A developer created Agent Launch, a unified command-line interface that provides a consistent workflow for seven different local coding agents including Codex, Claude Code, and Cursor Agent. The tool,…
A developer released Agent Launch, a command-line interface that unifies launching local coding agents including Codex, Claude Code, Cursor, Gemini, and OpenCode. The tool provides a single command wi…
The open-source AI coding agent pi, from the earendil-works project on GitHub, has surpassed 46,000 stars and offers a terminal-based assistant that reads files, writes code, runs shell commands, and …
The llm-cli-gateway v1.6.0 now implements first-class prompt caching across all five supported LLM providers—Claude, Codex, Gemini, Grok, and Mistral Vibe—allowing developers to avoid paying for repea…
A new AI agent token cost calculator estimates monthly spending and waste for coding loops like Codex and Claude Code, allowing developers to input token counts, run frequency, and provider rates. The…
A developer outlines a practical workflow for "vibe coding" with Claude Code, emphasizing that initial project setup is too critical to delegate to AI. The engineer writes their own plan first, then d…
OpenAI's `/goal` feature for Codex suffers from "compaction amnesia" and "context rot," causing significant performance degradation on complex, multi-issue workflows due to flawed context management. …
Zed users can now run local AI models directly within the editor, offering complete data privacy, predictable costs, and always-available access without reliance on cloud providers. The company report…
A developer built Skillmux, a Go-based CLI tool, to manage over 40 skills across Claude Code, Codex, and .agents folders after skill accumulation created latency and incorrect suggestions in every ses…
OpenGSD, the open-source rebuild of the popular AI coding tool GSD, launched as a community-driven platform designed to eliminate context bloat and improve code verification. The tool operates across …
Trendshift, a new open-source software ranking platform, now lists trending repositories by momentum rather than star count. The platform features a diverse range of projects, including AI agent toolk…
A developer used OpenAI's Codex to build a time zone conversion app entirely through AI prompts, with minimal manual coding, and launched it for public use. The app, available at time.philna.sh, was c…
AI-assisted software engineering evolved from GitHub Copilot's statistical code completion (2021-2022) through conversational chatbots with retrieval-augmented generation (2023-2024) to the current Ag…
AWO is a new Go CLI tool that runs Claude Code and Codex in isolated git worktrees, preventing agent edits from directly modifying a developer's working tree. The tool executes agents in single, write…
Claude Code reads CLAUDE.md, not AGENTS.md, contrary to claims in third-party guides. Anthropic documents two methods to make Claude Code use AGENTS.md: importing it via @AGENTS.md in CLAUDE.md, or sy…
Matt Lambert has developed SWARM, a loop-based protocol for nonlinear creativity and signal detection designed to preserve human judgment in AI-influenced environments. The protocol structures idea de…
Developers are using AI coding tools not to produce low-quality code faster, but to write higher-quality code more slowly by leveraging multiple AI models to find and fix bugs during code review. The …
Despite widespread warnings that AI will eliminate white-collar jobs, the team at Every has found that automation creates more human work, not less. The company has automated coding, writing, and cust…
Researchers have developed Inductive Deductive Synthesis (IDS), an AI system that jointly generates formally verified code and mathematical proofs, solving a long-standing challenge in automated softw…
A new glossary from Hugging Face aims to clarify the terms "harness" and "scaffold" in AI agent development, following confusion among researchers at the ICLR 2026 conference. The glossary defines a "…