Daily shares of interesting GitHub open-source projects. AI tools, automation gems, technical tutorials, open-source inspiration.
Vercel Labs' fx is a 7.8 MiB Zig-compiled coding agent kernel that runs as a CLI, connects to editors via ACP, and embeds into JavaScript apps via WebAssembly, offering model-agnostic design, fine-grained permissions, automatic session compression, and 40× faster initialization than prior versions.
This article compares two open-source approaches to AI-powered design-to-code conversion: screenshot-to-code, a universal tool that turns any screenshot into runnable frontend code with self-correcting iteration, and lanhu-mcp, a team-focused MCP server integrating AI with the Lanhu design platform for shared context and knowledge.
This article explains how Heretic automates directional ablation to permanently remove refusal behavior from language models by editing model weights, contrasting it with jailbreaks and steering vectors, and details its use of Optuna optimization with KL divergence to preserve model capabilities, situating it within a broader taxonomy of model modification techniques.
Fallow is a Rust-based static analysis tool that builds a complete dependency graph of TypeScript and JavaScript projects to detect dead code, circular dependencies, code duplication, complexity hotspots, architecture violations, and style drift, offering zero-configuration setup, millisecond-speed scans, CI integration, and machine-readable output for AI coding assistants.
The open-source project ai-engineering-from-scratch offers a 523-lesson, 20-phase curriculum that teaches AI engineering by building reusable tools from scratch, integrating coding agents as personalized tutors to bridge the gap between using AI tools and understanding their internals.
This article compares two open-source CapCut alternatives—Concat, a local-first desktop editor using Rust and Whisper for privacy, and Pireel, an AI-agent programmable editor with a BYO-brain architecture—analyzing their technical designs, trade-offs, and ideal use cases for creators.
This article reviews an open-source book 'Deep Understanding of AI Agent' that structures AI Agent engineering around the formula Agent = LLM + Context + Tools, offering 10 chapters and 103 runnable Python experiments covering context engineering, memory, tool use, multi-agent collaboration, and model post-training.
StemDeck is a free, open‑source desktop tool that uses the Demucs AI model to separate a track into up to six stems—vocals, drums, bass, guitar, piano and others—while keeping audio on your machine, addressing cost and privacy concerns of cloud‑based services.
Worktrunk, a Rust‑based CLI tool, streamlines Git worktree management so each AI coding agent can work in its own isolated directory, eliminating file‑level conflicts and simplifying the full lifecycle—from creation and parallel execution to merging, cleanup, and advanced features like hooks, shared caches, and AI‑generated commit messages.
Zoo Code is a VS Code extension that bundles multiple AI agents into distinct modes—Code, Architect, Ask, Debug, and custom roles—enabling natural‑language driven code generation, refactoring, debugging, documentation, and workflow orchestration, effectively giving developers an in‑editor AI development team.
