diff --git a/CHANGELOG.md b/CHANGELOG.md new file mode 100644 index 0000000..569d26a --- /dev/null +++ b/CHANGELOG.md @@ -0,0 +1,31 @@ +# Changelog + +## 0.1.0 Private Preview 1 - 2026-08-03 + +This private preview packages the current Meldwork MVP for internal evaluation on Apple silicon Macs. + +### Highlights + +- Local-first direct conversations and persistent multi-Agent working groups. +- Automatic multi-round discussions with explicit Agent targeting and bounded execution. +- Durable, sanitized run traces for reviewing Agent activity without exposing credentials, executable paths, or private reasoning. +- Independent Provider profiles, native Agent session continuity, Skills, knowledge-source references, images, and controlled workspace access. +- Support for Codex, Hermes, OpenClaw, WorkBuddy, Kimi Code, MiMo Code, Claude Code, Gemini CLI, OpenCode, Qwen Code, OpenCodeReview, and Custom Agents. +- Major frontend and Electron modularization while preserving the existing UI and public desktop bridge contracts. + +### Distribution + +- macOS Apple silicon: DMG and ZIP artifacts. +- Private preview only. The application is ad-hoc signed and not notarized with an Apple Developer ID. +- Windows and Intel Mac release artifacts are not included in this preview. + +### License + +Meldwork is source-available under PolyForm Noncommercial 1.0.0. Commercial use requires a separate written agreement. + +### Verification + +- Frontend tests: 217 passed. +- Desktop tests: 470 passed. +- Web and Electron frontend builds passed. +- Electron packaging, ASAR inspection, and deep signature verification passed. diff --git a/COMMERCIAL_USE.md b/COMMERCIAL_USE.md index f23c781..ff8428a 100644 --- a/COMMERCIAL_USE.md +++ b/COMMERCIAL_USE.md @@ -1,14 +1,16 @@ # Commercial Use Policy -Meldwork is published under the [PolyForm Noncommercial License 1.0.0](LICENSE). +Meldwork is source-available under the [PolyForm Noncommercial License 1.0.0](LICENSE). It is not licensed under Apache 2.0, because Apache 2.0 permits commercial use. -You may use, study, modify, and share the software only for purposes permitted by that license. Commercial use is not permitted unless you have a separate written agreement from the copyright holder. +You may use, study, modify, and share Meldwork only for purposes permitted by the PolyForm Noncommercial license. Commercial use requires a separate written agreement from the copyright holder. -Examples that require separate permission include: +Examples that require prior written permission include: -- using Meldwork to provide a paid product, paid service, hosted service, consulting delivery, or internal business workflow; -- redistributing Meldwork as part of a commercial product or package; -- using Meldwork branding, assets, or documentation in commercial marketing; -- offering support, integration, training, or managed deployment for Meldwork as a paid service. +- using Meldwork in a for-profit company's internal workflow, commercial evaluation, or client delivery; +- offering Meldwork as a paid product, hosted service, consulting service, integration, training, or managed deployment; +- redistributing Meldwork as part of a commercial product, bundle, or appliance; +- using Meldwork branding, product assets, or documentation in commercial marketing. -For commercial licensing, contact the repository owner through GitHub before using the software in a commercial context. +This page is a practical summary and does not replace or modify the license terms. When the classification of a use is unclear, obtain written permission before using Meldwork in a commercial context. + +For commercial licensing, contact the repository owner through GitHub. diff --git a/LICENSE b/LICENSE index 1a71cb6..c3a0298 100644 --- a/LICENSE +++ b/LICENSE @@ -1,59 +1,60 @@ -# PolyForm Noncommercial License 1.0.0 +PolyForm Noncommercial License 1.0.0 - +https://polyformproject.org/licenses/noncommercial/1.0.0 -## Acceptance +Required Notice: Copyright 2026 Ryder-MHumble and Meldwork contributors. + +Acceptance In order to get any license under these terms, you must agree to them as both strict obligations and conditions to all your licenses. -## Copyright License +Copyright License The licensor grants you a copyright license for the software to do everything you might do with the software that would otherwise infringe the licensor's copyright -in it for any permitted purpose. However, you may -only distribute the software according to [Distribution -License](#distribution-license) and make changes or new works -based on the software according to [Changes and New Works -License](#changes-and-new-works-license). +in it for any permitted purpose. However, you may +only distribute the software according to the Distribution +License section and make changes or new works based on the +software according to the Changes and New Works License section. -## Distribution License +Distribution License The licensor grants you an additional copyright license -to distribute copies of the software. Your license +to distribute copies of the software. Your license to distribute covers distributing the software with -changes and new works permitted by [Changes and New Works -License](#changes-and-new-works-license). +changes and new works permitted by the Changes and New Works +License section. -## Notices +Notices You must ensure that anyone who gets a copy of any part of the software from you also gets a copy of these terms or the URL for them above, as well as copies of any plain-text lines -beginning with `Required Notice:` that the licensor provided -with the software. For example: +beginning with "Required Notice:" that the licensor provided +with the software. For example: -> Required Notice: Copyright Yoyodyne, Inc. (http://example.com) +Required Notice: Copyright Yoyodyne, Inc. (http://example.com) -## Changes and New Works License +Changes and New Works License The licensor grants you an additional copyright license to make changes and new works based on the software for any permitted purpose. -## Patent License +Patent License The licensor grants you a patent license for the software that covers patent claims the licensor can license, or becomes able to license, that you would infringe by using the software. -## Noncommercial Purposes +Noncommercial Purposes Any noncommercial purpose is a permitted purpose. -## Personal Uses +Personal Uses Personal use for research, experiment, and testing for the benefit of public knowledge, personal study, private @@ -61,7 +62,7 @@ entertainment, hobby projects, amateur pursuits, or religious observance, without any anticipated commercial application, is use for a permitted purpose. -## Noncommercial Organizations +Noncommercial Organizations Use by any charitable organization, educational institution, public research organization, public safety or health @@ -70,19 +71,19 @@ or government institution is use for a permitted purpose regardless of the source of funding or obligations resulting from the funding. -## Fair Use +Fair Use You may have "fair use" rights for the software under the law. These terms do not limit them. -## No Other Rights +No Other Rights These terms do not allow you to sublicense or transfer any of your licenses to anyone else, or prevent the licensor from -granting licenses to anyone else. These terms do not imply +granting licenses to anyone else. These terms do not imply any other licenses. -## Patent Defense +Patent Defense If you make any written claim that the software infringes or contributes to infringement of any patent, your patent license @@ -90,42 +91,42 @@ for the software granted under these terms ends immediately. If your company makes such a claim, your patent license ends immediately for work on behalf of your company. -## Violations +Violations The first time you are notified in writing that you have violated any of these terms, or done anything with the software not covered by your licenses, your licenses can nonetheless continue if you come into full compliance with these terms, and take practical steps to correct past violations, within -32 days of receiving notice. Otherwise, all your licenses +32 days of receiving notice. Otherwise, all your licenses end immediately. -## No Liability +No Liability -***As far as the law allows, the software comes as is, without +As far as the law allows, the software comes as is, without any warranty or condition, and the licensor will not be liable to you for any damages arising out of these terms or the use -or nature of the software, under any kind of legal claim.*** +or nature of the software, under any kind of legal claim. -## Definitions +Definitions -The **licensor** is the individual or entity offering these -terms, and the **software** is the software the licensor makes +The "licensor" is the individual or entity offering these +terms, and the "software" is the software the licensor makes available under these terms. -**You** refers to the individual or entity agreeing to these +"You" refers to the individual or entity agreeing to these terms. -**Your company** is any legal entity, sole proprietorship, +"Your company" is any legal entity, sole proprietorship, or other kind of organization that you work for, plus all organizations that have control over, are under the control of, -or are under common control with that organization. **Control** +or are under common control with that organization. "Control" means ownership of substantially all the assets of an entity, or the power to direct its management and policies by vote, -contract, or otherwise. Control can be direct or indirect. +contract, or otherwise. Control can be direct or indirect. -**Your licenses** are all the licenses granted to you for the +"Your licenses" are all the licenses granted to you for the software under these terms. -**Use** means anything you do with the software requiring one +"Use" means anything you do with the software requiring one of your licenses. diff --git a/NOTICE b/NOTICE index a06ef9e..b32e357 100644 --- a/NOTICE +++ b/NOTICE @@ -1 +1,9 @@ Required Notice: Copyright 2026 Ryder-MHumble and Meldwork contributors. + +Third-party Agent names, product names, and logos remain the property of their +respective owners. They are used only to identify compatible integrations and +do not imply sponsorship or endorsement. + +The OpenCodeReview logo is sourced from Alibaba's OpenCodeReview project: +https://github.com/alibaba/open-code-review/blob/main/imgs/logo-core.svg +The upstream project is licensed under Apache License 2.0. diff --git a/README.md b/README.md index b95a10a..5335288 100644 --- a/README.md +++ b/README.md @@ -6,83 +6,86 @@ English · 简体中文

-# Multiple agents. One body of work. +# AI agents are interchangeable. Your work should not be. -**Meldwork gives different AI agents one persistent local workspace: context stays intact, collaboration stays visible, and you stay in control.** +**Meldwork is a local-first desktop workspace where one task can move between direct Agent conversations, multi-Agent working groups, and independent review without losing its context or execution history.** -The agent market is getting better and messier at the same time. One agent writes, another researches, another reviews. The hard part is no longer getting an answer. It is keeping the work coherent while the agents around it change. +Start with one Agent. Bring in others when the work needs a different capability, a second opinion, or an adversarial review. Meldwork keeps the conversation, participants, permissions, outputs, and sanitized run evidence together on your computer. -Meldwork brings the agents you already use into direct conversations and working groups, without turning your work into another hosted service. +

+ Download the private macOS preview + · Noncommercial license + · Commercial use +

-[PolyForm Noncommercial 1.0.0](LICENSE) · [Commercial use](COMMERCIAL_USE.md) · [Notice](NOTICE) +## Install the desktop client -## Stop rebuilding context +The current private preview is built for Apple silicon Macs. -Most multi-agent workflows are still tab switching with extra steps: +1. Open the [latest GitHub Release](https://github.com/Ryder-MHumble/Meldwork/releases/latest). +2. Download `Meldwork-0.1.0-arm64.dmg`. +3. Drag Meldwork into Applications and open it. +4. Connect the supported Agent CLIs already installed on your computer, or configure an independent Provider profile for an Agent. -- repeat the brief every time you change tools; -- carry decisions and files between disconnected sessions; -- manually decide who should answer, challenge, revise, or continue; -- lose sight of what happened once a polished final response appears. +The private preview is ad-hoc signed and not yet Apple-notarized. A public distribution build will require Developer ID signing and notarization. -**That is not collaboration. It is context tax.** +## One place to see the work -Meldwork keeps the task, conversation, participants, permissions, and run history together, so a different agent can join the work without forcing you to reconstruct it. +![Meldwork workspace overview](docs/assets/meldwork-workspace-overview.png) -## One workspace, clear roles +Direct conversations and working groups live in the same desktop workspace. A task can begin as a focused conversation and become a group review without turning into a trail of disconnected windows. -| What you need | What Meldwork changes | +## From a first answer to a reviewed decision + +| Step | What happens in Meldwork | | --- | --- | -| A fast answer from one agent | Start a focused direct conversation and keep it available for later | -| A second opinion | Bring selected agents into the same working group | -| Real critique, not polite agreement | Run a bounded multi-agent discussion and decide how many rounds it gets | -| Confidence in what happened | See who is queued, working, complete, or failed, with the run trace attached to the conversation | -| Control over your environment | Keep conversations and orchestration state local, with visible workspace write permissions | -| Freedom to use different vendors | Connect supported agents without replacing their accounts, providers, or native strengths | +| Start | Open a direct conversation with the Agent best suited to the first step | +| Escalate | Create a working group and select only the Agents that should participate | +| Discuss | Run a manual handoff or a bounded automatic multi-round discussion | +| Verify | Inspect final replies, status, source context, and sanitized execution traces before accepting the result | -## What feels different +![Multi-Agent product review in Meldwork](docs/assets/meldwork-multi-agent-review.png) -### Start with one agent. Escalate only when the work deserves it. +The conversation remains readable while Agent-specific process details stay available on demand. Group runs preserve compact evidence for later Agents and for the human making the final decision. -Meldwork does not force every task through a committee. Use one agent when one is enough. Add another for a different capability, an independent attempt, or an adversarial review. +## Why teams use Meldwork -### Let agents challenge each other, with a limit. +- **Research:** one Agent builds the evidence base while another challenges unsupported assumptions. +- **Product and strategy:** one develops the proposal, another tests positioning, feasibility, and expensive failure modes. +- **Software delivery:** one implements, another reviews the diff and the reasoning behind it. +- **Writing and content:** one creates, another checks structure, factual accuracy, and tone. +- **Operations:** specialized Agents handle different parts of the task while the full work record stays visible. -Working groups can run automatic discussions across selected agents. You set the boundary, watch the run, and decide what is worth keeping. +The goal is not to maximize Agent count. It is to use the right Agent at the right moment without fragmenting the work. -### Keep the work, not just the final reply. +## What the desktop client keeps together -Persistent conversations, compatible native-session continuity, visible run state, Skills, images, and collected outputs stay connected to the task that produced them. +- Persistent direct conversations and multi-Agent working groups. +- Explicit Agent targeting, manual runs, and automatic multi-round discussions. +- Compatible native-session continuity for each conversation and Agent. +- Sanitized run traces, completion state, and compact evidence capsules. +- Agent-specific Provider profiles and operating-system-backed credential storage where supported. +- Skills, images, approved knowledge sources, and opt-in workspace access. +- Local conversation and orchestration state with no Meldwork cloud account or remote conversation store. -### Stay in charge of the machine. +Model requests still follow the Agent and Provider you choose. Local-first describes Meldwork's workspace and orchestration state; it does not make third-party models offline. -Meldwork is local-first. Workspace access is explicit, sensitive credentials use operating-system-backed storage where supported, and agent execution stays behind the desktop application's controlled boundary. +## Connected Agents -## Built for work that cannot rely on one answer +Meldwork currently integrates with: -- **Research:** one agent gathers evidence, another attacks the assumptions. -- **Product and strategy:** one develops the proposal, another looks for the expensive mistake. -- **Writing and content:** one creates, another edits for accuracy, structure, and tone. -- **Development:** one implements, another reviews the code and the reasoning behind it. -- **Operations:** different agents handle specialized parts while the full task remains visible in one place. +**Codex · Hermes · OpenClaw · WorkBuddy · Kimi Code · MiMo Code · Claude Code · Gemini CLI · OpenCode · Qwen Code · OpenCodeReview · Custom Agents** -The point is not to use more agents. The point is to use the right agent for each part of the job without breaking the job apart. +Each Agent keeps its own capabilities, provider configuration, permission model, and session behavior. Availability depends on the installed Agent, its version, and its authentication state. -## Agents you can bring in today +## Private MVP status -Meldwork currently connects to: +This repository and its Releases are currently private while the MVP is being completed. The macOS Apple silicon client is the only release-validated target in this preview. Windows, Intel Mac, Apple notarization, and broad third-party Agent certification are not yet claimed. -**Codex · Hermes · OpenClaw · WorkBuddy · Kimi Code · MiMo Code · Claude Code · Gemini CLI · OpenCode · Qwen Code · OpenCodeReview** +
+Build from source for development -Each agent keeps its own capabilities, provider configuration, permission model, and session behavior. Availability depends on the installed agent, its version, and your configuration. - -## Local-first, without pretending the internet disappears - -Conversations, groups, and orchestration state stay on your computer. Model requests still follow the agent and provider you choose. Meldwork keeps the workspace local; it does not make third-party models offline. - -## Run Meldwork locally - -Current desktop target: macOS. Requires Node.js 20.19 or newer and npm. +Requires Node.js 20.19 or newer and npm. ```bash npm --prefix frontend ci @@ -90,6 +93,12 @@ npm --prefix desktop ci npm --prefix desktop run dev ``` +Verification commands are documented in [docs/tests.md](docs/tests.md). + +
+ ## License -Meldwork is source-available under the [PolyForm Noncommercial 1.0.0](LICENSE). Noncommercial use is permitted under the license terms. Commercial use requires a separate written agreement; see [COMMERCIAL_USE.md](COMMERCIAL_USE.md). +Meldwork is source-available under the [PolyForm Noncommercial License 1.0.0](LICENSE). It is not Apache-2.0 licensed: Apache 2.0 permits commercial use, while this project currently does not. + +Noncommercial use is permitted only under the license terms. Commercial use requires a separate written agreement; see [COMMERCIAL_USE.md](COMMERCIAL_USE.md). Third-party attribution is recorded in [NOTICE](NOTICE). diff --git a/README.zh-CN.md b/README.zh-CN.md index f6e935b..5bae5c2 100644 --- a/README.zh-CN.md +++ b/README.zh-CN.md @@ -1,88 +1,89 @@

- Meldwork：Agent 可切换，工作不断线 + Meldwork：Agent 随时切换，工作始终连续

English · 简体中文

-# 多个 Agent，一项完整的工作 +# Agent 可以换，工作不该断 -**Meldwork 把不同 AI Agent 放进一个持续的本地工作空间：上下文不重置，协作过程可见，最终决定权始终在人。** +**Meldwork 是一个本地优先的多 Agent 桌面工作台。你可以先找一个 Agent 直接开工；当任务需要交叉验证、不同能力或独立审查时，再把其他 Agent 拉进同一个工作群组。上下文、过程和最终判断始终围绕同一项工作展开。** -Agent 越来越强，工作反而越来越碎。一个负责写作，一个擅长研究，另一个更适合审查。现在真正困难的已经不是得到一句回答，而是在工具不断切换时，让上下文、过程和决策保持完整。 +它解决的不是“同时打开更多 AI”，而是让一项复杂工作能够在不同 Agent 之间真正接力：前一个 Agent 留下的结论和证据，后一个可以继续使用；所有人的回答仍然回到同一条任务脉络里，由你决定哪些结果值得接受。 -Meldwork 把你已经在用的 Agent 带进单聊与工作群组，同时不把你的工作变成另一个托管在云端的孤岛。 +

+ 下载 macOS 私有预览版 + · 非商用许可证 + · 商业使用说明 +

-[PolyForm 非商用许可证](LICENSE) · [商业使用](COMMERCIAL_USE.md) · [声明](NOTICE) +## 先装客户端，再开始工作 -## 别再反复重建上下文 +当前私有预览版面向 Apple 芯片 Mac： -今天多数所谓的多 Agent 工作流，本质上仍然只是更复杂的窗口切换： +1. 打开 [最新 GitHub Release](https://github.com/Ryder-MHumble/Meldwork/releases/latest)。 +2. 下载 `Meldwork-0.1.0-arm64.dmg`。 +3. 将 Meldwork 拖入“应用程序”并打开。 +4. 连接电脑上已经安装的 Agent CLI，或为某个 Agent 单独配置 Provider。 -- 每换一个工具，就重新解释一次任务； -- 在彼此割裂的会话之间搬运决策、文件和中间结果； -- 手动判断谁该回答、质疑、修改或继续； -- 最终回答一旦足够流畅，之前发生过什么反而无从追踪。 +当前内测包采用临时签名，尚未完成 Apple Developer ID 签名与公证。正式公开分发前会补齐这一环节。 -**这不是协作，只是上下文税。** +## 打开客户端，看到的是完整工作现场 -Meldwork 把任务、会话、参与者、权限和运行记录留在一起。换一个 Agent 加入，也不需要你从头拼回整项工作。 +![Meldwork 工作台总览](docs/assets/meldwork-workspace-overview.png) -## 一个工作空间，角色各自清楚 +单聊、工作群组和最近任务都在同一个桌面工作台里。一个需求可以先由 Codex 起草，再交给 Hermes 补充研究，最后让 OpenCodeReview 做独立审查，不需要在多个窗口之间复制背景、文件和中间结论。 -| 你真正需要的 | Meldwork 带来的改变 | -| --- | --- | -| 让一个 Agent 快速回答 | 发起聚焦的单聊，并在之后继续同一项工作 | -| 引入第二种判断 | 把选定的 Agent 放进同一个工作群组 | -| 得到真正的质疑，而不是礼貌附和 | 启动有轮次上限的多 Agent 讨论，由你决定讨论边界 | -| 确认过程里到底发生了什么 | 看清谁在排队、执行、完成或失败，并把运行轨迹留在会话中 | -| 掌控自己的工作环境 | 会话与编排状态保留在本机，工作区写入权限明确可见 | -| 自由选择不同厂商 | 连接已支持的 Agent，同时保留原有账号、Provider 与各自能力 | +## 一项任务如何在 Meldwork 里推进 -## 真正不同的地方 +| 阶段 | 你的操作 | Meldwork 保留下来的内容 | +| --- | --- | --- | +| 先开工 | 选择最合适的 Agent 发起单聊 | 当前任务、对话和原生 Session 延续关系 | +| 再协作 | 创建群组，只选择真正需要参与的 Agent | 群组成员、工作目录和明确的执行权限 | +| 多轮打磨 | 手动点名，或启动有边界的自动多轮讨论 | 每轮回答、Agent 接力关系和运行状态 | +| 最终验收 | 查看结论与运行轨迹，决定是否采用 | 精简后的证据、状态和可追溯结果 | -### 一个 Agent 够用时，就只用一个 +![Meldwork 多 Agent 产品审查群聊](docs/assets/meldwork-multi-agent-review.png) -Meldwork 不会强迫每项任务都经过一场会议。只有当不同能力、独立尝试或对抗式审查确实有价值时，再加入另一个 Agent。 +主对话只保留对工作有价值的内容；需要追问时，再展开某个 Agent 的执行过程。这样既不会让工具日志淹没结论，也不会只剩一段看似完整、却无法复盘的最终回答。 -### 让 Agent 彼此交锋，但不给流程失控的机会 +## 它适合哪些真实工作 -工作群组可以让选定的 Agent 自动进行多轮讨论。你设定边界，观察运行过程，并决定哪些结果值得留下。 +- **研究与情报：** 一个 Agent 收集证据，另一个专门寻找证据缺口和错误假设。 +- **产品与战略：** 一个完善方案，另一个从用户价值、商业风险和执行成本上进行压力测试。 +- **软件开发：** 一个负责实现，另一个审查代码改动、测试覆盖和关键判断。 +- **写作与内容：** 一个搭建结构和初稿，另一个检查事实、表达和读者体验。 +- **复杂运营：** 不同 Agent 处理各自擅长的部分，但完整任务仍然留在一个地方。 -### 留住的不只是最终回答 +Meldwork 不鼓励为了“看起来智能”而堆叠 Agent。一个 Agent 足够时就直接完成；只有当第二种能力确实能降低错误、返工或决策风险时，才把它加入工作。 -持续会话、兼容条件下的原生 Session 延续、可见的运行状态、Skill、图片与收集到的产出，都与产生它们的任务保持关联。 +## 客户端把这些能力放在一起 -### 机器仍然由你掌控 +- 持续存在的 Agent 单聊与多 Agent 工作群组。 +- 明确点名执行、手动接力和自动多轮讨论。 +- 在兼容条件下，为每个群组和 Agent 延续原生 Session。 +- 可复盘但经过脱敏和压缩的运行轨迹与证据摘要。 +- 每个 Agent 独立的 Provider 档案，以及兼容系统下的安全凭据存储。 +- Skill、图片、授权知识源和按需开启的工作目录访问。 +- 会话与编排状态留在本机，不依赖 Meldwork 云账号或远程会话数据库。 -Meldwork 坚持本地优先。工作区访问是明确的，兼容的敏感凭据使用操作系统安全存储，Agent 执行始终位于桌面应用的受控边界内。 +模型请求仍然会按照你选择的 Agent 和 Provider 发出。“本地优先”指 Meldwork 自己的工作空间和编排状态留在电脑上，并不意味着第三方模型自动变成离线模型。 -## 适合这些不能只靠一次回答的工作 +## 当前可以连接的 Agent -- **深度研究：** 一个 Agent 收集证据，另一个专门攻击假设。 -- **产品与战略：** 一个完善方案，另一个寻找代价最高的错误。 -- **写作与内容：** 一个创作，另一个检查事实、结构和语气。 -- **软件开发：** 一个实现，另一个审查代码以及代码背后的判断。 -- **复杂运营：** 不同 Agent 负责各自擅长的部分，完整任务仍然留在同一个地方。 +**Codex · Hermes · OpenClaw · WorkBuddy · Kimi Code · MiMo Code · Claude Code · Gemini CLI · OpenCode · Qwen Code · OpenCodeReview · 自定义 Agent** -重点从来不是使用更多 Agent，而是让每个环节使用更合适的 Agent，同时不把一项工作拆得支离破碎。 +每个 Agent 保留自己的能力、Provider、权限模型和 Session 行为。能否使用取决于本机是否安装、版本是否兼容，以及对应认证是否就绪。 -## 现在可以接入的 Agent +## 当前仍是私有 MVP -Meldwork 当前可连接： +仓库和 Release 暂时保持 private，等 MVP 真正达到可公开使用的标准后再开放。目前经过发布验证的目标只有 Apple 芯片 Mac；Windows、Intel Mac、Apple 公证以及所有第三方 Agent 的广泛兼容性还不属于本版本承诺。 -**Codex · Hermes · OpenClaw · WorkBuddy · Kimi Code · MiMo Code · Claude Code · Gemini CLI · OpenCode · Qwen Code · OpenCodeReview** +
+开发者从源码运行 -每个 Agent 仍然保留自己的能力、Provider 配置、权限模型和 Session 行为。实际可用性取决于已安装的 Agent、对应版本与用户配置。 - -## 本地优先，但不假装互联网消失了 - -会话、群组和编排状态保留在你的电脑上。模型请求仍然遵循你选择的 Agent 与 Provider。Meldwork 让工作空间留在本地，但不会把第三方模型伪装成离线服务。 - -## 在本地运行 Meldwork - -当前桌面目标为 macOS，需要 Node.js 20.19 或更高版本以及 npm。 +源码开发需要 Node.js 20.19 或更高版本以及 npm： ```bash npm --prefix frontend ci @@ -90,6 +91,12 @@ npm --prefix desktop ci npm --prefix desktop run dev ``` +完整验证命令见 [docs/tests.md](docs/tests.md)。 + +
+ ## 许可证 -Meldwork 以 [PolyForm Noncommercial 1.0.0](LICENSE) 许可证开放源代码。符合许可证条款的非商业使用无需额外授权；商业使用需要单独签署书面协议，详见 [COMMERCIAL_USE.md](COMMERCIAL_USE.md)。 +Meldwork 目前以 [PolyForm Noncommercial 1.0.0](LICENSE) 方式开放源代码，但不允许商业使用。这里不能使用 Apache 2.0 来实现“禁止商用”，因为 Apache 2.0 本身明确允许商业使用。 + +符合许可证条款的非商业使用无需额外授权；公司内部业务、收费服务、商业交付、商业分发等用途需要事先取得单独的书面授权，详见 [COMMERCIAL_USE.md](COMMERCIAL_USE.md)。第三方标识归属见 [NOTICE](NOTICE)。 diff --git a/docs/assets/meldwork-multi-agent-review.png b/docs/assets/meldwork-multi-agent-review.png new file mode 100644 index 0000000..47ef03a Binary files /dev/null and b/docs/assets/meldwork-multi-agent-review.png differ diff --git a/docs/assets/meldwork-workspace-overview.png b/docs/assets/meldwork-workspace-overview.png new file mode 100644 index 0000000..5cb9b2f Binary files /dev/null and b/docs/assets/meldwork-workspace-overview.png differ diff --git a/frontend/public/agent-logos/opencodereview.svg b/frontend/public/agent-logos/opencodereview.svg index 3716f1e..52b0b6b 100644 --- a/frontend/public/agent-logos/opencodereview.svg +++ b/frontend/public/agent-logos/opencodereview.svg @@ -1,6 +1 @@ - - - - - - + diff --git a/frontend/public/logos/meldwork-readme-banner-en.png b/frontend/public/logos/meldwork-readme-banner-en.png index 943aaf7..c494498 100644 Binary files a/frontend/public/logos/meldwork-readme-banner-en.png and b/frontend/public/logos/meldwork-readme-banner-en.png differ diff --git a/frontend/public/logos/meldwork-readme-banner-zh-CN.png b/frontend/public/logos/meldwork-readme-banner-zh-CN.png index cb399e9..92b1896 100644 Binary files a/frontend/public/logos/meldwork-readme-banner-zh-CN.png and b/frontend/public/logos/meldwork-readme-banner-zh-CN.png differ