GoModel – an open-source AI gateway in Go: VALIDATE, 62/100 | Ideas Lab

A lightweight Go-based AI gateway that competes on Docker image size and debuggability against LiteLLM, but needs to prove it solves real problems better than the incumbent.

The pain

Teams using multiple AI model providers face three concrete problems: (1) they can't easily track spending and usage per customer or internal team, (2) switching models requires code changes, (3) debugging API interactions is tedious. LiteLLM solves these but ships a 746MB Docker image and had a recent supply-chain incident.

The gap

LiteLLM dominates the AI gateway space with 10k+ GitHub stars and established adoption. GoModel is smaller and faster to deploy, but hasn't demonstrated that these technical advantages translate to customer preference or willingness to switch. The supply-chain attack creates a narrow window of opportunity, but that window closes as LiteLLM's reputation recovers.

Build angle

Start by validating that the 17MB vs 746MB difference actually matters to paying customers, specifically, which teams have deployment constraints that make LiteLLM's size a blocker. Then build distribution through DevOps and platform engineering communities where image size and observability are valued. Avoid competing on feature parity; instead, own the 'lightweight + debuggable' positioning and build integrations that make switching from LiteLLM frictionless.

Strengths

Technical differentiation is real: 44x smaller Docker image reduces deployment friction and attack surface
Environment-variable-first config is pragmatic for containerized deployments
Timing captures LiteLLM skepticism without requiring the product to be perfect
Solo founder with working code and contributors shows execution ability
Go language choice aligns with DevOps/infrastructure tooling preferences

Risks

LiteLLM is entrenched with massive community and ecosystem; switching costs are high for existing users
No evidence of paying customers or product-market fit, open-source adoption ≠ commercial viability
Feature set appears to match LiteLLM's core offering; unclear what GoModel does better beyond size and debuggability
Solo founder scaling a developer tool requires sales and marketing skills that aren't demonstrated
Supply-chain attack window is temporary; LiteLLM will recover trust within 6-12 months, eliminating the main acquisition lever
Semantic caching and cost tracking are table-stakes features, not differentiators
No pricing model or business strategy mentioned; unclear if this becomes a company or stays a hobby project

Fly Labs Method

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

62

Value Equation

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

58

One-Person Business

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

71

Viral Frameworks

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

65

Builder Lens

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

68

Five lenses, one composite. How scoring works

The angle

Start by validating that the 17MB vs 746MB difference actually matters to paying customers, specifically, which teams have deployment constraints that make LiteLLM's size a blocker. Then build distribution through DevOps and platform engineering communities where image size and observability are valued. Avoid competing on feature parity; instead, own the 'lightweight + debuggable' positioning and build integrations that make switching from LiteLLM frictionless.

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