Developer tools news — AI coding assistants, IDEs, CLI tools, APIs, and productivity tools for software engineers. GitHub Copilot, Cursor, and more.
A new Claude Code plugin called trajectory segmentation adds a side pane that breaks long autonomous agent sessions into short, non-overlapping phases, listing each decision the agent made and the reason behind it. The p…
Slaunt launched on Hacker News' Show HN, offering a platform that gives AI agents scoped, tenant-isolated permissions and an immutable, queryable log of every agent action. The tool ingests conversations, agent activity,…
A developer has outlined a method for running autonomous AI coding agents safely on Apple Silicon Macs by isolating agent execution inside a Linux VM while keeping model inference on the macOS host, working around Virtua…
OpenCode and OpenRouter launched Union Alpha, a free "stealth" coding model, on September 16 with a 262,144-token context window, text and image input support, and a zero-retention data policy. The model is free during a…
A developer published a guide showing how to call Google's Gemini models directly from an Angular browser app using Firebase AI Logic, the successor to Vertex AI in Firebase, without building a custom backend proxy. The …
A lead developer at a major Latin American fintech describes a framework for organizing ephemeral, mixed human-AI teams to speed software delivery. The developer argues the main barrier to AI-assisted development is orga…
A developer tested OpenAI's Codex and GitHub Copilot for building proof-of-concept applications, finding Codex produced a working React PDF viewer and extraction tool with iterative prompting while GitHub Copilot generat…
AI compilers differ fundamentally from classical compilers because they operate over a small set of recurring model families — transformers, convolutional networks, diffusion models, and mixture-of-experts — and because …
CuTile Rust (cutile-rs) extends Rust's ownership model to CUDA tile operations, partitioning mutable outputs into disjoint pieces so the compiler can verify data races are avoided before code reaches the GPU. The library…
Microsoft released Visual Studio Code 1.138 on September 16, 2026, adding the ability to run agent sessions inside local Dev Containers, expanded Codex support in the agent host, and a preview session-cleanup feature. Th…
Java code submitted to RuneLite's Plugin Hub has risen roughly 100x since the start of 2026, with about 20x as many submissions and each submission about 5x bigger, according to OSRS Wiki director Cook Me Plox and RuneLi…
A developer who has extensively used AI coding tools including Codex, Cursor, Claude Code, Copilot, and GLM reports that despite roughly 5x productivity gains, human oversight remains essential. The engineer found that a…
A developer has released Shipping Floor, an open-source example repo that demonstrates an agentic software factory capable of automatically rolling back a bad change without human intervention. The project uses three AI …
Cesar Aguirre published a piece advising people learning to code to adopt a single guiding rule when using AI. The article, framed as a short beginner-focused guide, argues for one core principle in how novice programmer…
A developer outlined a method for automating WhatsApp Business API replies using n8n and retrieval-augmented generation, connecting an LLM node to a vector database to ground responses in verified FAQ documents. The work…
A developer released a coding agent built from scratch using a custom Rust-based ML DSL, publishing the implementation under an MIT license with a demo video, sample code, and an Emacs org-mode literate programming docum…
NVIDIA Labs built an AI agent skill that translated all 24 public TileGym operators from cuTile Python and Triton-TileIR into cuTile Rust, reaching 99.5% of cuTile Python performance on average across roughly 40 GPU kern…
OpenAI's agentic software factory uses a risk classifier to route pull requests it labels "low risk" directly to production without human review when specialist reviewers find no blockers. The system's routing decision, …
AI-generated test suites can pass while the underlying feature is completely broken, because models trained on shallow human-written tests reproduce assertions that verify only that a function returns something rather th…
Nano Empire launched an open-source MCP gateway that combines x402 micropayments on Solana USDC with agent-to-agent (A2A) routing, charging a base toll of $0.01 per call. The gateway reports a p99 proxy overhead of 0.03m…