Meta Muse
Meta Muse: Turning a Personal AI into a Computer That Keeps Working
A technical deep dive into Meta Muse: Secure VM, browser runtime, approvals, credential isolation, and memory for persistent personal agents.
WRITING / 持续记录
Development notes
Notes on building AI applications and useful systems.
↗
Jev
Jev: Taking Agent Decisions Out of Text Generation
A standalone technical deep dive into Jev, typed decisions, calibration, and its boundary with Open-Jev, browser agents, and full agent runtimes.
Hermes Agent
After an Agent Calls a Tool, Who Is Still Guarding the Door?
A source-level tour of how Hermes turns a tool call into an auditable, rejectable execution path, from schemas to terminal approval.
Hermes Agent
As a Conversation Grows, How Does Hermes Know What Matters Now?
How does “don't change it yet” survive a long agent session? Follow Hermes through stored history, memory prefetch, usage anchors and compaction boundaries.
Hermes Agent
Is It Still the Same Agent in Another Chat?
Does the same agent in another chat automatically continue the same conversation? Follow Hermes from incoming messages to routing keys, durable sessions, and replaceable execution objects.
DeepSeek Harness
When Should an Agent Stop Moving Forward?
Follow a request to stop writing files through DeepSeek Harness: input queues, turns and steps, concurrent tools, approval guards, and cooperative cancellation.
DeepSeek Harness
After the Window Closes, What Does the Agent Remember?
Reopen yesterday’s conversation to explore how DeepSeek Harness records events, rebuilds model context, preserves interrupted-tool uncertainty, and forks from stable boundaries.
DeepSeek Harness
When One Agent Needs Help, Who Organizes the Others?
Follow a repository review to see how DeepSeek Harness orchestrates child Agents with JavaScript: concurrency slots, pipelines, partial failure, and cleanup after cancellation.
DeepSeek Harness
Why Does Replacing One Agent Component Mean Taking Everything Apart?
Follow a filesystem backend replacement to see how DeepSeek Harness combines service interfaces, dependency identity, scopes, and cleanup into replaceable Agent components.
OpenClaw
The Plugin Is Installed. Why Can’t OpenClaw Use It Yet?
The plugin is listed, but its tool is missing. Follow a capability through synchronous registration, failure rollback, and service startup and shutdown.
OpenClaw
OpenClaw Finished the Command. Where Did It Actually Run?
The command finished, but the report is missing. Follow OpenClaw through execution target selection, workspace mounts, and container reuse.
OpenClaw
When the Model Goes Down, How Does OpenClaw Keep Working?
After a rate limit, should the agent rotate credentials, switch models, or stop? Follow OpenClaw through failure classification, retry budgets, and session rollback.
OpenClaw
After a Long Conversation, How Does OpenClaw Keep the Important Parts?
How does a long conversation become a usable handover? Follow OpenClaw through context budgets, valid cut points, and persisted summaries.
OpenClaw
Why Does OpenClaw Sometimes Send Pieces and Sometimes Rewrite One Message?
Why does streaming sometimes edit one bubble and sometimes send several messages? Follow a checklist with code through OpenClaw previews, chunking, coalescing, and final delivery.
OpenClaw
I Said “Don't Change It Yet.” Why Is OpenClaw Still Working?
Why does “don’t change it yet” fail to stop an assistant immediately? Follow session lanes, shared capacity, steering, and timeouts through OpenClaw’s handling of new input.
OpenClaw
After a Restart, Does OpenClaw Remember Where It Left Off?
The checklist was saved, then the service restarted. Does remembering the conversation mean knowing the action completed? Follow session indexes, JSONL branches, and missing tool results to find the boundary.
OpenClaw
OpenClaw Can Read My File. Why Can't It Save One for Me?
The meeting notes can be read, but the checklist cannot be saved. Follow one request through OpenClaw tool filtering, allow and alsoAllow, path guards, and execution boundaries.
OpenClaw
What Happens When You Ask OpenClaw to “Read This for Me”?
Why can a simple request to read meeting notes take two model calls? Follow the file read, tool result, and final checklist through OpenClaw and Pi.
OpenClaw
OpenClaw Says “Accepted.” When Is the Work Actually Done?
A successful request, an accepted task, and a finished execution are different milestones. Follow OpenClaw Gateway through acknowledgments, idempotent retries, wait deadlines, and event recovery.
OpenClaw
How Does OpenClaw Decide Which Session a Message Belongs To?
Trace a Telegram message through OpenClaw agent selection and session-key construction. Explore dmScope, identity links, routing precedence, and isolation boundaries, with 15 checks against a pinned historical revision.
Hermes Agent
Hermes Agent One Click Launch Integration Package!! launch
Hermes Agent is a powerful open-source AI programming assistant. Official installation requires manual configuration of WSL2, Ubuntu, and Python environments, which has a high threshold for non-technical personnel. This project follows the installation plan of u-claw USB flash drive, encapsulating the entire installation process into a double-click. bat file and providing a GUI interface to configure API keys without any command line operations. Hermes Agent is a powerful open-source AI programming assistant. Official installation requires manual configuration of WSL2, Ubuntu, and Python environments, which has a high threshold for non-technical personnel. This project follows the installation plan of u-claw USB flash drive, encapsulating the entire installation process into a double-click. bat file and providing a GUI interface to configure API keys without any command line operations.
"计算机视觉"
Real time Elderly Ability Assessment System for Edge Segment Based on YOLO+Jetson Nano
This article documents my first real business project independently completed: developing a computer vision based elderly mobility assessment system for a tertiary hospital in Shanxi. From requirement research, solution selection, edge deployment to final delivery and payment, I have completed a complete To B medical delivery loop, which has also allowed me to personally understand the distance between "usable" and "easy to use" for the first time.
AI
Welcome to My Tech Space
I write about AI, computer vision, edge computing, and web development here.