OpenCode, an open-source AI coding tool, disclosed a security breach affecting 1.4% of users of its OpenCode Console platform, where some store API keys for AI services. The company described it as a large-scale distillation attack and notified affected users by email, while developers reported unexpected charges on OpenAI, Anthropic and Google AI accounts, some exceeding $1,000. Anthropic and Google blocked exposed keys, OpenAI worked with OpenCode to restore access and refund credits, and OpenCode said refunds for unauthorized charges are underway.
techcrunch.com
· 2026-10-19
OpenCode, an open-source AI coding agent, disclosed that a security breach exposed stored API keys for 1.4% of its Console users who had linked external AI providers such as Anthropic, OpenAI and Google. The project maintainer said affected users were notified by email, and several reported unauthorized charges, including one case exceeding $1,700 overnight, along with suspended Google Cloud projects. Co-founder Dax Raad said the attack used AI agents against OpenCode's systems for at least 48 hours before being detected.
bleepingcomputer.com
· 2026-10-19
OpenCode said it suffered a security breach described as a large-scale distillation attack, which affected 1.4% of its Console users. The company notified affected users by email and says the incident is still ongoing, so further details are not yet available. OpenCode stated it is working with Anthropic, OpenAI, and Google to address the issue.
twitter.com
· 2026-10-17
OpenCode has launched version 2.0, described as a significant overhaul of the platform built using data from millions of daily users. The update includes a range of new features, performance improvements, and bug fixes, with several user-facing changes highlighted as particularly impactful.
anoma.ly
· 2026-10-14
A developer reports using DeepSeek 4.1 Flash heavily across a dozen projects for about a month, saying it performs comparably to models like Opus in daily work and conversation without a noticeable quality gap. The model is paired with a $10/month OpenCode Go subscription, making usage effectively unlimited, with typical sessions costing under $1.
dgt.is
· 2026-10-08
A tech essay describes a trajectory where software companies increasingly wrap their operations around large language models, moving from engineers pairing with coding agents to entire teams triggering and reviewing background agents, and eventually to agents proactively deciding work themselves. The author terms this evolving structure a 'harness' — the infrastructure, interfaces, and state built around a stateless model — and suggests most SaaS businesses are already on this path, whether they recognize it or not.
blog.sshh.io
· 2026-10-02
Drawgent is a new open-source utility that connects existing installations of Claude Code, Codex or opencode agents to a live Excalidraw whiteboard. Users can request diagrams via a chat panel or annotate a drawing with an 'AGENT:' note, and the connected agent reads the canvas, makes edits, verifies the result, and marks the task done. Setup runs a one-time check per agent, installs ACP adapters and, if needed, a headless Chrome renderer, storing configuration locally.
tangled.org
· 2026-09-26
RTK, a popular tool with over 79,000 GitHub stars that compresses terminal output before AI coding agents read it, has been marketed as a way to cut AI coding costs, with one viral post claiming up to 60% token savings. But independent benchmark testing using Terminal-Bench 2.1 across 1,740 task attempts found mixed results: costs dropped 5% for one model setup but rose 5% for another, contradicting the widely shared savings figures.
quesma.com
· 2026-09-11
A developer outlines a workflow for running local large language models on an Apple MacBook Pro M5 with 48GB RAM, combining Ollama for model management, OpenCode as the development harness, and Docker's sbx sandbox tool for isolation. The setup uses models like Qwen 3.8 27B and Gemma 4 31B, pulled via Ollama and configured through a custom sbx kit for each project.
tensorsandtokens.com
· 2026-09-11
A developer ran the same prompt—building a self-contained sci-fi hangar scene with Three.js, including hovering drones, animated lights, and camera paths—across 10 combinations of AI models (including GLM, Luna, SOL, Astra, and Qwen variants) and coding harnesses like Codex, OMP, OpenCode, and DSH. The test tracked metrics such as completion time, token usage, tool calls, error rates, and whether the model verified its own output by opening the file in a browser and checking screenshots.
alvins82.github.io
· 2026-09-08
GoKawiil