Developer tools news — AI coding assistants, IDEs, CLI tools, APIs, and productivity tools for software engineers. GitHub Copilot, Cursor, and more.
A developer published a practical guide to fitting long-context LLM inference on 16 GB GPUs by budgeting VRAM for the KV cache, which grows with every active token and sequence. The guide provides a KV-cache size formula…
Jscpd v5, a copy/paste detector for programming source code maintained by kucherenko, now detects Type-2 renamed clones and Type-3 near-miss clones across 224 supported formats. The Rust-based tool runs on a Rabin-Karp a…
A database engineer's audit of 30 model-generated PostgreSQL schemas found that coding agents over-index tables, with one support-tool schema using 16 indexes on the `tickets` table versus a hand-written baseline of 7, p…
A developer built MindArena, an AI-powered quiz platform that supports both solo practice and live multiplayer contests, using React, Supabase, and n8n workflows instead of a traditional backend server. The system routes…
A developer outlined a structured-data approach for cross-border airport transfers, modeling Hong Kong Airport to Shenzhen and Dongguan bookings as a validated JSON and TypeScript schema rather than free-form chat reques…
A proposed AI agent loop stores structured "learnings" — each with a title, trigger, body, and originating project and ticket — in Git so that each completed ticket makes the next cycle cheaper, according to a Self-Impro…
StackGen principal engineer Sabith K Soopy detailed in a CNCF member post published 4 August that session traces and cost controls are needed to diagnose AI agent failures that standard application monitoring misses, suc…
OpenAI released its Agents API in public beta, letting developers build cloud agents that run autonomously for hours, execute code, and hand off tasks to sub-agents, with no extra fees beyond token usage. Cloudflare, Ver…
OpenAI opened its Agents API to all developers in public beta on September 10, packaging the Codex harness that powers its own coding agent behind a single API call that handles session state, context compaction, crash r…
A developer built a PDF Chat API in a single day using FastAPI, Google Gemini, Qdrant, and LangChain, enabling users to upload PDFs and ask natural-language questions answered through a retrieval-augmented generation pip…
Developer AniketWathore released Ramanujan, a free terminal-based multi-model agentic workbench for research in computational mathematics, available on GitHub. Ramanujan spawns N parallel subagents across any OpenAI-comp…
A developer compared five image compression tools — TinyPNG, compressor.io, docsmall, Squoosh, and ImgIng — on features including batch processing, animated image support, format coverage, and free-tier limits. The revie…
JetBrains's SkillsBench benchmark found that RTK (Rust Token Killer), a terminal-output compression tool with over 79,000 GitHub stars, produced no consistent cost savings for AI coding agents, with DeepSeek V4 Pro 0813 …
Developer Om Talaviya released claude-trade-skills, a free open-source Claude Code plugin that adds country-specific trade compliance rules to AI-generated export paperwork. The plugin targets US-centric bias in AI tools…
A developer argues that most enterprise RAG pipeline failures originate at the document parsing stage of ingestion, before any query runs, rather than in the LLM or retrieval layers teams typically tune. The writeup docu…
A security researcher tested 24 exfiltration payloads against a deny-by-default Tensorlake Sandbox configured with a single allowlisted destination, api.github.com, and none of the payloads delivered a token to the attac…
The stellarshenson/claude-code-plugins marketplace released a project-management plugin for Claude Code that stores acceptance criteria and defects in two markdown files per project, docs/acc-crit-<project>.md and docs/d…
BiNeuron, an open-source local alternative to Claude Code, was posted to Hacker News as a Show HN project. The tool supports over 25 programming languages including Python, Java, C/C++, JavaScript, TypeScript, Go, Rust, …
Cognition released SWE-2 on September 10, 2026, a coding model it says scores within one benchmark point of Anthropic's Fable 5.1 on FrontierCode 1.1 Main (50.0% vs 50.9%) at 64% lower compute cost, and is offering it fr…
A developer argues that AI coding agents, being probability machines trained on a web where 96% of top homepages have accessibility issues per WebAim's One Million report, tend to reproduce inaccessible patterns rather t…