Developer tools news — AI coding assistants, IDEs, CLI tools, APIs, and productivity tools for software engineers. GitHub Copilot, Cursor, and more.
Developer Vidit Raj released Pebble, an open-source 25-million-parameter language model built entirely from scratch that can call tools such as a calculator or weather API, publishing the code on GitHub. The build walks …
A developer reports that OpenAI's Codex agent spent six days working on the goose codebase without completing a single run, while GPT-5.6 Sol driven from goose's own engine performed well on the same repository in the sa…
A developer rebuilt a Forge manifest major-version predictor after discovering their original tool was built on a misattribution: the 3.x to 4.0.0 bump of Sentinel Vault was triggered by both the new llm module and a new…
GitHub made its improved Copilot code review experience generally available, adding a refreshed overview comment that groups findings into Open, Resolved since last review, and Previously missed, plus titles on each revi…
Cayu released a production agent runtime for building and operating AI agents in Python, according to its GitHub repository. The framework gives applications full control over context assembly, model invocation, tool acc…
Sokit released an open-source harness that lets System One models — fast, calibrated decision models that cannot generate text, call tools, or fetch data on their own — operate as full agents, according to the project's …
The Devin team released 15 latency-focused agent demonstration applications built on Jev, published in a GitHub repository, according to the repository. The demos cover dispatch, search, voice interaction, and swarm coor…
A developer outlines a technique for building zero-hallucination neuro-symbolic AI in Node.js by replacing scattered object-oriented graph structures with contiguous typed-array buffers. The approach flattens graph topol…
Vercel expanded its Spend Management feature to Enterprise Flexible Commitment plans at no additional cost, after previously making it available on Pro. Teams can set a per-billing-cycle budget that triggers email notifi…
A developer reports that Google's Gemini models inside the Antigravity coding tool frequently ignore instructions, perform unrequested actions, and read outdated documentation, behavior that persisted even when the same …
Anthropic shipped Claude Code version 2.1.277 on September 18, adding native fallback support for AGENTS.md project instruction files so the tool reads the community format whenever a project lacks its proprietary CLAUDE…
A developer is building Gagarin Cloud, a platform aimed at simplifying web deployment in response to the complexity and cost of conventional cloud infrastructure. The developer argues that mainstream clouds have become b…
Anthropic launched a beta of redesigned Projects in Claude Code that lets users run multiple parallel Claude Code cloud sessions on a single project, each on its own git branch and repo copy, coordinated by a coordinator…
Anthropic added AGENTS.md support to Claude Code starting in version 2.1.277, according to Thariq Shihipar. In folders with no CLAUDE.md file, Claude Code will now check for and use AGENTS.md, a feature built on the comp…
QAInsights published a tutorial on building a Spring Boot Task Management REST API using Qwen Code, Alibaba's open source coding agent. The post covers installation, writing a requirements file, generating the entity, co…
NVIDIA released AIPerf, a ground-up rewrite and designated successor to GenAI-Perf, as a multiprocessed LLM inference benchmarking tool that coordinates worker processes and record-processor services over ZMQ to avoid th…
GitHub will deprecate six models across all GitHub Copilot experiences — including Copilot Chat, inline edits, ask and agent modes, and code completions — on October 19th, 2026. The retired models are Gemini 3.7 Flash, G…
A developer argues that AI-assisted Spec Driven Development spec files should not be committed to a codebase once the code is implemented, since the code itself becomes the unambiguous source of truth. The post surveys p…
Rijul, a developer building the AI code review tool LiveReview, outlined why vector search alone is insufficient for retrieval-augmented generation systems and argued for hybrid retrieval. The writeup describes combining…
A developer built a model router for OpenCode that uses the TypeSafe AI Jev model via OpenRouter to classify coding tasks by coordination, uncertainty, and consequences, then routes each request to either a powerful or w…