OpenCode

AI SDK added HarnessAgent as a common interface for Pi, Claude, Codex, OpenCode, and other harnesses. Use it to run local or cloud software-factory jobs through official SDKs while subscriptions cover token usage.

OpenCode v2 moves its TUI, desktop, and web clients onto a shared backend so sessions stay synced and resource use drops across windows. The beta matters for multi-window agent workflows, though the next build still lacks features.

Vercel extended the AI SDK Harness API to cover OpenCode and Deep Agents, adding more agent runtimes to the unified interface introduced in AI SDK 7. The change matters because apps can swap supported runtimes without rewriting integration code, though ACP is still awkward for some cloud deployments.

BrowserCode, Hyper, OpenCode, Together, and other vendors added GLM-5.2 soon after release. That turns the open model into a deployable option across coding, browser automation, and hosted chat.

Independent tests put GLM-5.2 near Opus 4.8 and GPT-5.5 on planning and coding, and users shared Claude Code, BrowserCode, dcode, and local-serving recipes. It matters because many engineers are treating it as a daily-driver option for text-heavy coding, though teams still report weaker vision and provider limits.

OpenCode v1.17.7 added active-server reuse for plugin clients, workspace roots for MCP servers, and SDK auto-refresh for models and credentials. It follows a 1.17.6 compatibility update that declared OpenCode's supported client capabilities to improve MCP interoperability.

Moonshot open-sourced Kimi K2.7 Code and says it outperforms K2.6 by 21.8% on Kimi Code Bench v2 while using 30% fewer reasoning tokens. The release includes open weights and API access, so teams can test the 180 tok/s HighSpeed rollout and early Cline/OpenCode support.

Cohere open-sourced North Mini Code, a 30B-parameter coding MoE with 3B active parameters, 256K context, and Apache 2.0 licensing. OpenCode added it the same day, making the release immediately usable in a coding-agent client.

OpenRouter, OpenCode, Lovable, Cline, Browser Use Terminal, Nous Portal, and Venice all added Fable 5 within hours of launch. The rollouts put the model into gateways, coding agents, browser agents, and chat clients on day one.

Builders shipped OpenProse workflow files, ghzinga PR tabs, cmux terminal controls, datasette-agent-edit primitives, and an agent-optimized CLI fork. These pieces turn prompt strings into reusable files, panes, and testable edit loops for coding agents.

Helmor released an open-source mobile client that exposes Claude Code, Codex, OpenCode, and custom model backends behind a phone-first UI plus one-click Cloudflare Tunnel setup. The launch targets remote coding sessions from a handset instead of a laptop-only agent workflow.

Two days after Qwen 3.7 Plus launched, Hyper, OpenCode, Kilo, and Vals shipped support or rankings around the 1M-context multimodal model. The rapid pickup shows Alibaba’s new model landing quickly in coding-agent tools and public eval stacks outside its own platform.

A day after MiniMax M3 launched, OpenCode, Hermes Agent, Flowith, Atomic Chat, Kilo Code, Cloudflare AI Gateway, and Vercel AI Gateway shipped support. That breadth shows M3 plugged into agent harnesses and routing layers immediately, not just its own API.

A day after MiniMax M3 launched, independent testers posted mixed results: cheap demos and design tasks worked, but several coding runs stalled, broke features, or used more tokens than expected. New external numbers added nuance, with Context Arena falling sharply after 64k context and one DeepSWE run passing 15 of 113 tasks.

Alibaba rolled out implicit caching for Qwen3.7 Max, automatically reusing repeated context without user setup. The update also lands with fresh benchmark results and broader coding-agent support across OpenCode and Hermes Agent.

xAI put Grok Build 0.1 into the API with 256K context and $1 per million input plus $2 output pricing, while OpenCode and Kilo wired it into coding workflows. Early web-build tests in Kilo landed around $0.07 to $0.14 per task.

OpenCode, Kilo, Replicate, and Mastra exposed Gemini 3.5 Flash on launch day across coding agents, routers, and hosted APIs. The fast uptake gives engineers multiple harnesses to test Google's 1M-context model despite mixed first-party app reports.

OpenCode made Ring 2.6 1T available in the editor with reasoning enabled and free access for a limited period. Follow-on posts from Kilo and others claim frontier-level results on AIME 26, ClawEval, Gaia2-search, and Tau2-Bench Telecom.

Builders shipped pi-treebase, a Miko voice mode for pi-listens, devrage support, and a Japanese OpenCode Go guide after the first Pi extension burst. The releases arrive as Pi’s provider abstraction gets stress-tested by OpenClaw-scale multi-provider use.

OpenCode previewed a non-fullscreen minimal mode that keeps native terminal scrollback intact while refactoring core logic into internal plugins with tracing. The update matters because terminal-first users get steadier sessions and plugin hook performance becomes easier to inspect.

OpenCode shipped back-to-back 1.14.32 and 1.14.33 updates fixing shell editing, OpenAPI schema handling, custom-agent loading, and Kimi 2.6 instability while contributors said the package was slimmed by about 20,000 lines. The release matters because it reduces npm install pain and runtime slowness in self-hosted coding-agent setups.

Xiaomi’s MiMo-V2.5-Pro and MiMo-V2.5 arrived with million-token context windows, stronger coding and agentic claims, and immediate access through OpenRouter plus agent harnesses. The rollout adds another low-cost Chinese frontier model that engineers can route into coding workflows without waiting for a proprietary IDE deal.

OpenCode 1.4.11 beta lets sessions run inside git worktrees or remote environments, with a remote server that keeps sessions alive and resyncs locally after reconnects. Use it if you run multi-session agent work across machines or plugin-defined runtimes.

Z.ai released GLM-5.1, a 744B open model built for long-horizon agentic coding and ranked first among open systems on SWE-Bench Pro. Day-0 support in OpenRouter, Ollama, SGLang, vLLM, OpenCode, and local quantization paths makes it ready to test in existing stacks.

OpenCode says all Go models now run under zero-data-retention agreements and that hosted requests use the same upstream providers as direct access. That tightens the privacy boundary for hosted coding agents, but operators still need to watch RAM use, rapid updates, and plan economics.

OpenCode shipped terminal, desktop, and `opencode serve` workflows for an open-source coding agent with LSP support, plugins, and more than 75 providers. Users should look at the multi-backend web sessions, IPC plugins, and sandboxed local setup as the main differentiators.

OpenCode is adding remote sandboxes, synced state across laptop, server, and cloud, and more product surface inside its plugin system. That makes long-running off-laptop workflows more practical, but operators should still review telemetry, sandbox, and exposure defaults.

OpenCode can now run from AWS CloudShell via npx and inherit AWS auth plus Bedrock models; the same update also brought Firecrawl, India billing, and heap-snapshot debugging. It is becoming a real ops workflow, not just a local terminal toy.