First screen, captured .
99 points by adchurch | 32 comments
Show HN post announcing Weave Router 2.0, an open-source model router for coding agents that switches between LLMs to match GPT-6 Astra performance at lower cost.
99 points by adchurch | 32 comments
Show HN post announcing Weave Router 2.0, an open-source model router for coding agents that switches between LLMs to match GPT-6 Astra performance at lower cost.
62 points by thefourthchime | 38 comments
PacBench, a benchmark site comparing how well AI model and harness combinations recreate a Pac-Man game in a single HTML page from one prompt.
119 points by florianstandhar | 32 comments
Benchmark Heaven's JevBench v1.3.0 leaderboard page ranking 52 Jev-class typed decision models on intelligence, calibration, speed and cost across 534 decisions.
9 points by bsutto | 3 comments
Show HN post introducing reVault, a Rust-based encrypted, signed, compressed archive format (lockbox) with CLI, keyserver, and multi-language bindings.
359 points by n2d4 | 75 comments
GitHub repository for pgmock, an open-source in-memory PostgreSQL implementation for unit and end-to-end tests.
49 points by cyfyifanchen | 39 comments
GitHub repository for Raven by EverMind-AI, a self-evolving multi-agent ecosystem billed as a 'harness of harnesses' for recursive self-improvement.