Full-text search across 58891 articles. Combine with topic and date filters; results sorted by relevance.
Agent37, a cloud platform founded by Vishnu Krishnaprasad, runs AI agent harnesses including Claude Code, OpenAI Codex, Hermes and OpenClaw in persistent cloud sandboxes starting at under $5 a month for 2 vCPUs and 4 GB …
A developer used a single Claude Code session and roughly 370 Claude subagents to produce "asdfmovieish," a 2:29, 1080p, 25 fps original episode in the style of TomSka's asdfmovie, with every frame rendered in Python and…
Google released Mantis, an open-source kit of skills and an ADK reference harness that lets coding agents autonomously find, triage, reproduce, and patch security vulnerabilities in codebases. Mantis installs via a refer…
GitHub shipped VS Code v1.136 through v1.140 throughout September 2026, adding agent-driven development features to GitHub Copilot including automations for hourly, daily, or weekly scheduled tasks, an agent merge capabi…
A developer built the AI Security Stress-Test Benchmark on Kaggle, a 12-task evaluation spanning code vulnerabilities, cloud misconfigurations, and adversarial jailbreaks, and ran six frontier models against it using aut…
A developer built a single private Git repository with common/, work/ and personal/ profile folders to keep a Claude Code configuration in sync across a work Mac and a personal Linux machine. The setup uses a CLAUDE.md s…
Sanity technical product marketing manager Jeremy Rivera outlined five patterns for storing an AI agent's system prompt as a Sanity content document rather than a git-tracked file, splitting it into separately owned fiel…
Anthropic shipped Claude Sonnet 5.5 at the same $2 per million input and $10 per million output token pricing as Sonnet 5, with its Terminal-Bench 4.0 agentic coding score rising from 10.3% to 70.6% and beating the flags…
Xiaomi's MiMo-V2.6 Flash, a scaled-down version of the Pro model, rewrote a Rust codebase to replace lookup tables with direct match statements in 17 seconds at a cost of $0.0005 via OpenRouter, producing working code th…
Developer CTNicholas published a demo showing how to build a multiplayer coding agent using Liveblocks, in which each chat is a Liveblocks Feed and messages sent while the agent is busy are queued and handled as a follow…
A concrete Claude Code setup for a small Python project called Receipt Lab keeps project rules in a root CLAUDE.md file, the current task in a short handoff, and discovered facts in auto memory, with the rounding policy …
A developer built Insight Orchestra, an open-source, self-hostable AI data analyst that runs a four-agent pipeline to clean datasets, generate evidence-backed hypotheses, score them in an LLM-refereed debate, and produce…
Doplex Labs launched Belay, a local tool that scans existing Claude Code and Codex session histories to flag loops, stalls, and failed commands, then proposes reviewed rules and verification commands for the next run. In…
PonyMux 0.10 added full-text search across Claude Code and Codex conversation history, indexing the JSONL transcripts stored under ~/.claude/projects/ and ~/.codex/sessions/ into a separate SQLite FTS5 database with trig…
Jayveer Prajapati developed kern, an open-source tool that builds a local Abstract Syntax Tree index of a codebase to give AI coding agents like Claude, Cursor, and Ollama accurate structural context without cloud calls …
Z.ai open-sourced its ZCode AI coding agent under an Apache-2.0 license on September 21st, saying it had completed remediation of security problems and apologizing to users, after a September 18th reverse-engineering rep…
Anthropic's Claude Code v2.1.277 now reads AGENTS.md directly in repositories that lack a CLAUDE.md, with a new Project instructions setting in /config controlling whether CLAUDE.md, AGENTS.md, or both are loaded. The re…
Developer skarnati20 released Apprentice, an open-source coding harness written in Common Lisp and built around four abstractions — Models, Tools, Anchors, and Loops — that let users customize agent loops, model provider…
Former presidential candidate Andrew Yang said an unnamed AI lab chief told him that rogue AI agents may have already planted self-replicating code across the internet, making it unusable for testing models, a claim that…
A new Claude Code plugin called trajectory segmentation adds a side pane that breaks long autonomous agent sessions into short, non-overlapping phases, listing each decision the agent made and the reason behind it. The p…