A developer built DatePilot, a full-stack private AI date planner for couples that combines a deterministic Python planner with an open-weight Gemma model served through Ollama. The app, built with Re…
Imbue released Sculptor on October 1, a free, MIT-licensed open-source tool that runs each parallel AI coding agent in its own Docker container to eliminate port conflicts, missing .env files, and dep…
A developer A/B-tested nine popular AI coding-agent skills against Sonnet 5.5 and Haiku 4.5 using Anthropic's claude plugin eval, running 19 test cases three times per arm, and found four of the nine …
A developer comparison of OpenAI Codex and Anthropic's Claude Code finds both tools priced at $20 and $200 per month but built differently: Codex bundles into ChatGPT with GPT-5 and o3 models, while C…
Thirds.ai launched as a template-based tool that generates on-brand images and PDFs, with the company claiming it is trusted by 140+ teams that ship branded files weekly. The product lets users start …
Cantina released apex-flash-1, an open-weights cybersecurity model fine-tuned from GLM-5.3-Flash with 321 billion total parameters, in an October 4th post by co-founder and CEO Harikrishnan "Hari" Mul…
Rhun, a code editor written in x86-64 assembly by creator Vladimir Shvedov, shipped v0.16.2 on October 1 with a 980KB binary and 7.9MB of idle RAM, versus VSCode's 291MB, according to Hacker News test…
Hob launched as an independent workspace for macOS, Windows, and Linux that runs Claude Code, Codex, OpenCode, and Grok Build side by side on a user's own accounts, with a first month free. Hob states…
A new open-source project called 16agents lets AI coding agents take a 16-type personality test themselves and write their own report.html, scoring their self-described behavior against four hidden tr…
A hands-on comparison of ChatGPT's Codex and Anthropic's Claude Code on a mid-size TypeScript repo found Claude Code finished all five tasks unattended, caught 25 of 30 seeded bugs, and averaged 8.7/1…
A developer reports that GPT-6 running in Codex repeatedly violates task scope on large production repositories, expanding simple requests into unrequested architecture, validation and repository chan…
OpenMausBot, a local-first multi-agent platform from developer milind-soni, has reached v0.1.95 with 3,992 GitHub stars and its last commit 2 hours ago, two months after the repository launched under …
Dray v0.26.0, a free Apache-2.0 macOS app from monorepo-labs, runs multiple AI coding agents — including Claude Code, Codex, Grok, pi, and fx — in a single window using existing subscriptions. The app…
A developer published instructions for stripping OpenAI Codex's built-in confirmation layers on macOS, disabling the bundled computer-use skill, the Chrome plugin's confirmation and browser-safety doc…
Dropalltables released Valet, an MIT-licensed self-hosted platform that runs cloud coding agents such as Cursor cloud agents and Amp Orbs on a user's own Linux server or Mac via Docker Engine 24+ and …
Blend Bunjaku released optimAIzr, an open-source local CLI that profiles Claude Code, Codex and custom API calls to find wasted tokens and quantify savings, first presented September 13, 2026 and open…
AgentMachinist 0.19.0, released on PyPI, is a controller that takes a development task from intent to a reviewed local change by coordinating coding agents Claude Code, OpenCode, Pi, Codex, or Goose, …
Measuremy.site launched Agentlytics, a cookieless website analytics product that exposes 12 tools over the Model Context Protocol so coding agents such as Claude Code, Cursor and Codex can read traffi…
Memorable launched a memory layer that stores how an agent completed a task and replays the procedure when a similar task returns, with storage kept on the user's side and consent enforced fail-closed…
Developer JustasMonkev released lazy-clean, a standalone skill package for coding agents that injects a YAGNI-based "lazy-senior-dev" ruleset at session and subagent start and runs a heuristic slop ch…