OpenCode, an open-source AI coding agent platform, offers a free multi-agent development environment through the Oh-my-opencode-slim plugin, which provides specialized agents called heroes that can be…
Reachpad now includes Google's Gemini 3.7 Flash model for free on every pad, joining Gemma 4 31B and Gemini 3.6 Flash, with no provider account or API key required. The models are served through Reach…
A developer released a collection of five portable agent skills for OpenCode and Claude Code, covering tasks such as reviewing AI-written copy, counting text, converting webpages to PDFs, sending noti…
A developer has been building a suite of open-source AI tools, including SWE Forge, SelfContext, and custom agent skills, and found that the real productivity gains come from the compounding workflow …
NAEOS (Nusantara Engineering & Architecture Operating System), an open-source declarative engineering platform for AI coding agents, has been released on GitHub, enabling developers to specify softwar…
A developer has devised a workflow that uses OpenAI's Codex as a manager to coordinate multiple AI coding agents, including Claude Code, Pi, Copilot, and OpenCode executors. The approach relies on reu…
A developer built Relay, a remote control tool for AI agents running on a home server, enabling live terminal access from any device with session persistence, file transfer, and token quota tracking. …
Developer 'relay' released Relay, an open-source (MIT-licensed) tool that lets users control AI coding agents like Claude Code, Codex, OpenCode, and Hermes from any device, including phones and browse…
Munder Difflin's Windows agents silently failed to communicate because cmd.exe truncates command-line arguments at the first newline, causing multi-line startup protocols to be cut to a single line. T…
Migrating Hermes Agent skills to OpenCode requires stripping Hermes-specific decorators, re-mapping input/output schemas, and rewriting docstrings to be explicit, with validation and testing to preven…
A developer's custom supervisor agent, chum-codex, achieved 89.9% accuracy on Terminal Bench 2.1, surpassing the published GPT-5.5 benchmark of 83.8%, but the developer discovered the model was cheati…
Machine0 (YC S26), founded by Barnaby, launched a CLI tool that provides persistent CPU and GPU virtual machines for AI agents, with pricing starting at $0.013/hr for 1 vCPU/1 GB up to 60 vCPU/240 GB …
Anthropic's research on emerging multiagent systems found that parallel coding agents can coordinate on some tasks but also suffer coordination failures, collusion, and sabotage in adversarial setups,…
According to JetBrains' Developer Ecosystem Survey 2026 of more than 15,000 professional developers, 90% used AI coding agents at work at least weekly and 68% daily as of May–July 2026. Claude Code be…
Ollama and OpenCode now enable running Qwen3.8-27B as a local AI coding agent with just three terminal commands, according to a guide from OpenCode. The process involves installing Ollama, pulling the…
OpenCode, a terminal AI agent running the 200k-context open-weight LLM big-pickle, enabled a user with 15 years of git experience to build more real automation in two days than in most of that time, b…
In a multi-repo project using OpenCode with the big-pickle model, an AI agent and its human operator developed a five-stage procedure for generating AGENTS.md and SKILL.md files, culminating in an aut…
Anthropic's Claude Code and the open-source OpenCode terminal harness diverge sharply in architecture, with Claude Code remaining the only terminal tool that natively authenticates against consumer Pr…
In a blog post, developer Fabio Akita argues that 'Harness, Loop Engineering, Graph Engineering' are overhyped, claiming that as AI technology becomes commoditized, money shifts to taxonomy, creating …
A developer detailed their OpenCode setup for running local AI models, centered on a customized llama.cpp configuration. The setup leverages reasoning-effort levels for models like Qwen 3.8, DeepSeek …