// edition · 2026-05-03
13 stories on AI dev tools, agents, and the coding stack — curated from the day's RSS haul by Agentic Dev's pipeline.
A developer released Claude Code Cost Explorer, an open-source local dashboard that reads Claude Code's session files to show API costs broken down by individual turn, prompt, and tool call. It installs via pip and requires no API keys or external data uploads.
A developer used Claude Code to build a complete notification system (schema, API, queue worker, tests) for a Next.js/Postgres project over one week without writing code manually. A missing `await` keyword on an async call in the generated worker code caused random 4-second notification delays in...
A developer compared two verification approaches for AI coding agents: Claude Code Skills, which use LLM judgment to decide when and how to verify work, versus deterministic shell commands that run on every workflow step with binary exit-code results. The author uses shell-based verification in t...
Anthropic's Claude Projects feature provides persistent workspaces where users can store custom instructions, uploaded knowledge files, and conversation history across sessions. Each project supports a 200,000-token context window, equivalent to roughly 500 pages of text.
A developer running a 30-day daily automation using Claude to improve calculator pages found that 8 of 28 improved pages had no Google Search Console presence, and all early-April pages recorded zero clicks. Meanwhile, the site's highest-impression page — 880 impressions in 28 days at position 57...
Simon Willison added a "Sightings" section to his blog that pulls in wildlife photos from his iNaturalist account, back-populating over a decade of observations totaling 208 entries. He built the feature using Claude Code on his phone as an extension of his existing content syndication system.
A developer released Spine v1, an open-source tool that scans code repositories and generates architecture maps, prioritized reading orders, and a persistent context file at `.claude/REPO_CONTEXT.md` for use with Claude Code sessions.
A benchmark of Meta's Llama 3 70B Instruct and Anthropic's Claude 3.5 Sonnet across 1.2 million user queries found Llama 3 delivered 22% lower p99 latency and cost $0.0008 per 1k tokens self-hosted versus Claude 3.5's $0.003 via API, while Claude 3.5 scored 98.0% versus 82.3% on HellaSwag reasoni...
Kimi K2.6, an open-weights language model developed by Chinese AI company Moonshot AI, outscored Claude, GPT-5.5, and Gemini on a programming benchmark challenge, according to a report published April 30, 2026.
A 14-person fintech engineering team reported migrating from Meta's Llama 3.1 70B to Anthropic's Claude 3.5 Sonnet for on-premises LLM workloads, claiming 62% lower inference latency (217ms to 82ms p99) and 41% reduced GPU costs ($12.4k to $7.3k monthly per 1M daily queries) after benchmarking se...
VS Code was automatically adding "Co-Authored-by: GitHub Copilot" to git commit messages regardless of whether Copilot was actually used, prompting a pull request to address the behavior. Microsoft opened PR #310226 in the VS Code repository to fix the unintended attribution.
A developer built README Clew, a tool that audits public GitHub repositories for discrepancies between README documentation and actual code, using Claude Sonnet 4.5 to extract claims and five deterministic verifiers to check dependencies, scripts, environment variables, and file references. The t...
OpenSearch released versions 3.5 and 3.6 in February and April 2026, adding Better Binary Quantization (BBQ) that compresses high-dimensional vectors by 32x and the SEISMIC algorithm for sparse neural approximate nearest neighbor search. The project is positioning the open-source search engine to...