ICDYCT / I Can Do, You Can Too

Now there are CPA installation tutorials everywhere. Here I want to record my own操作过程 — Oracle VPS Ubuntu system using non-root user without sudo -i  Official installation script curl -fsSL https://raw.githubusercontent.com/brokechubb/cliproxyapi-installer/refs/heads/master/cliproxyapi-installer | bash source Pay attention to the information output by the script Execute command 1, enter your installation directory cd /home/ubuntu/cliproxyapi * If you are a root user, this directory will be different from mine, use your own directory as reference Execute command 2, check if cpa background process can run, if there are any errors ./cli-proxy-api Open a new SSH session, curl test curl localhost:8317 * Note:  8317  is cpa's default port Should get result like this {"endpoints":["POST /v1/chat/completions","POST /v1/completions","GET /v1/models"],"message":"CLI Proxy API Server"} At the same time, the SSH session running cpa pr...

Preface From Openclaw to Hermes, I've attempted multi-agent team collaboration multiple times. https://zelikk.blogspot.com/search?q=%E5%A4%9Aagent Many times cross-agent communication fails, and the erroneous behavior is unpredictable — meaning the same prompt / agent.md file might work this time but fail on the next try. The most recent case was using Hermes , and I had already previously prompted it to modify itself to gain the ability to bind agents to Telegram group topics, similar to Openclaw . During usage, Once, agent-design did not send a message to agent-watch but replied in its own topic instead Two other times, when agent-watch sent messages to agent-design, they did not follow the specified message format. https://www.youtube.com/watch?v=TBmbAcV6Gis Approach At the textual description level of SOUL.md, a sufficiently intelligent "person" or "model" should understand the effect I want. * The SOUL.md before this experiment has been overwritten; you can...

Hermes based on Python not only has higher proactiveness in modifying its own code, but also makes it more convenient to submit the modifications you've made to that code. Because the code you are running is exactly the modified version, and you've actually tested its usage. I now need you to do a task with quite a few steps 1. Create a new directory and clone your latest GitHub code into it 2. Apply the agent binding topic modification that we completed together on your code to the code in step 1 Note, do not sync all the modifications you've made recently, only implement the agent binding topic feature (Right click to open original image in new tab) Submit this modification to the main branch of the GitHub project They prompted me to create a GitHub token with repo permissions  I operated on github.com and sent the obtained token to them I want to see how the fork turned out GitHub https://github.com/crazypeace/hermes-agent/tree/feat/agent-topic-binding Another modificati...

Preface Based on the previous successful multi-agent team collaboration experiment , I invited fellow group members to give me some small tasks they thought of to try out. Someone provided this: Build a premium interactive isometric 3D cozy room using Vite + React + Three.js (react-three-fiber/drei), with all objects modeled in code (no external assets) and subtle ambient animations. Users can click objects to smoothly focus the camera and reveal descriptions, delivering a polished, accessible, $50M-startup-quality WebGL experience. Problem During development, I discovered that when agent-test says "Test report sent to agent-watch. Testing complete", agent-watch did not receive the report. (Right click to open original image in new tab) Analysis I used the default agent hermes to analyze this event to avoid context interference. The analysis conclusion is Conclusion: agent-test reached the maximum iteration limit and was forcibly stopped by the system. It did not call any scr...

Hermes uses telegram react emoji to indicate work status and task progress Eyes 👀 indicate seen Thumbs 👍   indicate completion This is the same as my collaboration with colleagues in Teams. To avoid the work group being flooded with uninformative interruptions like "Received", I require colleagues to use a green checkmark ✅ to indicate task completion,  use a non-green checkmark ☑️ to indicate "received".  (Why say non-green? Because in different systems, this emoji might be other colors -_,-  And on iOS, searching for "checkmark" brings up another one ✔️ ) React emoji when receiving messages hermes config set telegram.reactions true 这是我手工添加的文字, 这一篇是 stepfun/step-3.5-flash 模型处理的

Preface I often see some blogs that have a "Related Recommendations" section at the end of each article. A few days ago, I used the LLM-WIKI skill, so I thought about using the LLM-WIKI skill to analyze my blog and add related recommendations to each post as well. Approach Save my blog pages as WIKI pages, Use the LLM-WIKI skill to lint and analyze these pages, establishing connections between them, Count the connection counts for all pages, For each page, among its connected pages, find the 3 pages with the most connections. Practice Initialize WIKI I chatted with hermes (MIMO v2 pro 2026-4-21) I'm going to do something. Help me analyze the specific plan. Don't implement it yet, let's discuss first. There is a website https://zelikk.blogspot.com/ This website's RSS output is full content https://zelikk.blogspot.com/rss.xml Use your llm-wiki skill to create a new WIKI Ingest every article from this website into this WIKI Lint and organize this WIKI, and output...

Introduction I often see blogs that have a "Related Recommendations" section at the end of each article. A few days ago, I used the LLM-WIKI skill, so I thought about using it to analyze my blog and add related recommendations to each post. Approach Save my blog pages as WIKI pages, Use the LLM-WIKI skill to lint and analyze these pages, establishing connections between them, Count the connection counts for all pages, For each page, among its connected pages, find the 3 pages with the highest connection counts. Practice Initialize WIKI I chatted with hermes (MIMO v2 pro 2026-4-21) ... The entire development process involved lots of detailed design discussions, which I won't list one by one. See GitHub for details Eventually, I got several files: 1. Page index 2. Inter-page connection list 3. Individual page connection relationships 4. Top 3 pages with highest connection counts Processing all blog posts with semantic analysis took quite a while and ...

test 8 content

test 7 content 相关推荐 test-8 test-4 test-5

前言 test 6 content 相关推荐 test-7 test-8 test-4

前言 test 5 content 相关推荐 test-6 test-7 test-8

前言 test 4 content 相关推荐 test-5 test-6 test-7

这是一篇通过 Blogger API 自动发布的测试文章。 Hello from API! 相关推荐 test1 test2