All published AI news and analysis.

Sibyl, a self-hostable knowledge graph, has released version 1.4.10. It provides cross-agent memory for AI coding tools like Claude Code, Codex, and Cursor, enabling shared knowledge across different agents.

Paperclip is an open-source application designed for managing AI agents at work, written in TypeScript. It recently had a fresh release, v2026.1005.0, indicating active development.

ACRYL (Agent Context Relay Yielding Lifecycles) has released version v0.2.4. This TypeScript project aims to provide a persistent workspace and canonical context for any coding agent, facilitating agentic development workflows.

The raw-cli project introduces a local coding agent designed for models with limited context. It offers composable tools, skills, hooks, and agents, accessible via a terminal REPL and a browser dashboard.

The AI SDLC Framework has released version sdk-typescript-v0.31.0, introducing a declarative governance framework for AI-augmented software development lifecycles. This open-source project, written in TypeScript and Go, focuses on AI governance and LLM-Ops.

In his Import AI newsletter, Jack Clark suggests that AI systems may be approaching recursive self-improvement (RSI) sooner than previously anticipated, potentially by 2027, due to advancements in AI research taste.

The cmuxlayer repository offers 10 public MCP (Model Context Protocol) tools designed for controlling cmux workspaces. It facilitates the management of AI agents including Claude, Codex, Gemini, Kiro, and Cursor.

AI Canvas Tauri, a local-first application for visual AI workflows, has released version v0.10.5. This update focuses on AI short drama, image/video generation, storyboarding, and asset management, integrating with tools like ComfyUI, AI agents, MCP, and Blender.

Teable is an open-source AI spreadsheet designed for business use, offering a low-code/no-code platform. It recently had a fresh release, indicating active development.

Bex is an open-source platform designed as an alternative to Render, enabling users to build and deploy applications from Git repositories onto their own infrastructure. It emphasizes AI-native capabilities, treating agents as first-class users.