Anthropic.txt
Anthropic has deployed two new egress gateway certificate authorities for its sandbox environments, with separate production and staging CAs valid through 2036. The production CA, identified by serial…
Anthropic has deployed two new egress gateway certificate authorities for its sandbox environments, with separate production and staging CAs valid through 2036. The production CA, identified by serial…
A developer has created eval-app, a tool that connects to a running Clojure application's nREPL to evaluate code for inspecting app state, querying databases, or debugging issues. The tool accepts Clo…
A developer has created a zero-dependency GitHub Issue poller designed for multi-agent coding teams. The Node.js script, named gh-agent-watch.js, monitors a repository for issues labeled with specific…
A developer has created a "triple agent" code review tool called "code-review-turbo" that runs Cursor Bugbot, a Claude sub-agent, and Codex in parallel on a pull request, then cross-references all fin…
The PUBLIC LIGHTHOUSE CORE v1.7 runtime has been released, adding two new sublayers to Layer 3 (State Validation): the Orientation State Register (OSR) for spatial frame and basis tracking, and Narrat…
A developer has released the Maintainer-Wiki Kit, an agent-agnostic tool that uses an LLM to automatically create and maintain structured documentation for open-source scientific software projects. Th…
Cloudflare Workers developer Think has built an opinionated reasoning engine that treats AI interactions as durable, actor-like processes rather than simple model calls. The system uses Durable Object…
A developer has published a verified pricing and setup guide for AI coding tools, comparing free and paid options for students using Linux, macOS, or WSL. The guide recommends Google Gemini CLI for ze…
A developer expanded their AI-agent security benchmark from 10 to 16 scenarios, revealing that Claude Code Sonnet 4.6 scores +9 out of 16 while Haiku 4.5 scores only +3. The original tie between the t…
A developer has created a Google Apps Script that automatically drafts polite replies to recruiter emails when the user is not job searching. The script runs every five minutes, scans Gmail inbox thre…
A developer created a Python script that copies a Weights & Biases saved-view template from one project's workspace to another, preserving all sections, panels, workspace settings, and runset configur…
Claude Code reads CLAUDE.md, not AGENTS.md, contrary to claims in third-party guides. Anthropic documents two methods to make Claude Code use AGENTS.md: importing it via @AGENTS.md in CLAUDE.md, or sy…
A developer has released a drop-in replacement chat template for Qwen/Qwen3.6-27B that fixes six critical bugs affecting open-source agentic coding harnesses. The fork addresses issues including multi…
A developer has published a system prompt and IDE configuration guide designed to resolve terminal hanging, broken token parsing, and execution loop issues when running Google's Antigravity IDE on Win…
Developer Nixel released MessageBuilderV4.3.js, an advanced WhatsApp interactive message builder that creates buttons, carousels, native flows, and AI-rich response payloads using the Baileys library.…
A developer has published a conceptual blueprint for AURORA, a low-energy cognitive organism architecture that operates without transformers or token prediction. The system uses sparse predictive micr…
An engineer has developed the LLM Research Manager, a deterministic project-state layer designed to maintain the live epistemic state of long-horizon research projects using agents and large language …
A developer has created a "Dogfood Loop" setup wizard for Claude Code that automates browser-based application testing with an autonomous exploration and auto-fix loop. The wizard detects project conf…
A developer has published a free, markdown-only study workbook for the GH-600 certification exam, "Developing in Agentic AI Systems." The guide is organized around the exam's six official domains, cov…
An engineer has developed a workflow packaging audit prompt that systematically identifies recurring manual tasks suitable for automation. The prompt prioritizes evidence from recent Codex sessions, m…