanted to filter the waitlist for developers who actually know how to orchestrate agents.Because of this, there is no real UI on the landing page. It's an API handshake. Point your LLM agent at the site and see if it can figure out the payload to whitelist your email.
FL score
out of 100
Verdict
high confidence
Competition
7
competitors found, emerging market, funded players
Trend
No signal yet
A decentralized multi-agent research hub with an agent-only waitlist, addressing the future problem of closed AI research.
The pain
The gap
Build angle
Strengths
- Highly innovative and visionary concept in a cutting-edge field (AI agents).
- Addresses a significant, albeit future-oriented, philosophical concern about open science.
- Clear differentiation from existing human-centric AI research tools.
- The 'reverse-CAPTCHA' is a brilliant, viral, and effective way to filter for the target audience.
- Strong leverage potential if successful, establishing leadership in decentralized AI research.
Risks
- Extremely high technical complexity for a solo builder.
- Demand for a fully autonomous, agent-to-agent research platform is speculative and not an immediate, widespread pain.
- Unclear and unproven monetization strategy for a decentralized ecosystem.
- High assumption risk regarding agent orchestration capabilities and willingness to pay for such a system.
- Competition from well-funded incumbents (e.g., Perplexity, Superagent) who might pivot into agentic systems.
- Limited target audience size (developers who orchestrate agents) may hinder initial growth.
Next steps
- Continue collecting sign-ups via the reverse-CAPTCHA and engage directly with those early users to deeply understand their specific needs, workflows, and willingness to pay for autonomous agent collaboration.
- Focus the MVP on the single most critical autonomous agent interaction, proving its value before expanding features like bounties or peer review.
- Explore potential revenue models (e.g., API usage fees, premium agent features, data licensing) and validate them with the waitlist audience.
- Research the technical feasibility of a truly decentralized system for a solo builder, considering incremental decentralization.
Fly Labs Method
Is the pain real, is there a gap, is it the right time, can one person build it.
- Problem clarity
- 19
- Solution gap
- 19
- Willingness to pay
- 12
- Buildability
- 10
The idea targets a niche but forward-thinking problem of open, decentralized AI research. While there's a clear whitespace from existing human-centric tools, the complexity and nascent demand for a fully autonomous agent ecosystem make it a challenging build for a solo founder, with unclear willingness to pay signals for this specific approach.
Value Equation
Dream outcome and how likely it feels, against the time and effort it costs.
This idea has potential in a rapidly growing, speculative market, but its complex build, abstract value proposition, and challenging go-to-market make it a high-risk venture for monetization.
One-Person Business
Curiosity pull, identity fit, and a path from free value to paid for a solo creator.
A highly complex, niche idea targeting a speculative future problem, requiring significant technical prowess and an unproven monetization model for a solo builder.
Viral Frameworks
Hook strength, shareability, and how cheaply it can be tested.
A technically ambitious idea with a clear, niche target audience but high business model and assumption risks, requiring more validation for commercial viability.
Builder Lens
Evidence the problem exists, timing, defensibility, and a model that fits on a napkin.
A visionary idea targeting the future of AI research with a clever, technical entry point, but the immediate demand and concrete user benefits are still speculative.
Why this verdict
Five lenses, one composite. How scoring works
The angle
This weekend
- Continue collecting sign-ups via the reverse-CAPTCHA and engage directly with those early users to deeply understand their specific needs, workflows, and willingness to pay for autonomous agent collaboration.
- Focus the MVP on the single most critical autonomous agent interaction, proving its value before expanding features like bounties or peer review.
- Explore potential revenue models (e.g., API usage fees, premium agent features, data licensing) and validate them with the waitlist audience.
- Research the technical feasibility of a truly decentralized system for a solo builder, considering incremental decentralization.
Who is already there, emerging market
An AI research assistant that uses semantic search to find papers, summarize them, and extract key information for systematic reviews and literature reviews.
Pricing: Free plan; Plus plan: ~$12/month (billed annually); Pro plan: ~$49/month (billed annually); Scale plan: ~$169/month (billed annually); Enterprise: Custom pricing.
An AI-powered platform for academic research and writing that offers paper summarization, automated literature reviews, and AI-assisted writing.
Pricing: Basic (Free); Premium: $20/month (or $12/month billed annually); Teams: $18/user/month (or $8 annually); Advanced: $90/month; Max: $200/month.
An AI-powered search engine for researchers that scans a repository of scientific papers to answer research queries with supporting and opposing evidence.
Pricing: Limited free usage; Paid plans: $11.99/month or $108 annually for individuals. Enterprise pricing starting at $600/month, averaging $25,000 for sales teams, and over $100,000 for enterprise.
An AI search engine that provides real-time, citation-backed answers to queries and offers conversational AI for research.
Pricing: Free plan; Pro plan: $20/month or $200 annually; Max plan: $50/month or $200/month (Dec 2025 data); Enterprise Pro: $40 per user/month or $400 annually; Enterprise Max: $325 per user/month or $3,250 annually.
- Paperguide AI Research AssistantVisit
An all-in-one AI research assistant that handles paper discovery, systematic reviews, reference management, and AI-powered writing.
Pricing: Paid plans start at $9/month.
A new AI research assistant that works as a coordinated team of agents to answer complex questions and deliver polished reports.
Pricing: Not specified in search results; likely requires a demo or custom quote given its nature.
A system designed to automate the complete scientific research process, from idea generation and literature search to experimentation and manuscript writing.
Pricing: N/A (research project, not a commercial product).
What they charge
Recent news
- The AI Scientist: Full Automation of Scientific Research
Avantgarde News, March 28 2026
- The AI Scientist takes a big step toward end-to-end automation of scientific research
Nature, March 27 2026
- Perplexity vs. ChatGPT: Which AI tool is better? [2026]
Zapier, March 24 2026
- SciSpace Review (2026): Pricing, Pros + Free Trial | Comparateur-IA
Comparateur-IA, March 18 2026
- Elicit vs. Scispace: Comparing AI Research Tools (2026) - Paperguide
Paperguide, March 20 2025
Market signals
The market for AI-powered research tools is rapidly growing, driven by the increasing volume of academic literature and the need for faster, more efficient research. Recent advancements are pushing towards fully automated research, with companies and research institutions investing heavily in multi-agent systems. Several AI research tools have secured funding, and new products are continuously launching, indicating a dynamic and expanding market.
What frustrates people
- Slow, opaque credit consumption, and misleading compensation policies.
- Limited features and restrictive usage in free or basic plans.
- Generic AI writing features that lack depth and true understanding of user intent.
- Lack of deep linking to original PDF sources, requiring manual investigation.
- Limitations in handling non-English academic writing and citation formats.
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 “We built a multi-agent research hub. The waitlist is a reverse-CAPTCHA”.