OPEN SOURCE
150 items
123 posts, 27 tools
Frame is an X11 server in 20,000 lines of assembly, built with Claude as a natural language compiler. It runs Firefox and GIMP on a third of Xorg's idle CPU.
Kimi K3 developer guide: the 2.8T-parameter model's 1M-token context, native vision, API pricing and open-weights timing, and how it fits coding agents.
LM Studio launches Bionic, a standalone agent harness for open models with local inference, voice input, and zero data retention cloud options.
Mozilla's State of Open Source AI report puts open models within 3.3% of closed ones, yet only 51% reach production. The deployment barriers explained.
Gemma 4 26B on a 2013 Xeon with no GPU: how a sub-$300 box reached about 5 tokens/sec, the silent MoE bug behind the gibberish, and the upstream fix.
Days after getting caught uploading entire codebases to xAI servers, Grok Build is now open source on GitHub. The HN community isn't convinced it's enough.
A new American open-weights frontier model with multimodal capabilities, 1M token context, and competitive benchmarks. Here's what the HN community thinks.
Open-source tool gives Claude Code, Codex, and other agents their own isolated Linux VM on your machine - network firewall included, no cloud account required.
Mesh LLM pools GPUs across home lab machines behind one OpenAI-compatible API, splitting 235B models over iroh and QUIC with no RDMA or NVLink required.
A solo developer built a complete JavaScript ecosystem from scratch - runtime, engine, package manager, and Electron alternative. Here's what HN thinks.
A solo developer built a 1,300-line C inference engine that runs the 744B GLM 5.2 model on consumer hardware by streaming routed experts from disk.
Mitchell Hashimoto on building Ghostty in Zig: why he chose Zig over Rust, how the GPU-first terminal is architected, and what Hacker News made of it.
Tencent's Hy3 ships 295B parameters but activates only 21B per token, matching flagship performance at flash-tier pricing under Apache 2.0.
pgrust, a Rust rewrite of PostgreSQL, passes all 46,000+ regression test queries. What it delivers, what it does not, and the HN debate on AI-assisted rewrites.
An 82M parameter text-to-speech model that runs on CPU and produces high-quality speech across multiple languages - no cloud APIs or GPU required.
Better Auth, the open-source auth framework popular with Next.js developers, is joining Vercel. What it means and why HN is wary of open source acquisitions.
Ternlight is a 7 MB ternary-quantized embedding model that runs semantic search in the browser via WASM, with no API calls. How it works and what HN thinks.
Flipper Zero firmware reaches stable 1.0 and moves to a community contribution model. What changes for contributors and how HN sees official vs custom firmware.
Leanstral 1.5 is Mistral's open Apache-2.0 model for Lean 4 theorem proving. The benchmark claims, the HN pushback on its bug-finding pitch, and how to use it.
Box3D is an open source 3D physics engine from the creator of Box2D, with cross-platform determinism, a wide SIMD contact solver and Valve Rubikon heritage.

Get Smarter About AI Dev
New tutorials, open-source projects, and deep dives on coding agents - delivered weekly.