docs: add Agent future trend analysis to doc 13

Add predictions about Agent platform evolution based on Claude Code
source analysis and OpenClaw design philosophy comparison, covering
cross-session memory, native channel integration, lowering usage
barriers, and professional modes for advanced users.

Author: anneheartrecord

docs/13-Source-Code-Findings.md

@@ -101,6 +101,26 @@ This telemetry data is sent to Anthropic's backend. While model inference happen
 - Don't share accounts
 - Keep your usage patterns similar to a normal user: work and rest, don't go 24/7 non-stop
 
+## The Future Direction of Agents
+
+After thoroughly analyzing this source code, and combining it with my own experience building TME-Claw (an enterprise Agent platform based on OpenClaw), I have some predictions about where Agents are heading.
+
+**Claude Code is evolving toward a platform, and its evolutionary path overlaps heavily with the design philosophy of Agent platforms like OpenClaw.**
+
+The most obvious signal: cross-session memory. The MEMORY.md mechanism in the source code has already implemented a basic version of cross-session memory persistence. The EXTRACT_MEMORIES and TEAMMEM feature flags indicate Anthropic is working on two things — automatic memory extraction and team memory sharing. This aligns perfectly with OpenClaw's design philosophy: an Agent shouldn't start as a blank slate every time it launches. It needs to remember who the user is, what they prefer, and where things left off last time. OpenClaw achieved instance-level state persistence through COS storage early on. Claude Code is now heading in the same direction, just via a different path — one uses the file system, the other uses object storage.
+
+The second signal is native channel integration. On March 20, 2025, Claude gained the ability to connect to Telegram through MCP plugins. This means the Agent is no longer confined to a terminal waiting for users to come to it — it can proactively exist within the communication tools users already use daily. OpenClaw was designed around channels from day one — WeChat, WeCom, Slack, Discord. Where the Agent lives depends on where the user is. Claude Code is now beginning to understand this. It's foreseeable that Claude Code will natively support more channels in the future, rather than just bridging through MCP. WhatsApp, Line, Lark — these are all just a matter of time.
+
+The third signal is the continuous lowering of the usage barrier. Looking at Claude Code's product iteration trajectory: from manually configuring API keys to one-click login, from pure CLI to VS Code integration, from manually writing CLAUDE.md to automatic memory extraction. Every step lowers the bar. The ultimate goal is clear: **let people who don't understand technology get things done with an Agent.** OpenClaw's Skills marketplace is the ultimate expression of this philosophy — users don't need to understand prompt engineering; they just pick a ready-made Skill and use it. Claude Code's Skills system is already doing the same thing.
+
+But lowering the barrier doesn't mean sacrificing the ceiling. This is the fourth prediction: **for advanced users, Agent platforms will provide increasingly more professional modes.**
+
+The 82 feature flags in Claude Code's source code are evidence. Default configuration is enough for ordinary users, but capable users can unlock entirely different experiences through flag combinations: custom compression strategies, permission mode adjustments, MCP toolchain configuration, Hooks for workflow automation. This layered design — simple to start, deep to master — is a common trait of all successful developer tools. Git is like this, Vim is like this, Kubernetes is like this too.
+
+OpenClaw's Planner-Executor architecture and Claude Code's ReAct loop are essentially solving the same problem: how to keep an Agent controllable during complex tasks. OpenClaw uses DAGs for task orchestration; Claude Code uses AsyncGenerator for tool loops. Different implementations, but the design philosophy is the same — **give the Agent autonomy, but always preserve human intervention points.**
+
+My prediction is: within the next 12 months, Claude Code and platforms like OpenClaw will rapidly converge in functionality. Claude Code will become more platform-like (multi-channel, persistent memory, team collaboration), and OpenClaw will become more intelligent (stronger models, better reasoning capabilities). The ultimate competition won't be about who has the stronger model or more features, but about who can find the best balance between **lowering the usage barrier** and **raising the capability ceiling**.
+
 ## Final Thoughts
 
 These findings gave me a more concrete understanding of AI Coding.

docs/13-啃完源码之后的一些发现.md

@@ -101,6 +101,26 @@ const feature = (_name: string) => false;
 - 不要共享账号
 - 使用模式尽量接近正常用户：有工作有休息，不要 24 小时不停
 
+## Agent 的未来走向
+
+啃完这份源码，再结合我自己做 TME-Claw（基于 OpenClaw 的企业级 Agent 平台）的经验，对 Agent 的未来走向有一些判断。
+
+**Claude Code 正在向平台化演进，而它的演进路径和 OpenClaw 这类 Agent 平台的设计哲学高度重合。**
+
+先说最明显的一个信号：跨 session 记忆。源码中的 MEMORY.md 机制已经实现了基础版的跨会话记忆持久化，EXTRACT_MEMORIES 和 TEAMMEM 这两个 feature flag 说明 Anthropic 正在做两件事——自动记忆提取和团队记忆共享。这和 OpenClaw 的设计思路完全一致：Agent 不应该每次启动都是一张白纸，它需要记住用户是谁、偏好什么、上次做到了哪里。OpenClaw 很早就通过 COS 存储实现了实例级的状态持久化，Claude Code 现在也在往这个方向走，只是路径不同——一个是文件系统，一个是对象存储。
+
+第二个信号是原生渠道接入。2025 年 3 月 20 日，Claude 已经能通过 MCP 插件接入 Telegram。这意味着 Agent 不再局限于终端里等用户来找它，而是可以主动存在于用户日常使用的通讯工具中。OpenClaw 从第一天起就是围绕渠道设计的——微信、企业微信、Slack、Discord，Agent 在哪里取决于用户在哪里。Claude Code 现在也开始理解这一点。可以预见，未来 Claude Code 会原生支持更多渠道，而不仅仅是通过 MCP 做桥接。WhatsApp、Line、飞书，这些都是时间问题。
+
+第三个信号是使用门槛的持续下降。看 Claude Code 的产品迭代方向，从需要手动配置 API key 到一键登录，从纯命令行到 VS Code 集成，从需要自己写 CLAUDE.md 到自动记忆提取。每一步都在降低 bar。终极目标很清晰：**让不懂技术的人也能用 Agent 做事。** OpenClaw 的 Skills 市场就是这个思路的极致体现——用户不需要理解 prompt engineering，选一个现成的 Skill 就能用。Claude Code 的 Skills 体系已经在做同样的事。
+
+但降低门槛不意味着牺牲上限。这是第四个判断：**对于高级用户，Agent 平台会提供越来越多的专业模式。**
+
+Claude Code 源码中的 82 个 feature flag 就是证据。普通用户用默认配置就够了，但有能力的用户可以通过 flag 组合解锁完全不同的使用体验：自定义压缩策略、调整权限模式、配置 MCP 工具链、编写 Hooks 做流程自动化。这种分层设计——入门简单、进阶深邃——是所有成功的开发者工具的共同特征。Git 是这样，Vim 是这样，Kubernetes 也是这样。
+
+OpenClaw 的 Planner-Executor 架构和 Claude Code 的 ReAct 循环，本质上解决的是同一个问题：如何让 Agent 在复杂任务中保持可控。OpenClaw 用 DAG 做任务编排，Claude Code 用 AsyncGenerator 做工具循环。实现不同，但设计哲学是相通的——**给 Agent 自主权，但永远保留人的介入点。**
+
+我的判断是：未来 12 个月内，Claude Code 和 OpenClaw 这类平台会在功能上快速趋同。Claude Code 会变得更像一个平台（多渠道、持久记忆、团队协作），OpenClaw 会变得更智能（更强的模型、更好的推理能力）。最终的竞争不在于谁的模型更强或者谁的功能更多，而在于谁能在**降低使用门槛**和**提升能力上限**之间找到最好的平衡。
+
 ## 最后的思考
 
 这些发现让我对 AI Coding 有了更具体的认知。