Paperclip, an MIT-licensed open-source management layer for AI agent teams, has reached 86,000 GitHub stars by treating agents like employees with roles, reporting lines, and monthly token budgets, ac…
A developer built Mochi, an open-source Linux desktop companion with a real behavior state machine, persistent memory, and context awareness, positioning it as a more capable alternative to OpenAI's C…
Developer Junchen Pan released OnPoint, an MIT-licensed skill that installs into 12+ AI coding agents including Claude Code, Cursor, and Codex to make them emit less prose and more actionable steps. P…
Rival AI assistants from SpaceXAI, Anthropic and OpenAI degraded in the same September morning window — Grok down three and a half hours from 6:30 a.m. PT, Claude logging elevated errors across multip…
A personal LLM user reports that Qwen3.8-27B running locally via llama.cpp on an RTX 5090 laptop GPU with 24 GB of VRAM now handles Q&A, coding, sysadmin and web research without a cloud provider, del…
Ryan Merket reported a ninth-place standing on the FLARE-On 13 reverse-engineering challenge leaderboard with all nine numbered challenges solved, according to a live leaderboard screenshot posted to …
A developer built Agent Pigeon, an open-source CLI that reads local Claude Code and Codex session history after a run and condenses it into a short "Flight" report of edits, verification checks, and f…
A developer built ContextForge, a tool that snapshots a repository's file tree and key files to draft agent instruction files such as .cursorrules, CLAUDE.md, AGENTS.md and .github/copilot-instruction…
Codex v0.80.0+ now uses the Responses API as its sole inference interface and no longer supports the Chat Completions API, according to x-cmd documentation. The x-cmd tool offers `x codex <provider>` …
A developer built an experimental harness that records what an AI coding agent actually attempts inside its execution environment, rather than trusting the agent's own report of what it did. The setup…
OpenAI's Codex service experienced a 401 authentication outage, and the company said logging in via API key would unblock access at that time. OpenAI reported the availability metrics at an aggregate …
A developer tutorial walks through building an Agent Skill for Claude using a single SKILL.md file, the open standard Anthropic launched in October 2025 and published at agentskills.io on December 18,…
Aidash released Cockpit 0.1.2, a free macOS app that runs Anthropic's Claude Code and OpenAI's Codex side by side in one window, reading the transcripts those tools already write to disk rather than r…
OpenAI merged a pull request into the public Codex repository on September 25th that adds an HTTP client crate letting Codex agents on a Mac, in the cloud and on a server exchange messages through a r…
PromptPad 0.1.0, a lightweight native editor for writing long coding prompts, was released as a macOS Apple Silicon preview by developer aaravchour. Built with C++20, Qt 6 Widgets, upstream Scintilla …
Agnostic-ai released version 0.68.1, which fixes global sync so it respects target filters, and users of global hooks or skills should run `agnostic-ai sync --global` to apply the corrected output. Th…
GPT-6 Astra led a new 71-task biopharma benchmark with a 70.4% mean score and fully passed 8 tasks, while GPT-6 Sol placed fifth at 54.3% and DeepSeek V4.1 Flash fourth at 57.0%, according to results …
A developer built sdlc-playbooks, an open-source, file-based delivery procedure for agentic coding that runs in both Claude Code and Codex from a single source. The workflow replaces prompt-based beha…
A developer reports that OpenAI's Codex subagent orchestration has become reliable enough to design development workflows around, after earlier problems in which parent agents would duplicate delegate…
Dev.fast released Whiteboard, an open-source desktop app that connects coding agents such as Claude Code and Codex to a shared visual workspace where agents draw architecture, sequence diagrams and tr…