The full gallery
Tech stack
23 projects
Play strategic games against AI models and see how different LLMs rank on an objective leaderboard.
masterchef2209 · HN
I created a platform to check which AI models is the best gamer
API providing token-level citations for LLM output grounded in attention analysis.
apoorvumang · HN
TokenPath – token-level citations for LLM output, read from attention
Benchmark version-control systems and coding agents on realistic development tasks.
videlov · HN
I was interested in answering this question so I built a benchmark comparing git, jj and gitbutler in agentic context https://vcbench.dev/ Disclaimer - I am a co-founder of GitButler
Inspect RAG chunks and visualize AI agent workflows, memory architecture, and execution traces.
@Higgs0110 · X
Build and run ML workflows in an agent-native cloud notebook with evaluation tools.
eldar_hsnv · HN
Show HN: AI Notebook for Data Science – Kind of Like Cursor but for Jupyter
Compare and benchmark SaaS APIs with independent verified data to make informed build-vs-buy decisions.
fenilsuchak · HN
OpenBenchmarks – Helping agents discover and pick the right SaaS APIs
Access 207+ AI models from different providers through a single unified API.
TaylorM492 · HN
InferAll – One API for OpenAI, Anthropic, Google, Nvidia Nim
Agent-native TypeScript framework that trains and deploys custom ML models on managed GPUs.
@soleil_colza_ · X
Explore Y Combinator companies and receive an AI analysis of your startup idea's fit with the accelerator.
sirily11 · HN
Application Signal – AI That Evaluates Your YC Startup Idea
Monitor LLM calls, APIs, and infrastructure performance for AI agents.
kirankgollu · HN
Oodle.ai – $10 per million agent traces
Interactive solver and visual guide for projectile motion problems.
@Quaxguy · X
