OpenCode news
The latest OpenCode news, : LiteLLM 1.107.0 compromised, developer says release process was hijacked.
17 stories mentioning OpenCode since 15 September 2026, newest first, each with its sources and discussion. Follow to see new ones on your front page.
-
LiteLLM 1.107.0 compromised, developer says release process was hijacked
A study from the Hong Kong University of Science and Technology and collaborators compared several code‑generation models. Claude Haiku 4.5 asked for clarification on ambiguous prompts at a rate of 38.3% to 44.5%,…
1 sourcenote.com -
Coding agent harnesses triple token costs without boosting benchmark scores, study finds
Complex harnesses for coding agents inflate token bills by up to three times while barely improving benchmark performance over minimal setups, according to a study by researchers Liu and Han at Shandong University. The…
1 sourceThe Decoder -
Railway reports breach that may have exposed AI API keys
Railway, a US‑based PaaS provider, announced on October 21 that an external party accessed its encrypted environment‑variable store and may have read some contents. The intrusion, detailed in a breaking report on…
1 sourcenote.com -
Five free AI coding agents you can try in 2026
AI coding agents that let you explore repositories, edit files, run terminal commands, debug errors and execute tests are now reachable without paying for API credits. The guide highlights five options – OpenCode,…
1 sourceKDnuggets -
Vercel open-sources durable-harness to keep coding agent sessions alive after crashes
Vercel released durable-harness, an open-source npm package (version 0.0.x) under Apache-2.0 that stores each step of a coding‑agent turn in a durable log, allowing sessions to survive crashes and timeouts. The package…
1 sourceMarkTechPost -
OpenCode Console attack leaks API keys, leading to unauthorized charges
In mid-October, the online service for the AI coding tool OpenCode, called OpenCode Console, was attacked, resulting in the leak of OpenAI, Anthropic, and Google API keys stored by users. The attack affected 1.4% of…
1 sourcenote.com -
vLLM 0.31 adds constrained decoding for 100% tool-call accuracy
Ubicloud found that open-weight models like Kimi K2.6 and DeepSeek V4 Flash often fail to generate correct tool calls, with vLLM version 0.28 achieving only 92% schema accuracy for Kimi K2.6. This led to nonsensical…
1 source HN 47ubicloud.com -
OpenCode and Claude Code compared: open source flexibility versus Anthropic's easier tool
OpenCode is a free, open‑source AI agent harness that can work with almost any model – from free options like Space Bunny and Nemotron to commercial ones such as Claude, GPT and Gemini. To use paid models you must…
1 sourceZapier Blog -
Google Cloud AI Research open-sources Harness² recursive agent framework
Google Cloud AI Research released Harness², an open‑source recursive agent harnessing framework version 0.1.0. The framework adds eight editable harness components—system prompt, guardrails, memory, tool guidance,…
1 sourceMarkTechPost -
Sphinx adds git hook that quizzes developers on AI code before push
Sphinx is a free, open‑source git hook that asks developers a question about the behavior of AI‑generated code before the change is pushed. It works by pausing the push, presenting a scenario—such as a Stripe webhook…
1 source HN 49sphinx-six-theta.vercel.app -
Anomaly Innovations reports breach exposed API keys for ~1.4% of OpenCode Console users
Anomaly Innovations confirmed a security breach on October 17, 2026, affecting roughly 1.4% of OpenCode Console users, where attackers accessed stored API keys for Anthropic, OpenAI, and Google models via a legacy…
4 sourcesTechCrunch AIinfosecurity-magazine.comvectorwire.aistartupfortune.com -
Reflection releases Beam, a 501B-parameter open-weight model under Apache 2.0
Reflection has released Beam, its first open-weight model, on Hugging Face under an Apache 2.0 license. The model has 501 billion total parameters and 23 billion active parameters, uses a sparse mixture-of-experts…
6 sources primary sourcenote.comventurebeat.comAWS Machine Learning BlogUnite.AI +1 more -
Google releases open-source Scion for multi-agent AI teamwork
Google’s open-source Scion framework lets developers run multiple AI agents—like Claude Code, Codex, or Gemini CLI—as a coordinated team rather than competing models. Released under GoogleCloudPlatform on GitHub, Scion…
1 sourcenote.com -
Drawgent connects coding agents to live Excalidraw canvases
Drawgent is a new tool that bridges coding agents like Claude Code, Codex, and opencode with Excalidraw whiteboards. It allows developers to request diagrams via a chat panel or by writing "AGENT:" notes directly on…
1 source HN 45tangled.org -
Z.ai Deploys GLM‑5.3‑Flash on 100,000‑Chip Chinese Cluster
Z.ai announced a technical account detailing how it built a production‑grade inference service for its GLM‑5.3‑Flash model on a cluster of more than 100,000 Chinese‑made AI accelerators, a first at this scale. The…
1 sourceUnite.AI -
OpenCode offers a free, no‑rate‑limit alternative to Claude Code
OpenCode, an open‑source terminal AI coding agent, lets developers bypass Claude’s 5‑hour rolling window and weekly cap that can cut off heavy users. The author, a frequent Claude Code Pro subscriber, switched to…
1 sourcexda-developers.com -
OrcaReplay provides open, versioned archive of AI agent prompts and tool schemas
OrcaReplay, created by the team behind OrcaRouter, offers a public repository that stores system prompts, developer instructions, tool schemas, and agent harnesses used by current AI products. The archive holds 106…
1 source primary sourcegithub.com
Questions about OpenCode
What is the latest OpenCode news?
As of 26 October 2026: LiteLLM 1.107.0 compromised, developer says release process was hijacked. A study from the Hong Kong University of Science and Technology and collaborators compared several code‑generation models.