Tag
Graphify is an open-source tool that turns codebases, docs, SQL schemas, configs, and PDFs into a queryable knowledge graph for AI coding assistants like Claude Code, Cursor, Codex, and Gemini CLI, using local deterministic AST parsing with no vector store.
Kent C. Dodds shares that his project Kody has grown to 250k lines of code in just a couple of months, built by one developer.
X (formerly Twitter) announces plans to open source their entire codebase, a major move towards transparency and community involvement.
Mindwalk is an open-source visualization tool that replays coding-agent sessions on a 3D map of your codebase, supporting Claude Code and Codex session logs with a local Go server and React/Three.js frontend.
The article argues that in large codebases, it's acceptable and often necessary to have only partial understanding, contrary to the ideal of complete comprehension advocated by Peter Naur's 'Programming as Theory Building'. It defends the practice of working with limited understanding in high-turnover, large-scale environments.
A video overview of the OpenClaw codebase showing maintainer contribution statistics.
The article argues that AI's coding effectiveness depends on codebase consistency, making rewrites economically viable to align codebases with AI's strengths, thereby improving output quality and speed.
Devin Security Swarm is a new tool that uses AI agents to automatically find and fix security vulnerabilities in codebases, achieving 72% recall at lower cost than alternatives.
OpenWiki is a CLI tool from LangChain that automatically generates and maintains documentation for your codebase, designed for AI agents. It supports multiple inference providers and can be integrated with GitHub Actions for daily updates.
OpenWiki is an open source agent and CLI that automatically generates and maintains documentation for codebases, helping coding agents understand repo structure and logic.
DeepSeek has open-sourced DeepSpec, a full-stack codebase for training and evaluating speculative decoding models.
An analysis of why running more than three parallel agents in Claude Code hits a bottleneck, revealing a duty-cycle problem where the developer becomes the primary latency source, and the 'join' process of merging parallel outputs is the biggest time cost.
A developer reports that using Qwen3.6-27B for vibe coding introduced subtle bugs in their codebase and asks the community for best practices to reduce errors when working with the model.
LiveDocs is an open-source, self-hosted chat box that answers documentation queries using both structured docs and the actual codebase, citing exact file locations to prevent stale or missing answers.
This paper introduces RL4F, an offline reinforcement learning benchmark for plasma control in nuclear fusion, providing closed-loop evaluation environments and baseline comparisons across four profile tracking tasks using real tokamak data from DIII-D. The codebase and datasets are open-sourced to foster further research.
A user praises a command or tool called /improve-codebase-architecture, describing it as a rarely seen wonderful skill.
MashuPack converts codebases into a single clean file for use with Claude and ChatGPT, streamlining AI-assisted code review.
Sheing Ng built Grok-Wiki, a native desktop app powered by Grok CLI that turns any code repository into a searchable wiki, enabling users to generate documentation, ask questions, and explore codebases locally.
Mintlify released mintlify.wiki, an auto-doc generator that keeps docs in lock-step with code, joining similar tools like DeepWiki and CodeWiki.
TorchUMM is a unified codebase for evaluating and analyzing multimodal models across understanding, generation, and editing tasks, with standardized protocols and diverse datasets, enabling fair comparisons and deeper insights into model strengths and limitations.