Developer tools news — AI coding assistants, IDEs, CLI tools, APIs, and productivity tools for software engineers. GitHub Copilot, Cursor, and more.
A developer found that Ollama 0.34.0's OpenAI-compatible Responses API silently ignores the previous_response_id parameter, returning HTTP 200 with status "completed" while the model never sees prior conversation turns. …
A developer outlined a resilient Python client pattern for integrating NousResearch's hermes-agent against OpenAI-compatible endpoints, focusing on handling upstream HTTP 502, 503, and 504 errors without amplifying outag…
A developer built an AI-callable developer portfolio at techiewithbeard.com using Angular 22 and the emerging WebMCP (Web Model Context Protocol) standard, exposing structured tools that AI agents can query instead of sc…
A developer has reverse-engineered Anthropic's Claude tokenizer, finding it is not a standard byte-level BPE but instead uses a minimum-piece tokenization scheme similar to MinGram or PathPiece. The reconstruction reveal…
A developer running Claude Code with five separate subagents — architect, coder, reviewer, conflict resolver, and UI designer — found that one persona silently stopped loading after an editor inserted content above the o…
A developer testing NovelAI's V5 image generation API found that the params_version field — which third-party tools set inconsistently to 4, 3, 1, or 0 — produces pixel-for-pixel identical images when calling nai-diffusi…
A developer documented a workflow for running a Debian 13 Linux VM under Apple's container CLI on Apple silicon while offloading LLM inference to a local Gemma 4 model via Ollama on the Mac's Metal GPU. The setup splits …
Solon AI has released solon-ai-sandbox, a Java module that wraps agent-issued shell commands in real filesystem and network isolation on macOS, Linux, and Windows. The module, a Java port of Claude Code's sandbox-runtime…
A developer outlined four common AI agent architecture patterns — ReAct, SOP, Reflection, and Multi-Agent — in a deep dive on modern agent design. The writeup explains how each pattern handles reasoning, reliability, sel…
Simon Willison released commit-rewriter 0.1, a web app that edits Git commit messages across a repository, built to clean up commit messages for the Datasette security releases that contained coding agent cruft and priva…
A developer published a PowerShell script that automates access to Google's Gemini AI features on Windows by installing OpenVPN Connect V3, connecting to a US VPN Gate node with split-tunneling, and launching Chrome with…
Atlassian reports its Rovo Dev AI reviewer cut pull request cycle time by up to 45% internally and 32% for customers, but the reduction largely reflects routing of mechanical checks rather than the core correctness decis…
Specific Labs released Real-SWE, an enterprise-code SWE benchmark whose leaderboard shows that the same CLI harness can produce more than a 2x score gap depending on the underlying model. Results such as Codex CLI scorin…
Real-SWE benchmarked frontier coding agents against licensed, private enterprise codebases in billing, tax, and multi-service work, finding that extending rollout duration barely improves resolution rates. Rollouts finis…
Claudebox v2.4.2, a self-hosted MCP server that exposes Claude Code as an agentic AI tool over streamable HTTP, was published to the official MCP registry on 2026-09-14 as the Docker image docker.io/psyb0t/claudebox:v2.4…
A developer released Agent-Cache, an open-source multi-tier caching library for Valkey and Redis that stores LLM responses, tool outputs, and session state behind a single connection. Version 0.1.0 shipped with Valkey 7+…
A developer built a personal health knowledge base that uses retrieval-augmented generation to turn a decade of medical checkup PDFs into a queryable system. The pipeline combines LlamaIndex for orchestration, Unstructur…
SkillTotal v0.46.0, a deterministic security scanner for MCP servers, agent skills, and npm/PyPI packages, was published to the official MCP registry on 2026-09-14 and is distributed as skilltotal on PyPI. The mcpindex i…
A developer built a test harness for their mcpscan security scanner that generates synthetic attack fixtures to verify each detection rule, and found that 6 of 7 fixtures fired while the secrets-detection rule completely…
AI coding agents are shifting the primary consumers of code from humans to machines, making code itself secondary to correctness, speed and judgement, according to a blog post by developer Jimmyislive. The post argues th…