Learn from 30 historical figures, open source, nonprofit, self-hosted
Hello HN, I am the founder of Agora Cosmica.This started about three years ago. On a walk I asked a chatbot to interpret the cave dream from Cormac McCarthy's book "The Road" as C.G. Jung. It gave me a perspective I had not thought of. But for my own dreams the policies of the big providers felt wrong for so personal conversations, as zero data retention is not available. So I started building.The project evolved to a German nonprofit and we published the code (AGPL-3.0) last month. The content is still copyright, but will be opened to CC-BY 4.0 in the next 6 to 12 months.Agora Cosmica is a library to learn from 30 historical figures. Each one has 12 narrated stories about their teachings / life wisdom, speech to speech conversation. Four learning modes and a council where you can gather the figures to discuss or reflect on a topic. Each figure is an AI Echo, an interpretation grounded in primary works, historical context, with a factcheck per figure to show what's verified versus recreated. On privacy: The speech is self hosted on Hetzner GPU servers, Qwen3-TTS for German, Kokoro TTS for English, Faster-Whisper for transcription. 30 free messages per day (EU-hosted for GDPR), BYOK, or you can run it in a full local self-hosted mode.No conversation is stored, no tracking cookies, no profiling, no signup.The app is slow on purpose. Cosmic, no dopamine rush.The mission is to be a doorway, a first step, an introduction to get people interested and outgrow the app to move to primary texts and human teachers.Live at: https://agoracosmica.org
FL score
out of 100
Verdict
medium confidence
Competition
No competitor data yet
Trend
No signal yet
A privacy-first conversational learning platform featuring AI interpretations of 30 historical figures, positioned as a gateway to deeper study rather than a destination product.
The pain
The gap
Build angle
Strengths
- Shipped product with real privacy implementation (self-hosted TTS/transcription, no storage, no tracking)
- Clear philosophical positioning that differentiates from engagement-maximizing competitors
- Open source code (AGPL-3.0) builds trust and enables community contribution
- Solves a real problem for people uncomfortable with data retention on intimate conversations
- Founder has conviction and has iterated for 3 years before public launch
- Multi-modal learning (narrated stories, speech-to-speech, council mode) shows thoughtful design
Risks
- Nonprofit structure limits ability to raise capital for scaling and may struggle to attract top talent long-term
- 30 historical figures is a fixed, non-expanding asset, no clear path to growth beyond initial set without massive content creation effort
- Intentionally slow/non-addictive design conflicts with user acquisition and retention metrics VCs typically track
- No clear monetization model articulated; 30 free messages/day suggests freemium, but nonprofit status complicates this
- Market size unclear, how many people actually want this vs. how many try it once? No traction metrics shared
- Positioning as 'gateway to primary texts' means success is measured by users leaving, not staying
- German nonprofit structure may limit international expansion and hiring
- Dependency on open source TTS/transcription models that may change or become unavailable
- No evidence of product-market fit beyond founder conviction; early HN post ≠ validated demand
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 “Learn from 30 historical figures, open source, nonprofit, self-hosted”.