Automated change intelligence

Anthropic changes radar.

Automated source-backed change intelligence for Anthropic: releases, articles, model/API signals, and related decision pages. The page updates from auto-published radar items and decision candidates; weak coverage stays noindex.

Articles
24
auto-published
Candidates
16
decision graph
Sources
40
distinct URLs
Updated
Nov 20, 2026
indexable

Recent source-backed updates

24 items
AgentsScore87

Grajo: Self-Hosted Agentic Framework and MCP Platform

Grajo is an open-source, self-hostable agentic framework and Model Context Protocol (MCP) platform. It allows users to build and run AI agents with persistent memory, research capabilities, and P2P sharing, while also serving as an MCP platform to connect existing AI clients like Claude Code and Cursor.

Nov 20, 2026github.com
AI CodingScore87

Mirador: Desktop App for Visualizing Coding Agent Interactions

Mirador is a new desktop application designed to enhance the interaction between developers and coding agents. It provides a visual canvas alongside conversations, allowing agents to draw diagrams, mockups, and code tours, and enables users to interact with agent suggestions through visual previews.

Nov 20, 2026github.com
RAG & SearchScore68

BurnyCoder Releases ArcticSwarm Folder RAG Dataset

BurnyCoder has released the ArcticSwarm-folder-rag-results dataset on Hugging Face, containing evaluation outputs, metrics, and reports for adapting the ArcticSwarm framework to Retrieval Augmented Generation (RAG) over local folders using Claude Haiku 5.5. The dataset is intended to support research and development in RAG systems.

Nov 20, 2026huggingface.co
AI CodingScore87

Termaxa: AI Agent Shell Command Safety Gate

Termaxa is a new Rust binary that acts as a gatekeeper for AI coding agents interacting with the shell. It previews command consequences, takes backups, and enforces policies before execution, aiming to prevent accidental damage from agents like Claude Code, Codex, Cursor, and Copilot.

Nov 19, 2026github.com
AI CodingScore86

aSPARK: Agile AI Product Team Process for Claude Code

The aSPARK project introduces a gated agile delivery process designed for AI product teams using Claude Code. This framework structures development through distinct phases: Specify, Plan, Act, Review, and Keep, with each stage requiring a quality gate before proceeding. It aims to provide a reviewable paper trail for feature development within a project.

Nov 19, 2026github.com

Related decision candidates

CandidateKindAccessFitSource
paperclipai/papercliprepoOpen sourceScore88github.com
ruvnet/ruflorepoOpen sourceScore87github.com
Anthropic Claude API servicePaid APIScore83platform.claude.com
Fzkuji/OpenProgramrepoOpen sourceScore81github.com
ogulcancelik/herdrrepoOpen sourceScore79github.com
stablyai/orcarepoOpen sourceScore79github.com
morluto/rearepoOpen sourceScore77github.com
Cotal-AI/CotalrepoOpen sourceScore75github.com
pipeshub-ai/pipeshub-airepoOpen sourceScore74github.com
anthony-chaudhary/dos-kernelrepoOpen sourceScore72github.com
swarmclawai/swarmclawrepoOpen sourceScore72github.com
griffinwork40/agent-afkrepoOpen sourceScore72github.com