AI Briefing#coding-agent
The latest AI and developer news about #coding-agent, with the original source and a short summary.
The latest AI and developer news about #coding-agent, with the original source and a short summary.
Kimi K3 has been officially integrated into GitHub Copilot and is now available for use.
Meta has released the beta version of Muse Code, a terminal agent designed to perform large-scale coding tasks.
Meta's Muse Spark 1.2 has been added to Vercel AI Gateway.
GitHub proposed a method to split massive AI-generated PRs into hierarchical stacks to facilitate easier review and merging.
MirrorCode evaluated long-horizon autonomous coding ability and revealed Claude Opus 4.7's results.
Qwen has unveiled the 2.4T-parameter Qwen3.8-Max and announced an upcoming open-weight release.
Qwen 3.8 Max is now available on Vercel AI Gateway.
On 111 SWE problems, Fable 5 recorded the highest resolve rate at 64.5%.
DeepSeek V4 Flash now runs by default with new weights on AI Gateway.
AI Gateway has increased processing capacity for both the paid and free versions of Laguna S 2.1 by 10x.
Cursor redesigned its development environment so cloud agents can directly run and verify code.
An extension tool that adds an autonomous experimentation and optimization loop to the AI coding agent pi.
An experimental decompiler called Kuna was unveiled that uses LLMs to autonomously improve its own performance.
We introduce ENPIRE, an autonomous research framework in which a coding agent learns and improves manipulation policies for real robots on its own.
JetBrains Rider 2026.2 has launched features that give coding agents access to the IDE's context and verification loops.
Anthropic's Claude Opus 5 has launched on AI Gateway, bringing enhanced agentic coding performance.
LangChain has released the 'Eval Engineering Skill,' which automatically generates agent evaluations (evals) by analyzing repository structure and execution traces.
zerostack, a Rust-based coding agent that limits memory usage to around 16MB, has been released, making it over 20 times lighter than JavaScript runtime-based tools.
OpenWiki 0.2 now supports Google Cloud's OKF standard, improving the structuring of codebase documentation.
By using a tiered architecture where a cheap model extracts context and a frontier model writes the final patch, the approach captures both cost efficiency and performance at the same time.
ReactBench v1 comprehensively evaluates coding agents' React-writing ability using the React Doctor validator, which has over 400 rules.
Open Interpreter is a coding agent optimized for low-cost AI models, delivering top performance through a Kimi K3 Rust implementation.
xAI has open-sourced the source code of Grok Build, its coding agent and TUI.
LangSmith visualizes the execution process of various coding agents as standardized Traces, helping with debugging and performance improvement.