mirror of
https://github.com/Ryder-Sun/Meldwork.git
synced 2026-11-07 06:56:03 -10:00
docs: improve AI discoverability and project positioning
This commit is contained in:
Ryder Sun committed
1 parent
524009f2ea
commit
159ff767fa
3 files changed
+327
-126
No files matched your search
@@ -14,113 +14,153 @@
|
||||
<strong>English</strong> · <a href="README.zh-CN.md">简体中文</a>
|
||||
</p>
|
||||
|
||||
# Meldwork builds the organization layer for AI agents.
|
||||
# Meldwork: Local-First Multi-Agent Collaboration Workspace
|
||||
|
||||
**Most tools help humans run more agents. Meldwork is built for a different job: make multi-agent work legible, accountable, and reusable.**
|
||||
> Meldwork is a local-first Electron desktop workspace for multi-agent collaboration and agent orchestration. It brings supported local Agent CLIs into one AI agent workspace, runs concurrent or negotiated work, preserves inspectable evidence, and keeps a human in the loop before workspace writes and adoption decisions.
|
||||
|
||||
The current preview is a local work cell for supported Agent CLIs. It keeps participants explicit, context scoped, collaboration bounded, run state inspectable, and human review in the loop. Selected Agents can now respond concurrently or move through independent proposals, peer negotiation, responsibility-based work, single-writer integration, and independent verification around one goal.
|
||||
Meldwork is a source-available, local-first desktop application for people who already use more than one AI coding or research Agent. The current public preview is a single-user work cell: you choose the participants, the working directory, the context, and the final decision. There is no required Meldwork server, account, or remote conversation store.
|
||||
|
||||
<p align="center">
|
||||
<a href="https://github.com/Ryder-MHumble/Meldwork/releases/download/Meldwork-V1.0.3/Meldwork-0.1.3-arm64.dmg"><strong>Download Meldwork V1.0.3 for Apple silicon macOS</strong></a>
|
||||
<a href="https://github.com/Ryder-MHumble/Meldwork/releases/tag/Meldwork-V1.0.3"><strong>Download the V1.0.3 prerelease for Apple silicon macOS</strong></a>
|
||||
· <a href="architecture.md">Architecture</a>
|
||||
· <a href="desktop/README.md">Desktop guide</a>
|
||||
· <a href="LICENSE">License</a>
|
||||
</p>
|
||||
|
||||
## The missing layer in the Agent workforce
|
||||
## What problem does it solve?
|
||||
|
||||
Agent supply is growing quickly. The organization around it is not.
|
||||
Using several Agents usually means manually choosing a tool, moving context between terminals, reconciling conflicting answers, and remembering why a change was accepted. Meldwork provides the organization layer between individual Agents and a finished decision:
|
||||
|
||||
Today, people still choose every Agent, move every piece of context, explain every role, reconcile conflicting answers, and carry the final accountability. Parallel managers improve throughput. Agent frameworks let developers program workflows. Single-Agent products improve one worker.
|
||||
- one shared goal and explicit acceptance boundary;
|
||||
- independent proposals instead of hidden routing;
|
||||
- declared permissions, responsibilities, handoffs, dependencies, and stopping conditions;
|
||||
- durable, bounded artifacts and evidence that remain reviewable when Agents change;
|
||||
- human-controlled permission, budget, write, and adoption decisions.
|
||||
|
||||
Meldwork is focused on the work between them:
|
||||
## Core capabilities
|
||||
|
||||
- one shared goal and acceptance boundary;
|
||||
- independent viewpoints instead of hidden routing;
|
||||
- explicit authority, responsibility, handoffs, and stopping conditions;
|
||||
- artifacts and evidence that survive Agent changes;
|
||||
- a human-controlled adoption decision.
|
||||
### Multi-agent collaboration and orchestration
|
||||
|
||||
## What Meldwork is building
|
||||
- **Direct conversations and persistent groups**: keep Agent sessions, messages, working directories, Skills, knowledge references, images, and other attachments together in a local workspace.
|
||||
- **Concurrent Responses**: freeze one task snapshot for all selected Agents, collect independent replies, and commit completed responses in stable member order.
|
||||
- **Auto Discussion V4**: selected Agents produce independent proposals, challenge and negotiate a shared responsibility graph, execute dependency-aware work packages, converge through a single synthesis writer, and run independent verification.
|
||||
- **Harness control plane**: enforce context, permission, budget, recovery, phase, receipt, and commit boundaries without privately assigning responsibilities outside the negotiated plan.
|
||||
- **Evidence and traceability**: persist sanitized run traces and compact typed records for Artifacts, Evidence, Findings, and Adoption. Raw chain-of-thought, credentials, executable paths, and unrestricted tool output stay outside the renderer.
|
||||
- **Human-in-the-loop safety**: workspace writes are opt-in. Permission, budget, ambiguous writable outcomes, and review decisions can require an explicit Human Gate; human adoption is recorded separately as an outcome.
|
||||
- **Local-first context**: import validated local files and media, select bounded knowledge-source references, use target-scoped Skills, and configure compatible Providers without moving Meldwork conversations to a hosted service.
|
||||
|
||||
The collaboration mechanism is not a hidden preset A → B → C assignment. The user selects the participants; those Agents expose the solution space, negotiate responsibilities, and execute inside Harness-enforced context, permission, budget, recovery, and evidence boundaries.
|
||||
### Supported local Agent CLIs
|
||||
|
||||
The selected-Agent proposal, challenge, responsibility, work, integration, and verification loop is available today. Automatic participant selection from a broader roster, remote Agents, enterprise governance, and outcome-driven reputation remain future direction.
|
||||
Meldwork can detect and invoke these built-in local CLI profiles when the corresponding command is installed and compatible:
|
||||
|
||||
### Demo
|
||||
| Agent | Local command |
|
||||
| --- | --- |
|
||||
| Codex | `codex` |
|
||||
| Hermes | `hermes` |
|
||||
| OpenClaw | `openclaw` |
|
||||
| WorkBuddy | `codebuddy` |
|
||||
| Pi Agent | `pi`, `pi-agent`, or `piagent` |
|
||||
| Kimi Code | `kimi` |
|
||||
| MiMo Code | `mimo` |
|
||||
| Claude Code | `claude` |
|
||||
| Gemini CLI | `gemini` |
|
||||
| OpenCode | `opencode` |
|
||||
| Qwen Code | `qwen` |
|
||||
| OpenCodeReview | `ocr` |
|
||||
|
||||
Custom Agents and the local Agent Connector SDK provide explicit extension paths. Connector packages are content-addressed, approved by the user, and constrained by declared capabilities; see the [Agent Connector SDK](docs/agent-connector-sdk.md).
|
||||
|
||||
## When Meldwork fits
|
||||
|
||||
| Use Meldwork when you need | Use the native tool or another product when you need |
|
||||
| --- | --- |
|
||||
| independent viewpoints from several local Agents on one goal | one Agent and one work surface are enough |
|
||||
| concurrent responses or multi-round proposal, negotiation, work, and verification | a hosted team workspace or remote Agent fleet |
|
||||
| inspectable evidence, bounded run traces, and explicit acceptance | automatic participant selection from a large roster |
|
||||
| local files, Skills, knowledge references, and opt-in workspace writes | enterprise SSO, centralized governance, or organization-wide audit today |
|
||||
|
||||
Remote Agents, Cloud and Channel Connectors, automatic participant selection, enterprise governance, and an Outcome Network are outside the current public preview boundary. The preview is also not a commercial license; see [License](LICENSE) and [Commercial use](COMMERCIAL_USE.md).
|
||||
|
||||
## Workflow
|
||||
|
||||
1. **Discover and select** the local Agent CLIs you want to use.
|
||||
2. **Define context** with a working directory, prompt, validated files or media, Skills, and optional knowledge references.
|
||||
3. **Choose a mode**: direct conversation, Concurrent Responses, or Auto Discussion V4.
|
||||
4. **Review the trace**: inspect phase progress, Agent results, artifacts, evidence, and any Human Gate.
|
||||
5. **Decide what to adopt**. Meldwork does not silently write to the workspace or make the final decision for you.
|
||||
|
||||
## Demo
|
||||
|
||||
| Local Agent discovery | Direct multimodal work | Concurrent multi-Agent work |
|
||||
| --- | --- | --- |
|
||||
| [](assets/meldwork-agent-discovery.png) | [](assets/meldwork-direct-multimodal.png) | [](assets/meldwork-group-collaboration.png) |
|
||||
| See which supported Agents are ready. | Keep prompts, files, permissions, and compatible sessions together. | Run concurrent replies or an Agent-negotiated collaboration with the participants you selected. |
|
||||
| Check which supported Agents are ready. | Keep prompts, files, permissions, and compatible sessions together. | Run concurrent replies or an Agent-negotiated collaboration with the participants you selected. |
|
||||
|
||||
## What makes Meldwork different
|
||||
## How it differs from adjacent tools
|
||||
|
||||
### Harness design
|
||||
|
||||
The Harness is the control plane that keeps conversations, context, adapters, streams, and durable state aligned in one workspace. It is what makes a run continuous across sessions, timeouts, recovery, and Agent changes.
|
||||
|
||||
<p align="center">
|
||||
<img src="frontend/public/logos/Harness-readme.png" alt="Meldwork Harness" width="100%">
|
||||
</p>
|
||||
|
||||
This is a comparison of working models, not a feature-scorecard claiming Meldwork should replace every tool.
|
||||
|
||||
| Approach | Examples | Best at | Main tradeoff | Meldwork's choice |
|
||||
| --- | --- | --- | --- | --- |
|
||||
| One Agent CLI or AI IDE | Claude Code, Codex, Cursor, Windsurf | Deep work inside one Agent or product ecosystem | Moving to another Agent still requires a manual handoff | Preserve work across heterogeneous Agents |
|
||||
| Parallel coding-Agent managers | Superset, Vibe Kanban, Nimbalyst, Conductor | Running multiple coding tasks and isolated workspaces in parallel | Primarily optimized for throughput and code delivery | Optimize proposal quality, responsibility, evidence, and adoption |
|
||||
| Cloud Agent control planes | GitHub Agent HQ, Warp Oz, Devin, Factory, OpenHands Cloud | Dispatching and observing remote jobs, sandboxes, and Agent fleets | Work is organized around cloud or platform infrastructure | Start local-first and bring your existing Agents |
|
||||
| Programmable Agent frameworks | LangGraph, CrewAI, AutoGen, Agents SDK, ADK | Building custom graphs, roles, routing, and automation | Developers must design and maintain the orchestration | Deliver an organization and acceptance experience to users |
|
||||
| Multiple terminals and scripts | tmux, shell scripts, manual copy and paste | Maximum access to native Agent capabilities | The user becomes the router, context bus, and final judge | Make the work, boundaries, and decisions durable |
|
||||
| **Meldwork** | Supported local Agent CLIs; remote supply is direction | Concurrent independent responses and selected-Agent proposal, negotiation, responsibility, evidence, and verification | Local single-user preview today; participants are still selected by the user | Build the organization layer for the Agent workforce |
|
||||
|
||||
If one Agent and one work surface are enough, use the native tool. Use Meldwork when handoff, independent judgment, authority, evidence, and acceptance become part of the problem.
|
||||
| Category | Typical focus | Meldwork's scope |
|
||||
| --- | --- | --- |
|
||||
| One Agent CLI or AI IDE | Deep work inside one Agent ecosystem | Preserve context and decisions across heterogeneous local Agents |
|
||||
| Parallel coding-Agent manager | Throughput and isolated code tasks | Proposal quality, responsibility, evidence, and acceptance |
|
||||
| Cloud Agent control plane | Remote jobs, sandboxes, and Agent fleets | Local-first execution with the Agents already installed on your computer |
|
||||
| Programmable Agent framework | Developer-defined graphs, roles, and routing | A user-facing organization and review workflow around selected Agents |
|
||||
| Terminals and scripts | Direct access to native Agent capabilities | Durable context, boundaries, traces, and explicit human decisions |
|
||||
|
||||
## Install
|
||||
|
||||
### Packaged preview: Apple silicon macOS
|
||||
|
||||
The current release-validated target is Apple silicon macOS.
|
||||
|
||||
1. Open the [Meldwork V1.0.3 prerelease](https://github.com/Ryder-MHumble/Meldwork/releases/tag/Meldwork-V1.0.3).
|
||||
2. Download Meldwork-0.1.3-arm64.dmg.
|
||||
3. Drag Meldwork into Applications and try to open it once.
|
||||
4. This prerelease is ad-hoc signed, not signed with an Apple Developer ID, and not Apple-notarized. If macOS blocks it, open **System Settings → Privacy & Security**, find the Meldwork warning, choose **Open Anyway**, and confirm.
|
||||
5. Connect a supported Agent CLI already installed on the computer, or configure an independent Provider profile where supported.
|
||||
2. Download `Meldwork-0.1.3-arm64.dmg`.
|
||||
3. Drag Meldwork into Applications and open it once.
|
||||
4. This prerelease is ad-hoc signed, not signed with an Apple Developer ID, and not Apple-notarized. If macOS blocks it, open **System Settings -> Privacy & Security**, find the Meldwork warning, choose **Open Anyway**, and confirm.
|
||||
5. Install or connect at least one supported local Agent CLI, then let Meldwork detect it.
|
||||
|
||||
Use only artifacts downloaded from the official Release.
|
||||
Use only artifacts downloaded from the official GitHub Release.
|
||||
|
||||
<details>
|
||||
<summary><strong>Build from source</strong></summary>
|
||||
### Run from source
|
||||
|
||||
Requires Node.js 22.12 or newer and npm.
|
||||
Prerequisites: Node.js `22.12` or newer and npm.
|
||||
|
||||
~~~bash
|
||||
```bash
|
||||
npm --prefix frontend ci
|
||||
npm --prefix desktop ci
|
||||
npm --prefix desktop run dev
|
||||
~~~
|
||||
```
|
||||
|
||||
Run the repository checks before distributing a build:
|
||||
|
||||
~~~bash
|
||||
```bash
|
||||
npm --prefix frontend test
|
||||
npm --prefix frontend run build
|
||||
npm --prefix frontend run build:desktop
|
||||
npm --prefix desktop test
|
||||
~~~
|
||||
```
|
||||
|
||||
</details>
|
||||
For desktop-specific development, packaging, supported CLI details, and the provider matrix, see the [desktop guide](desktop/README.md).
|
||||
|
||||
## Trust boundaries
|
||||
## Trust boundaries and local data
|
||||
|
||||
- Conversations and Meldwork orchestration state stay local.
|
||||
- Model requests still follow the Agent and Provider you choose; local-first does not mean every model runs offline.
|
||||
- Credentials use operating-system-backed secure storage where supported.
|
||||
- Workspace writes are explicit and opt-in.
|
||||
- Raw chain-of-thought, executable paths, secrets, and unrestricted command output are not exposed to the renderer.
|
||||
- Cloud, Channel, automatic participant selection, enterprise governance, and an Outcome Network are not current release promises.
|
||||
- Conversations, groups, orchestration state, bounded run records, and imported attachment metadata stay in local Electron user data.
|
||||
- Agent execution, file access, attachment validation, Provider storage, Connector approval, and installer control remain in the Electron main process behind narrow preload APIs.
|
||||
- Provider API keys use operating-system-backed secure storage where supported; credentials and executable paths are not exposed to the renderer.
|
||||
- Workspace writes are explicit and opt-in. Agent CLIs and their configured model Providers remain external dependencies with their own data-handling terms.
|
||||
- Local-first does not mean every model runs offline: a selected Agent may still send prompts, attachments, or Skills to its configured Provider.
|
||||
|
||||
Read the [architecture](architecture.md) and [Agent Connector contract](docs/agent-connector-sdk.md) for the public technical boundary.
|
||||
Read the [architecture](architecture.md) and [security policy](SECURITY.md) for the complete boundary and known limitations.
|
||||
|
||||
## Documentation and contribution
|
||||
|
||||
- [Architecture and product boundary](architecture.md)
|
||||
- [Desktop setup, Agent matrix, and packaging](desktop/README.md)
|
||||
- [Agent Connector SDK](docs/agent-connector-sdk.md)
|
||||
- [AI discoverability index](docs/ai-discoverability.md)
|
||||
- [Contributing](CONTRIBUTING.md)
|
||||
- [Security policy](SECURITY.md)
|
||||
- [Changelog](CHANGELOG.md)
|
||||
|
||||
## License
|
||||
|
||||
Meldwork is source-available under the [Meldwork Non-Commercial Source License](LICENSE). You may inspect, run, modify, and share it for non-commercial purposes. Commercial use requires prior written permission; see [COMMERCIAL_USE.md](COMMERCIAL_USE.md).
|
||||
Meldwork is source-available under the [Meldwork Non-Commercial Source License](LICENSE). It is not open source in the OSI sense. You may inspect, run, modify, and share it for non-commercial purposes. Commercial use requires prior written permission; see [COMMERCIAL_USE.md](COMMERCIAL_USE.md).
|
||||
+103
-65
@@ -14,115 +14,153 @@
|
||||
<a href="README.md">English</a> · <strong>简体中文</strong>
|
||||
</p>
|
||||
|
||||
# Meldwork 为 AI Agent 构建组织层
|
||||
# Meldwork：Local-first 多 Agent 协作工作空间
|
||||
|
||||
**多数工具是在帮人类管更多 Agent；Meldwork 解决的是另一件事：让多 Agent 协作变得可见、可追责、可复用。**
|
||||
> Meldwork 是一个 Local-first Electron 桌面工作空间，用于多 Agent 协作与 Agent 编排。它把受支持的本地 Agent CLI 放进同一个 AI Agent 工作空间，支持并发或协商式工作，保留可检查的 Evidence，并在工作区写入和采用决定之前让人类保持在环（human-in-the-loop）。
|
||||
|
||||
当前预览版是一个面向已支持本地 Agent CLI 的本地工作单元。它把参与者、上下文、协作边界、运行状态和人类复核放在同一个工作空间里。已选 Agent 现在可以并发回复，也可以围绕同一目标先独立提案、再协商职责、分工执行、单写者整合并由其他 Agent 独立复核。
|
||||
Meldwork 是一个源码可见（source-available）的 Local-first 桌面应用，面向已经使用多个 AI 编程或研究 Agent 的用户。当前公开预览版是单用户工作单元：由你选择参与者、工作目录、上下文和最终决定。Meldwork 不要求服务器、账号或远程对话存储。
|
||||
|
||||
<p align="center">
|
||||
<a href="https://github.com/Ryder-MHumble/Meldwork/releases/download/Meldwork-V1.0.3/Meldwork-0.1.3-arm64.dmg"><strong>下载 Meldwork V1.0.3 Apple 芯片 macOS 版</strong></a>
|
||||
<a href="https://github.com/Ryder-MHumble/Meldwork/releases/tag/Meldwork-V1.0.3"><strong>下载 V1.0.3 Apple 芯片 macOS 预览版</strong></a>
|
||||
· <a href="architecture.md">架构</a>
|
||||
· <a href="desktop/README.md">桌面端指南</a>
|
||||
· <a href="LICENSE">许可证</a>
|
||||
</p>
|
||||
|
||||
## Agent workforce 缺少的那一层
|
||||
## 它解决什么问题？
|
||||
|
||||
Agent 的供给正在快速增长，但围绕它们工作的组织能力并没有跟上。
|
||||
同时使用多个 Agent，通常意味着手动选择工具、在终端之间搬运上下文、处理互相冲突的答案，并记住最终为什么采用某个结果。Meldwork 提供单个 Agent 与最终决定之间的组织层：
|
||||
|
||||
今天，人类仍然需要自己选 Agent、搬运上下文、解释角色、处理冲突答案，并承担最终责任。并行管理器优化吞吐量，多 Agent 框架让开发者编写 Workflow，单 Agent 产品优化一个 Worker。
|
||||
- 一个共享 Goal 和明确的验收边界；
|
||||
- 独立提案，而不是隐藏路由；
|
||||
- 声明式的权限、责任、交接、依赖和停止条件；
|
||||
- 可持续复核的 Artifact 与 Evidence，不因切换 Agent 而消失；
|
||||
- 由人类掌握的权限、预算、写入和采用决定。
|
||||
|
||||
Meldwork 关注的是中间那层工作：
|
||||
## 核心能力
|
||||
|
||||
- 一个共享 Goal 和明确验收边界；
|
||||
- 独立判断，而不是隐藏路由；
|
||||
- 明确的权限、责任、交接和停止条件；
|
||||
- 不随 Agent 切换而丢失的 Artifact 与 Evidence；
|
||||
- 由人类掌握的最终采用决定。
|
||||
### 多 Agent 协作与 Agent 编排
|
||||
|
||||
- **直接会话和持久群组**：在本地工作空间中保留 Agent Session、消息、工作目录、Skill、知识引用、图片和其他附件。
|
||||
- **并发回复（Concurrent Responses）**：为全部已选 Agent 冻结同一份任务快照，收集独立回复，再按稳定的成员顺序提交完成结果。
|
||||
- **Auto Discussion V4**：已选 Agent 先独立提案，再交叉质询并协商一张共享职责图，按依赖执行工作包，由单一整合写入者收敛结果，最后独立复核。
|
||||
- **Harness 控制平面**：约束上下文、权限、预算、恢复、阶段、回执和提交边界；不会绕过协商计划在模型之外私自分配职责。
|
||||
- **Evidence 与可追溯性**：持久化经过脱敏的运行轨迹，以及 Artifact、Evidence、Finding 和 Adoption 等紧凑类型化记录。Raw chain-of-thought、凭据、可执行路径和不受限工具输出不会进入渲染层。
|
||||
- **Human-in-the-loop 安全控制**：工作区写入默认关闭。权限、预算、存在歧义的写入结果和评审决定可以要求显式 Human Gate；人类采用结果会作为独立 Outcome 记录。
|
||||
- **Local-first 上下文**：导入经过校验的本地文件和媒体，选择有边界的知识源引用，使用面向目标 Agent 的 Skill，并为兼容 Agent 配置 Provider；Meldwork 对话不会迁移到托管服务。
|
||||
|
||||
## Meldwork 正在构建什么
|
||||
### 当前支持的本地 Agent CLI
|
||||
|
||||
当前协作机制不是 Harness 暗中预设的 A → B → C 分配链。用户选定参与者后，Agent 先展开解空间、自主协商职责，再在 Harness 管理的上下文、权限、预算、恢复和证据边界内执行。
|
||||
当对应命令已安装且兼容时，Meldwork 可以检测并调用以下内置本地 CLI profile：
|
||||
|
||||
已选 Agent 的独立提案、交叉质询、职责协商、分工执行、整合和复核现在已经可用。从更大候选池自动选人组队、远程 Agent、企业治理和 Outcome 驱动的声誉系统仍是未来方向。
|
||||
| Agent | 本地命令 |
|
||||
| --- | --- |
|
||||
| Codex | `codex` |
|
||||
| Hermes | `hermes` |
|
||||
| OpenClaw | `openclaw` |
|
||||
| WorkBuddy | `codebuddy` |
|
||||
| Pi Agent | `pi`、`pi-agent` 或 `piagent` |
|
||||
| Kimi Code | `kimi` |
|
||||
| MiMo Code | `mimo` |
|
||||
| Claude Code | `claude` |
|
||||
| Gemini CLI | `gemini` |
|
||||
| OpenCode | `opencode` |
|
||||
| Qwen Code | `qwen` |
|
||||
| OpenCodeReview | `ocr` |
|
||||
|
||||
### 效果演示
|
||||
Custom Agent 和本地 Agent Connector SDK 提供明确的扩展路径。Connector package 采用内容寻址，由用户批准，并受声明能力约束；详见 [Agent Connector SDK](docs/agent-connector-sdk.md)。
|
||||
|
||||
| 本地 Agent 检测 | 单聊中的多模态工作 | 并发多 Agent 协作 |
|
||||
## 适用场景与不适用场景
|
||||
|
||||
| 适合在这些场景使用 Meldwork | 这些需求应优先选择原生工具或其他产品 |
|
||||
| --- | --- |
|
||||
| 需要多个本地 Agent 针对同一目标给出独立判断 | 一个 Agent 和一个工作面已经足够 |
|
||||
| 需要并发回复，或提案、协商、执行、复核等多轮流程 | 需要托管式团队工作空间或远程 Agent Fleet |
|
||||
| 需要可检查的 Evidence、受边界约束的运行轨迹和明确验收 | 需要从大型候选池自动选人组队 |
|
||||
| 需要本地文件、Skill、知识引用和显式开启的工作区写入 | 当前就需要企业 SSO、集中治理或组织级审计 |
|
||||
|
||||
远程 Agent、Cloud 和 Channel Connector、自动选人组队、企业治理以及 Outcome Network 不在当前公开预览边界内。本预览版也不等于商业授权；请查看[许可证](LICENSE)和[商业使用说明](COMMERCIAL_USE.md)。
|
||||
|
||||
## 使用流程
|
||||
|
||||
1. **检测并选择**要使用的本地 Agent CLI。
|
||||
2. **定义上下文**：设置工作目录、Prompt、经过校验的文件或媒体、Skill 和可选知识引用。
|
||||
3. **选择模式**：直接会话、并发回复或 Auto Discussion V4。
|
||||
4. **检查轨迹**：查看阶段进度、Agent 结果、Artifact、Evidence 和待处理的 Human Gate。
|
||||
5. **决定是否采用**。Meldwork 不会静默写入工作区，也不会替你做最终决定。
|
||||
|
||||
## 效果演示
|
||||
|
||||
| 本地 Agent 检测 | 直接会话中的多模态工作 | 并发多 Agent 工作 |
|
||||
| --- | --- | --- |
|
||||
| [](assets/meldwork-agent-discovery.png) | [](assets/meldwork-direct-multimodal.png) | [](assets/meldwork-group-collaboration.png) |
|
||||
| 查看哪些受支持 Agent 已就绪。 | Prompt、文件、权限和兼容 Session 留在一起。 | 让已选 Agent 并发回复，或进入由 Agent 自主协商职责的协作流程。 |
|
||||
| [](assets/meldwork-agent-discovery.png) | [](assets/meldwork-direct-multimodal.png) | [](assets/meldwork-group-collaboration.png) |
|
||||
| 查看哪些受支持 Agent 已就绪。 | 让 Prompt、文件、权限和兼容 Session 保持在一起。 | 运行并发回复，或让已选择的 Agent 自主协商协作方式。 |
|
||||
|
||||
## 与相邻工具的区别
|
||||
|
||||
## Meldwork 和别的产品有什么区别
|
||||
|
||||
### Harness设计
|
||||
|
||||
Harness 是把会话、上下文、适配器、流和持久化状态拴在一起的控制平面。它让一次任务可以跨会话、超时、恢复和 Agent 切换继续下去。
|
||||
|
||||
<p align="center">
|
||||
<img src="frontend/public/logos/Harness-readme.png" alt="Meldwork Harness" width="100%">
|
||||
</p>
|
||||
|
||||
这张表比较的是不同工作范式，不是一张声称 Meldwork 应当替代所有工具的功能勾选表。
|
||||
|
||||
| 范式 | 例子 | 最擅长什么 | 主要代价 | Meldwork 的选择 |
|
||||
| --- | --- | --- | --- | --- |
|
||||
| 单 Agent CLI / AI IDE | Claude Code、Codex、Cursor、Windsurf | 在一个 Agent 或产品生态内完成深度工作 | 换 Agent 时仍需手工交接 | 保留跨异构 Agent 的工作 |
|
||||
| 并行 Coding-Agent 工作台 | Superset、Vibe Kanban、Nimbalyst、Conductor | 并行运行多个 Coding 任务和隔离工作区 | 主要优化吞吐量和代码交付 | 优化方案质量、责任、证据和采用 |
|
||||
| Cloud Agent 控制面 | GitHub Agent HQ、Warp Oz、Devin、Factory、OpenHands Cloud | 派发和观察远程 Job、Sandbox 与 Agent Fleet | 工作围绕云基础设施和平台边界 | 先从 Local-first 和 BYO Agent 切入 |
|
||||
| 可编程多 Agent 框架 | LangGraph、CrewAI、AutoGen、Agents SDK、ADK | 开发者自定义 Graph、角色、路由和自动化 | 需要开发者设计并维护编排 | 面向使用者交付组织与验收体验 |
|
||||
| 多终端与脚本 | tmux、Shell、手工复制粘贴 | 最大化原生 Agent 访问权 | 人类成为 Router、Context Bus 和最终裁决者 | 让工作、边界和决定保持持续 |
|
||||
| **Meldwork** | 已支持本地 Agent CLI；远程供给属于方向 | 并发独立回复，以及已选 Agent 之间的提案、协商、责任、Evidence 和复核 | 当前仍是本地单用户预览；参与者仍由用户选定 | 构建 Agent workforce 的组织层 |
|
||||
|
||||
如果一个 Agent 和一个工作面已经足够，直接使用原生工具。只有当交接、独立判断、权限、证据和验收成为问题时，才需要 Meldwork。
|
||||
| 类别 | 通常关注什么 | Meldwork 的范围 |
|
||||
| --- | --- | --- |
|
||||
| 单 Agent CLI 或 AI IDE | 在一个 Agent 生态中完成深度工作 | 让上下文和决定跨异构本地 Agent 保持连续 |
|
||||
| 并行 Coding-Agent 工作台 | 吞吐量和隔离的代码任务 | 方案质量、责任、Evidence 和验收 |
|
||||
| Cloud Agent 控制平面 | 远程 Job、Sandbox 和 Agent Fleet | Local-first 执行，使用电脑上已经安装的 Agent |
|
||||
| 可编程 Agent 框架 | 开发者定义 Graph、角色和路由 | 面向使用者的 Agent 组织与复核工作流 |
|
||||
| 多终端与脚本 | 直接访问原生 Agent 能力 | 持久上下文、边界、轨迹和明确的人类决定 |
|
||||
|
||||
## 安装
|
||||
|
||||
### Apple 芯片 macOS 打包预览版
|
||||
|
||||
当前经过发布验证的目标是 Apple 芯片 macOS。
|
||||
|
||||
1. 打开 [Meldwork V1.0.3 预发布页](https://github.com/Ryder-MHumble/Meldwork/releases/tag/Meldwork-V1.0.3)。
|
||||
2. 下载 Meldwork-0.1.3-arm64.dmg。
|
||||
3. 将 Meldwork 拖入“应用程序”，然后先尝试打开一次。
|
||||
4. 当前预发布版使用临时签名，没有 Apple Developer ID 签名，也尚未经过 Apple 公证。如果 macOS 阻止启动，请打开“系统设置 → 隐私与安全性”，找到 Meldwork 提示，点击“仍要打开”并确认。
|
||||
5. 连接电脑上已安装的受支持 Agent CLI，或在兼容情况下单独配置 Provider。
|
||||
2. 下载 `Meldwork-0.1.3-arm64.dmg`。
|
||||
3. 将 Meldwork 拖入“应用程序”，然后打开一次。
|
||||
4. 当前预发布版使用 ad-hoc 临时签名，没有 Apple Developer ID 签名，也没有经过 Apple 公证。如果 macOS 阻止启动，请打开“系统设置 -> 隐私与安全性”，找到 Meldwork 提示，选择“仍要打开 / Open Anyway”并确认。
|
||||
5. 至少安装或连接一个受支持的本地 Agent CLI，然后让 Meldwork 执行检测。
|
||||
|
||||
请只使用官方 Release 下载的产物。
|
||||
请只使用官方 GitHub Release 下载的产物。
|
||||
|
||||
<details>
|
||||
<summary><strong>从源码运行</strong></summary>
|
||||
### 从源码运行
|
||||
|
||||
需要 Node.js 22.12 或更高版本以及 npm。
|
||||
前置条件：Node.js `22.12` 或更高版本以及 npm。
|
||||
|
||||
~~~bash
|
||||
```bash
|
||||
npm --prefix frontend ci
|
||||
npm --prefix desktop ci
|
||||
npm --prefix desktop run dev
|
||||
~~~
|
||||
```
|
||||
|
||||
分发前运行：
|
||||
分发前运行仓库检查：
|
||||
|
||||
~~~bash
|
||||
```bash
|
||||
npm --prefix frontend test
|
||||
npm --prefix frontend run build
|
||||
npm --prefix frontend run build:desktop
|
||||
npm --prefix desktop test
|
||||
~~~
|
||||
```
|
||||
|
||||
</details>
|
||||
桌面端开发、打包、完整 Agent 矩阵和 Provider 配置见[桌面端指南](desktop/README.md)。
|
||||
|
||||
## 信任边界
|
||||
## 信任边界与本地数据
|
||||
|
||||
- Meldwork 会话和编排状态保存在本地。
|
||||
- 模型请求仍然按照你选择的 Agent 和 Provider 发出；Local-first 不等于所有模型离线运行。
|
||||
- 兼容环境使用操作系统安全存储保存凭据。
|
||||
- 工作目录写入必须显式开启。
|
||||
- Renderer 不暴露 raw chain-of-thought、可执行路径、Secret 或不受限命令输出。
|
||||
- Cloud、Channel、自动选人组队、企业治理和 Outcome Network 不是当前发布承诺。
|
||||
- 对话、群组、编排状态、受边界约束的运行记录和附件元数据保存在本地 Electron 用户数据中。
|
||||
- Agent 执行、文件访问、附件校验、Provider 存储、Connector 审批和安装器控制都在 Electron 主进程中完成，并通过窄化的 preload API 暴露能力。
|
||||
- Provider API Key 在兼容环境中使用操作系统安全存储；凭据和可执行路径不会暴露给渲染层。
|
||||
- 工作区写入必须显式开启。Agent CLI 及其配置的模型 Provider 仍是外部依赖，各自适用自己的数据处理条款。
|
||||
- Local-first 不等于所有模型都离线运行：选定的 Agent 仍可能把 Prompt、附件或 Skill 发送到其配置的 Provider。
|
||||
|
||||
公开技术边界见[架构](architecture.md)和 [Agent Connector 契约](docs/agent-connector-sdk.md)。
|
||||
完整边界和已知限制见[架构说明](architecture.md)与[安全策略](SECURITY.md)。
|
||||
|
||||
## 文档与贡献
|
||||
|
||||
- [架构与产品边界](architecture.md)
|
||||
- [桌面端设置、Agent 矩阵和打包](desktop/README.md)
|
||||
- [Agent Connector SDK](docs/agent-connector-sdk.md)
|
||||
- [AI 可发现性索引](docs/ai-discoverability.md)
|
||||
- [贡献指南](CONTRIBUTING.md)
|
||||
- [安全策略](SECURITY.md)
|
||||
- [变更记录](CHANGELOG.md)
|
||||
|
||||
## 许可证
|
||||
|
||||
Meldwork 采用 [Meldwork 非商用源码许可](LICENSE)。你可以为非商用目的查看、运行、修改和分享；商业使用需要事先书面许可，详见 [COMMERCIAL_USE.md](COMMERCIAL_USE.md)。
|
||||
Meldwork 采用 [Meldwork 非商用源码许可](LICENSE)。它不是 OSI 意义上的开源许可证。你可以为非商用目的查看、运行、修改和分享；商业使用需要事先书面许可，详见[商业使用说明](COMMERCIAL_USE.md)。
|
||||
@@ -0,0 +1,123 @@
|
||||
# Meldwork AI Discoverability Index
|
||||
|
||||
This page is a factual index for search systems and AI assistants. Statements below are based on the repository source and documentation; they do not describe capabilities that are not implemented here.
|
||||
|
||||
## Canonical identity
|
||||
|
||||
- **Project:** Meldwork
|
||||
- **Type:** Local-first Electron desktop application with a Vue renderer (`desktop/package.json`, `frontend/package.json`, `desktop/src/main.cjs`, `frontend/src/main.js`).
|
||||
- **Primary subject:** A local workspace for direct conversations and user-selected multi-Agent conversations. The Electron main process discovers and invokes local Agent CLIs, while the renderer receives a constrained preload API.
|
||||
- **Runtime boundary:** Conversations, orchestration state, run checkpoints, attachments, Skill snapshots, Provider metadata, and selected knowledge-source state are stored locally. The repository does not require an application server, account/tenant system, or Meldwork-hosted remote conversation store (`architecture.md`).
|
||||
- **Repository terms:** local-first AI workspace; multi-Agent collaboration; Agent CLI orchestration; Electron desktop; Vue renderer; Harness; evidence-aware runs; human-in-the-loop decisions; Agent Connector SDK.
|
||||
|
||||
## Search intents this repository answers
|
||||
|
||||
Use these phrases when looking for this project or related implementation evidence:
|
||||
|
||||
- local-first multi-Agent desktop workspace / 本地优先多 Agent 桌面工作空间
|
||||
- Electron app for multiple AI Agent CLIs / Electron 多 AI Agent CLI 客户端
|
||||
- direct and group AI Agent conversations / AI Agent 直接会话与群聊
|
||||
- concurrent multi-Agent responses with frozen context / 共享快照与并发 Agent 回复
|
||||
- Auto Discussion V4 proposal, challenge, responsibility, synthesis, verification / 多 Agent 提案、质询、职责协商、整合与复核
|
||||
- Agent Client Protocol (ACP) desktop integration / ACP（Agent Client Protocol）桌面集成
|
||||
- JSONL and stream-json Agent runtime normalization / JSONL、stream-json Agent 事件归一化
|
||||
- local Agent Connector SDK with content-addressed manifests / 内容寻址的本地 Agent Connector SDK
|
||||
- durable sanitized run ledger, evidence-aware runs, and human-in-the-loop Human Gate recovery / 脱敏运行账本、Evidence-aware 运行与 human-in-the-loop 人类审批门恢复
|
||||
- local Skills, image/file attachments, Provider profiles, and Obsidian knowledge selection / 本地 Skill、附件、Provider 与 Obsidian 知识源
|
||||
- deterministic local Eval Harness for Agent workflows / 本地确定性 Agent Eval Harness
|
||||
|
||||
## Main execution path
|
||||
|
||||
1. Electron starts at `desktop/src/main.cjs` and loads the built renderer through a local `file:` document.
|
||||
2. `desktop/src/preload.cjs` exposes the named `window.meldworkDesktop` IPC surface; the renderer does not receive arbitrary filesystem, shell, executable-path, credential, or native-session access.
|
||||
3. `desktop/src/agents/cli/cli-discovery.cjs` scans fixed executable names and known platform paths. `desktop/src/agents/cli/cli-adapters.cjs` validates capability and invokes the selected executable using code-defined arguments.
|
||||
4. `desktop/src/workspace/local-workspace.cjs` coordinates conversations, direct/group targets, session references, persistence, and run lifecycle. `local-workspace-message-submission.cjs` accepts a message and starts direct, manual, or automatic execution.
|
||||
5. `desktop/src/agents/cli/cli-output-parsers.cjs` and `cli-runtime-event-mappers.cjs` reduce Agent output to final text, bounded status/progress, plans/reasoning summaries where available, tool lifecycle summaries, terminal outcomes, and a main-only session reference.
|
||||
6. `desktop/src/runs/run-ledger.cjs`, `run-scheduler.cjs`, and `failure-policy.cjs` checkpoint bounded sanitized state, enforce budgets/limits, classify failures, and support stop/recovery semantics.
|
||||
7. `frontend/src/App.vue`, `frontend/src/components/ConversationTimelineView.vue`, and `RunTracePanel.vue` render messages and sanitized run events. Final messages and compact evidence are persisted in the local workspace.
|
||||
|
||||
## Collaboration modes
|
||||
|
||||
- **Direct conversation:** One selected Agent with conversation-and-Agent session continuity when the adapter supports it.
|
||||
- **Concurrent Responses (`manual`):** A selected group runs from one frozen task snapshot; selected members are retained and results are published in stable member order after the batch barrier (`architecture.md`, `docs/flows.md`).
|
||||
- **Auto Discussion (`auto`, V4 `discussion`):** Selected Agents produce independent proposals, challenge and negotiate one normalized responsibility plan, execute dependency-aware work packages, use one synthesis writer when workspace writes are enabled, and independently verify the candidate. The Harness validates receipts, permissions, watermarks, Human Gates, and idempotent commits; it does not privately assign roles (`desktop/src/collaboration/orchestration-v4-records.cjs`, `desktop/src/workspace/local-workspace-auto-runner.cjs`).
|
||||
- **Context:** Messages may carry up to four target-scoped Skill snapshots and up to four knowledge-source selections. Attachment validation and per-Agent image limits occur before execution (`docs/automation.md`, `docs/flows.md`).
|
||||
|
||||
## Built-in Agent adapters and wire protocols
|
||||
|
||||
The fixed catalog is defined in `desktop/src/agents/cli/cli-discovery.cjs`. Command aliases are discovery names, not claims that the executable is bundled.
|
||||
|
||||
| Agent kind | Display name / command aliases | Invocation or event protocol in code | Runtime notes |
|
||||
| --- | --- | --- | --- |
|
||||
| `codex` | Codex / `codex` | Codex App Server JSONL (`codex exec --json`) | Streaming answer deltas, plans, reasoning, tool start/result, sessions; read-only or workspace-write sandbox. |
|
||||
| `hermes` | Hermes / `hermes` | ACP JSON-RPC (`hermes acp`), with legacy terminal-text fallback (`hermes chat --quiet`) | Session continuity; legacy path includes result recovery from a local message watermark when available. |
|
||||
| `openclaw` | OpenClaw / `openclaw` | ACP JSON-RPC (`openclaw ... acp`), with legacy terminal-document JSON fallback | Managed local runtime and explicit tool policy; live behavior depends on the installed CLI and Provider. |
|
||||
| `workbuddy` | WorkBuddy / `codebuddy` | `stream-json` invocation with bounded nested turn count | Read-only/plan or workspace-write/acceptEdits permission mode; session resume supported by the invocation. |
|
||||
| `pi` | Pi Agent / `pi`, `pi-agent`, `piagent` | Pi JSONL (`--mode json --print`) | Streaming answer, reasoning, and tool lifecycle events; session resume supported. |
|
||||
| `kimi` | Kimi / `kimi` | ACP `plan` mode for read-only; native `stream-json --prompt` for workspace-write | The two permission paths use different transports. |
|
||||
| `mimo` | MiMo / `mimo` | ACP JSON-RPC (`mimo acp --pure`), JSON fallback (`mimo run --format json`) | Plan/build mode follows permission; session resume supported. |
|
||||
| `claude` | Claude Code / `claude` | Anthropic-style `stream-json` | Streaming answer, reasoning, plans, tool lifecycle, and session resume. |
|
||||
| `gemini` | Gemini CLI / `gemini` | Gemini `stream-json` | Streaming answer and tool start/result events; session resume supported. |
|
||||
| `opencode` | OpenCode / `opencode` | ACP JSON-RPC (`opencode acp --pure`), JSON fallback (`opencode run --format json`) | Plan/build mode follows permission; session resume supported; image/file arguments are validated. |
|
||||
| `qwen` | Qwen Code / `qwen` | Anthropic-style `stream-json` | Plan/auto-edit approval mode; optional configured Provider and session resume. |
|
||||
| `opencodereview` | OpenCodeReview / `ocr` | Terminal JSON document (`ocr review --format json`) | Read-only code-review adapter; output is final text/evidence without session or tool lifecycle events. |
|
||||
|
||||
The event profile mapping is explicit in `desktop/src/agents/cli/cli-event-profiles.cjs`; ACP transport is implemented in `desktop/src/agents/cli/cli-acp-runner.cjs`. The runtime capability contract (`desktop/src/agents/agent-runtime-contract.cjs`) recognizes domains including `software-development`, `software-review`, `research`, `document-production`, `tool-use`, and `automation`, input types including text/image/audio/video/file/structured-data, and permission modes `read-only` and `workspace-write`.
|
||||
|
||||
Custom local Agents are also supported through `desktop/src/agents/custom-agent-contract.cjs` and `custom-agent-store.cjs`. A custom definition uses an absolute executable path, allowlisted arguments, and either `stdin` or `argument` prompt mode; custom execution currently requires `workspace-write` and is not part of the fixed built-in protocol table.
|
||||
|
||||
## Core modules and public technical documents
|
||||
|
||||
| Area | Source of truth |
|
||||
| --- | --- |
|
||||
| Electron bootstrap, IPC trust boundary, persistence wiring | `desktop/src/main.cjs`, `desktop/src/shell/main-ipc.cjs`, `desktop/src/preload.cjs` |
|
||||
| Vue renderer and desktop lifecycle | `frontend/src/main.js`, `frontend/src/App.vue`, `frontend/src/desktop.js` |
|
||||
| Agent discovery, invocation, parsing, runtime events | `desktop/src/agents/cli/cli-discovery.cjs`, `cli-invocations.cjs`, `cli-adapters.cjs`, `cli-output-parsers.cjs`, `cli-runtime-event-mappers.cjs` |
|
||||
| Conversations, Context Packs, sessions, message submission | `desktop/src/workspace/local-workspace.cjs`, `local-workspace-context-packs.cjs`, `local-workspace-message-submission.cjs` |
|
||||
| V4 orchestration and recovery | `desktop/src/collaboration/orchestration-v4-records.cjs`, `desktop/src/workspace/local-workspace-auto-runner.cjs`, `desktop/src/runs/run-ledger.cjs` |
|
||||
| Agent Connector packages | `desktop/src/agents/connectors/`, `docs/agent-connector-sdk.md` |
|
||||
| Local Skill discovery and trust | `desktop/src/skills/`, `docs/local-skill-contracts.md` |
|
||||
| Knowledge sources | `desktop/src/knowledge/`, `docs/flows.md` |
|
||||
| Optional Cloud/Channel runtimes | `desktop/src/agents/cloud/`, `desktop/src/channels/`, `docs/integrations/cloud-agent-bridge.md`, `docs/automation.md` |
|
||||
| Tests and CI | `desktop/test/`, `frontend/src/__tests__/meldwork/`, `.github/workflows/ci.yml`, `docs/tests.md` |
|
||||
|
||||
## Installation and verification commands
|
||||
|
||||
Prerequisite: Node.js `>=22.12.0` and npm (`desktop/package.json`, `frontend/package.json`). From the repository root:
|
||||
|
||||
```bash
|
||||
npm --prefix frontend ci
|
||||
npm --prefix desktop ci
|
||||
npm --prefix desktop run dev
|
||||
```
|
||||
|
||||
Focused and full checks:
|
||||
|
||||
```bash
|
||||
npm --prefix frontend test
|
||||
npm --prefix frontend run build
|
||||
npm --prefix frontend run build:desktop
|
||||
npm --prefix desktop test:agents
|
||||
npm --prefix desktop test:runs
|
||||
npm --prefix desktop test:workspace
|
||||
npm --prefix desktop test:security
|
||||
npm --prefix desktop test
|
||||
npm --prefix desktop run eval:deterministic
|
||||
npm --prefix desktop run connector:conformance
|
||||
npm --prefix desktop run pack
|
||||
```
|
||||
|
||||
`desktop/test/README.md` documents suite discovery. CI runs frontend tests/builds on Ubuntu and desktop tests, deterministic Eval Harness, and Electron packaging on macOS (`.github/workflows/ci.yml`).
|
||||
|
||||
## Boundaries and explicit non-goals
|
||||
|
||||
- The current packaged release target is Apple silicon macOS. The V1.0.3 prerelease is ad-hoc signed, not Apple Developer ID signed or notarized (`docs/releases/Meldwork-V1.0.3.md`, `docs/tests.md`).
|
||||
- Automatic participant selection from a larger roster, cross-user remote collaboration, enterprise RBAC/governance, a production Cloud/Channel Agent service, and an Outcome Network are outside the current release boundary.
|
||||
- Cloud and Channel Connector runtimes exist as optional main-process contracts, but no concrete Cloud or Channel Connector is enabled by default. The documented SSH bridge currently supports Codex read-only only; remote writes, attachments, and session resume are not supported (`docs/integrations/cloud-agent-bridge.md`).
|
||||
- Agent output and model access depend on the locally installed CLI, authentication, Provider, declared capabilities, and upstream protocol behavior. Repository fixtures and unit tests do not certify every Agent installation, version, operating system, or live Provider.
|
||||
- Workspace writes default to disabled. Agent processes run with the local operating-system user's permissions; permission flags and read-only instructions are not an OS sandbox (`architecture.md`, `docs/permissions.md`).
|
||||
- The repository is source-available under the **Meldwork Non-Commercial Source License 1.0**. Commercial use requires prior written permission (`LICENSE`, `COMMERCIAL_USE.md`).
|
||||
|
||||
## Aliases and keyword index
|
||||
|
||||
`Meldwork`, `meldwork`, `local-first AI workspace`, `multi-Agent collaboration`, `multi-agent orchestration`, `AI Agent work cell`, `Electron Agent desktop`, `Vue Agent workspace`, `Agent CLI manager`, `evidence-aware`, `human-in-the-loop`, `Codex`, `Hermes`, `OpenClaw`, `WorkBuddy`, `Pi Agent`, `Kimi Code`, `MiMo Code`, `Claude Code`, `Gemini CLI`, `OpenCode`, `Qwen Code`, `OpenCodeReview`, `ACP`, `Agent Client Protocol`, `JSONL`, `stream-json`, `Agent Connector SDK`, `Context Pack`, `Run Ledger`, `Human Gate`, `Auto Discussion V4`, `Concurrent Responses`, `frozen task snapshot`, `responsibility graph`, `typed Artifact`, `Evidence`, `Skill snapshot`, `Provider profile`, `Obsidian knowledge source`, `local Electron multi-agent app`, `本地优先`, `多 Agent 协作`, `Agent CLI 编排`, `桌面端 Agent 工作空间`, `多 Agent 群聊`, `并发回复`, `自动讨论`, `职责协商`, `运行账本`, `人类审批门`, `Agent 连接器 SDK`.
|
||||
Reference in new issue
Block a user