Tag
Glasshouse v0.1 is a memory benchmark tool designed to address issues with existing AI memory benchmarks by providing multi-language support, varied conversation lengths, and detailed evaluation across multiple axes.
A developer built a tool to compare different AI agent frameworks side-by-side, aiming to evaluate architectural differences and seeking feedback from experienced practitioners.
Devin has introduced cloud integration into its terminal CLI, allowing users to create, steer, and resume cloud sessions with features like handoff and full SSH access for a seamless development workflow.
python-build-standalone now uses full LTO for CPython 3.12 and later, which should modestly improve runtime performance. CPython defaults to ThinLTO when building with clang on these versions.
Valori is a deterministic memory layer designed for AI applications, aiming to provide reliable and consistent memory functionality.
agy-staff is a plugin that enables AI coding assistants like Claude Code and Codex to delegate tasks to Gemini 3.8 Flash for faster, cost-effective operations.
The article explains how Cloudflare's cloudflared tunnel can be used to expose local services to the internet without inbound ports, but warns that Cloudflare terminates TLS, exposing traffic in plaintext.
A tool called drawio-skill enables AI-powered generation of Draw.io diagrams, including reverse-engineering from codebases, with multiple templates and export options.
Datasette-explain version 0.2.2 has been released, enhancing Datasette with additional explanation features for data exploration.
Kent C. Dodds announces @kentcdodds/jev, a typesafe AI evaluation tool integrated with Cloudflare AI Gateway for making fast, typed decisions on inputs like messages and tickets.
Claude Code now supports AGENTS.md as a fallback configuration file in version 2.1.277, with an option to toggle the behavior in settings.
Vercel introduces turbo build machines that can be enabled for single deployments, providing 30 vCPUs and 60 GB of memory to speed up builds for hotfixes.
BonoboMock is a GoogleTest-compatible C++ mocking library that allows mocking of various function types without requiring virtual interfaces, released as open-source by Bloomberg.
Aclif is a CLI framework for AI agents that provides a unified grammar and canonical names across SaaS providers, simplifying integration and reducing context costs.
The article introduces 'gh secure', a GitHub CLI extension that enables free security settings in public repositories with a single command, following best practices from the GitHub Security Lab.
Tilia is a new formatter for Haskell that addresses challenges like comment handling, operator fixity inference, and CPP support.
Benzi is an AI coding agent that outperforms competitors on benchmarks by reading less source code and using deterministic tool calls, achieving high efficiency in code intelligence tasks.
The article presents a tool that displays the release age and training cutoff dates for 20 current AI models, highlighting how stale the data might be in each model.
Grok-Wiki is a local-first desktop tool that uses AI agents to power repository wikis, offering source-grounded context, CLI-owned model access, and integrated task management for developers.
Bough is an open-source tool that visualizes Claude Code and Codex history by reading local data to create an interactive view of daily tasks and prompts, ensuring privacy by keeping everything on the machine.