Claude Code reads AGENTS.md only when no CLAUDE.md, .claude/CLAUDE.md or CLAUDE.local.md exists in the working directory or any parent directory, and until version 2.1.281 the loader was gated behind …
Anthropic is rolling out a redesigned Claude Projects feature to selected Pro and Max subscribers using Claude Code cloud sessions, with existing web and desktop Projects users excluded from the initi…
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 it…
Amazon called for "rigorous testing and strong safeguards" before new AI models are released, with an Amazon spokesperson saying "We don't see it as a choice between progress and safety," but the comp…
Amazon said on September 17, 2026 that AI models should be released only after rigorous testing and with strong safeguards, taking a middle position between labs urging caution and executives dismissi…
OpenRouter introduced in-region routing that filters API requests to provider endpoints physically located in a specified region, failing closed with an error rather than falling back to an out-of-reg…
A new Python library called litelm extracts the core routing and message-translation functionality of litellm into roughly 2,900 lines of code with just 2 dependencies, openai and httpx, dropping the …
OpenAI released GPT-6 Astra on September 3, its first flagship model to ship with computer use as a core capability and the first pre-trained on more than 100,000 GPUs at its Stargate site in Texas. T…
A developer demonstrated how to orchestrate a multi-agent system in .NET using the Agent-to-Agent (A2A) protocol, converting remote agents into AIFunction tools for an LLM-based orchestrator. The proo…
TauricResearch released TradingAgents v0.4.0, a multi-agent LLM trading framework, with look-ahead and point-in-time fixes across FRED macro, social sentiment, and decision-log memory, plus GPT-5.6 an…
Neo4j's Director of Engineering demonstrates using the company's new Document Intelligence tool to convert unstructured PDFs, such as a history assignment on the Swedish-Danish war of 1657–1658, into …
A developer has released btp-guard, an open-source Python package that performs in-memory AST-based safety checks on code blocks generated by local LLM agents before execution. The tool parses Python,…
A developer tested ohmyaistaffs, a self-hosted, single-binary AI tool that claims to turn plain-language requests into compiled, tested applications. The tool uses a team of AI agents (analyst, design…
An AWS Labs sample for evaluating AI agents, Agent-EvalKit, uses the same Anthropic Claude model as both the judge and the subject in its QA example, a design choice that is not disclosed in the repos…
Anthropic on August 25 unified memory across Claude chat and Cowork, making all memory entries readable, editable, and deletable, with sensitive categories opt-in, and introduced a memory tool for dev…
A developer known as TokenOps on AWS has released three open-source packages—sayay-guard, styrr-llm, and tinkuy-agent—that together form what they call an 'AI Harness,' a set of traditional middleware…
Experiential Labs released Experiential, an open-source gateway and router for AI agent workflows that unifies hosted, BYOK, and local models behind an OpenAI-compatible API, with features for control…
A developer released Z, a minimal agentic coding harness for the terminal that supports 26 providers via LiteLLM, including Z.AI, DeepSeek, Anthropic, OpenAI, Ollama, Bedrock, Copilot OAuth, and OpenR…
FinOps, traditionally focused on cloud infrastructure costs, must now account for AI token spend, which behaves differently from conventional cloud costs. The author explains that token usage is meter…
Backboard, an AI startup, emphasizes that benchmarks should serve as tools for improving products rather than trophies for marketing. The company published an R-CLI result of 84.3% on Terminal Bench 2…