CodeWhale {isZh ? " 是社区共建的终端智能体，本地运行，支持你真正在用的模型——GLM、DeepSeek、Kimi、MiniMax、OpenRouter 等等。完整的工具面、审批闸门、快照回滚、子智能体与可恢复会话，都在你的终端里。" : " is a community-built terminal agent that runs locally and works with the models you actually use — GLM, DeepSeek, Kimi, MiniMax, OpenRouter, and more. A full tool surface, approval gates, snapshots you can roll back, sub-agents, and sessions you can resume."}
{/* COMMUNITY CALLOUT */}
{isZh ? (
<>
# npm（推荐，无需 Rust 工具链）{"\n"}
$ npm install -g codewhale{"\n"}
$ codewhale{"\n"}
# Cargo / Homebrew / 直接下载请见{"\n"}
# /install
) : (
<>
# npm — no Rust toolchain required{"\n"}
$ npm install -g codewhale{"\n"}
$ codewhale{"\n"}
# Cargo / Homebrew / direct download:{"\n"}
# /install
)}
{isZh ? "别的 Agent 声称自己「对齐」「可信」。CodeWhale 能证明——因为宪法会在模型的推理中现身：它决策时会援引「第 II 条」「第 V 条」。下面是真实会话中的推理摘录，以及它们所促成的决定。" : "Every agent claims to be aligned and trustworthy. CodeWhale can prove it — the Constitution shows up in the model's reasoning, citing \"Article II\" and \"Article V\" as it decides. These are real traces from an actual session, paired with the decision each produced."}
{isZh ? "模型会生成文本；Agent 会留下后果。CodeWhale 把后果需要的结构放在模型外面：自我、权威、证据、工具，各在其位。" : "A model generates text; an agent leaves consequences. CodeWhale puts the structure for those consequences around the model: self, authority, evidence, and tools, each in its place."}
Agent 不是模型卡片，也不是排行榜数字。它是这个终端、这个工作区、这个会话里的实例。先有地址，责任才有落点。
全局 Constitution、当前用户请求、运行时规则、仓库本地 law、实时证据、记忆、个性和旧交接各有顺位。冲突时不靠感觉。
文件、Shell、Git、Web、MCP、子 Agent、回滚和诊断都由 runtime 管理。模型不需要假装验证；它必须留下证据。
The agent is not a model card or leaderboard score. It is an instance in this terminal, this workspace, this session. Give it an address before you ask it to act.
Global Constitution, current user request, runtime statutes, repo-local law, live evidence, memory, personality, and old handoffs each have a rank. When they conflict, the agent has an order to follow.
Files, shell, git, web, MCP, sub-agents, rollback, and diagnostics are runtime surfaces. The model does not claim verification as a mood; it has to leave evidence.
{isZh ? "难点不是让模型一次做更多事，而是让用户意图、权威顺序、证据和贡献者上下文足够清楚，让下一个维护者可以接住。" : "The hard part is not making the model do more at once. It is keeping intent, authority, evidence, and contributor context clear enough for the next maintainer to inherit."}
{isZh ? "好的 Agent 工作不是一团活动记录，而是一条可以复核的线：请求、调查、补丁、验证、署名。" : "Good agent work is not a pile of activity. It is a reviewable line: request, investigation, patch, verification, credit."}
{isZh ? "框架承担了繁重工作：宪政提示、结构化信任、反馈循环、回滚和跨会话存活的交接。模型可以把注意力放在任务本身。" : "The harness carries the heavy parts: constitutional prompts, structured trust, feedback loops, rollback, and handoffs that survive the session. The model can keep its attention on the task itself."}
{item.d}
{isZh && dispatch.summaryZh ? dispatch.summaryZh : dispatch.summary}
{h.blurb}
{isZh ? "这一版合并和吸收了来自社区的大量工作。完整条目在 CHANGELOG 中；这里保留最新发布的公开致谢入口。" : "This release merged and harvested a large community tranche. The full notes live in the changelog; this keeps the latest public credit surface easy to find."}
{isZh ? "查看完整 changelog →" : "Full changelog →"}{isZh ? "无 CLA，无赞助商优先通道。维护者亲自阅读每一条内容，议题公开分类，版本从 main 分支发布。" : "No CLA. No sponsor lockouts. The maintainer reads everything personally, issues are triaged in the open, and releases cut from main."}