Reflexio, a new learning platform for AI agents, claims to reduce task failure by 36% while saving more than 50% on tokens by turning user corrections and successful outcomes into reusable behavior ch…
An investigation has found that Anthropic's Claude Code Auto Mode, which uses a safety classifier to autonomously execute commands, is vulnerable to indirect prompt injection attacks, achieving a 60-8…
Anthropic's Claude Code tool result caching reduces token consumption by 40-60% in multi-hour sessions by storing and reusing file reads and shell command outputs, according to an article written with…
Firekeep, a self-hosted shared memory system, connects multiple MCP clients including Claude Code, Codex, Kiro, and OpenCode, allowing agents to preserve and recall context across sessions. On the 202…
A developer known as kltng has published a set of instructions, 'Playable Past,' that enables AI agents to transform historical sources into playable classroom games. The framework guides agents throu…
Anthropic reported elevated errors on Claude Code and Claude Cowork, according to a status page update. The incident affects users of these AI developer tools, and Anthropic is providing email and SMS…
Intel and ten contributors released 20 open-source Agent Skills for deploying and debugging AI models on Intel Arc and Arc Pro GPUs, packaged in the intel/gpu-ai-skills repository under the Apache-2.0…
Anthropic's Claude Code has been used by a developer for over a year, and they have developed a workflow that emphasizes planning and red-teaming before implementation. The workflow involves using the…
A developer reports that using AI coding agents like Claude Code and Cursor has dramatically accelerated their workflow, shifting from syntax-level debugging to describing the intended user experience…
AMD has released ROCm 10, marking the tenth anniversary of its open software stack, and made ROCm.AI generally available, claiming a 3.3x average inference performance improvement and 2.4x training pe…
A developer used Anthropic's Claude Code to reverse-engineer an undocumented vendor billing API in two days, turning roughly 40 exploratory HTTP requests into an inferred schema, a typed client, and a…
The proliferation of AI-assisted 'vibe coding' tools like Claude Code is democratizing software creation, reminiscent of the desktop publishing revolution sparked by PageMaker, the LaserWriter, and th…
CodeYam CEO and cofounder Nadia Eldeib published part 5 of her series on rebuilding her personal website with CodeYam and Claude Code, reporting the redesigned site is now live on a secondary custom d…
DeepModel AI released dmx, an open-source MCP server that adds configurable, gated loops to coding agents in Cursor, Claude Code, and Copilot, implementing a five-phase AI SDLC framework with human ap…
A developer reported that Anthropic's Claude Code significantly accelerated a four-week refactor merging several repositories, cutting the time by 2-3x and improving test coverage and code quality. Th…
Lanes Link, a new open-source tool from Lanes, provides a unified memory and skills layer for AI coding agents, allowing users to store context once and access it across different clients like Claude …
KHMS, a file-based long-term memory system for LLM agents, stores knowledge as immutable markdown cards in a git repository, with hook-driven recall and a propose-review-approve pipeline, and has been…
Conductor, a Mac app that runs Claude Code, Codex, and Cursor agents in parallel isolated workspaces, offers a free tier for local use, Pro at $50 per month, Teams at $60 per user per month, and custo…
Charlie Labs has launched daemons, standing agents that triage issues, update dependencies, and maintain documentation across GitHub and Linear without requiring prompts, with configuration stored as …
Meta launched Muse Code, a terminal-native coding agent, on 5 August 2026, built on the Muse Spark 1.2 model with a one-million-token context window and subagent orchestration for large repositories. …