After 100-plus hours with both Pi and OpenCode
After 100-plus hours testing both coding agents, Pi's context overhead is under 1,000 tokens per request versus OpenCode's roughly 6,900 tokens, a 7x difference that can waste thousands of dollars in …
After 100-plus hours testing both coding agents, Pi's context overhead is under 1,000 tokens per request versus OpenCode's roughly 6,900 tokens, a 7x difference that can waste thousands of dollars in …
A developer's comparison of open-source coding agents Pi and OpenCode after 100+ hours of real use found a dead tie in features but distinct trade-offs. Pi, built by Mario Zechner, excels in efficienc…
An anonymous AI model called Ox Alpha, listed on OpenRouter under the provider name 'stealth' on August 20, is offering free access with a 1,048,576-token context window and reported strengths in codi…
A benchmark comparing AI coding harnesses—Codex, JCode, Pi, OpenCode, and DSH—using the same prompt and the DeepSeek V4 Flash model produced completely different results on the Ship Simulator Harness …
A confirmed bug in OpenAI's Codex CLI is inflating AWS Bedrock bills by up to 10x for developers running agentic coding sessions, with one developer documenting $1,182 in charges over four days on a w…
Developer Dext4r (Zaxs) has released env-guard, an open-source tool that prevents AI coding agents from exposing sensitive credentials like API keys. The tool works by having agents reference secrets …
A stealth model named Ox Alpha appeared on OpenRouter on August 21 under the provider name 'stealth' with no company attached, offering a 1,048,576-token context window, 131,072-token maximum output, …
OpenCode Go, a new low-cost subscription service from OpenCode, offers 8× usage limits for Hy3 for a limited time, priced at $5 for the first month and $10/month thereafter. The service provides relia…
NestMux, a desktop application for running coding agents in parallel, has addressed the lack of native support for split-pane agent teams on Windows. The tool provides isolated home directories, git w…
OpenCode founder Jay V reported on X that the company's $10-per-month Go subscription surpassed 301,000 active subscribers, with a dashboard showing 301,018 accounts and 14.6% growth. At standard pric…
Career-ops, an AI job-search pipeline that runs inside coding CLIs and has amassed 66,000 GitHub stars since its April launch, refuses to auto-apply to jobs, instead filtering listings and requiring h…
Vercel's AI Gateway has added DeepSeek V4 Flash Vision Experimental, a model that accepts images alongside text for tasks like describing pictures, reading screenshots, and analyzing charts. The model…
Bruin Data released a free, open-source method to build an AI context layer for data warehouses, using the Bruin CLI and an AI coding agent to generate YAML files that describe tables, columns, and da…
AI coding agents have made building software cheap, but AdaL's developers found that cheap implementation increases the risk of building the wrong thing. After building a benchmark first, they discove…
A software engineer used AI coding assistants, including Claude and open-weights models like Kimi K3 and DeepSeek v4 Pro, to build a custom Casio-style watch face for the $27 PineTime smart watch, pub…
Unity, a lightweight CLI tool created by Nicolas Akf, synchronizes agent skills and rule files across coding agents including Codex, Orion, Claude Code, Cursor, and OpenCode, using a single source-of-…
Evepad, a new open-source IDE for building and shipping eve agents, launched on Hacker News, providing a local dashboard and build harness that integrates with Vercel, eve CLI, and OpenCode. The tool,…
NVIDIA open-sourced NOOA, a Python agent framework that treats agents as single Python classes, with version 0.0.8 under Apache 2.0, supporting Python 3.12–3.13. The GitHub repository has surpassed 1,…
The HTB-Challenger Benchmark evaluates large language models' ability to find and exploit security vulnerabilities using selected Hack The Box challenges of varying difficulty, according to the benchm…
UnlimitedNIM, a streaming reverse proxy for NVIDIA's NIM free tier, eliminates 429 rate-limit errors for coding agents by enforcing a 40-request-per-minute sliding window and priority queue, with test…