Gregoryy
Re:Anthropic Fable just deleted a .git folder of mine, what's next?
on Friday June 12, 2026 @05:56PM (#48509901)
i honestly don't understand. In which case did you find it more powerfull then e.g. latest Opus? i also used it a lot and did not find the different
p.s. it generates radically different designs but after many iterations you understand that they are also all the same - it's like they've just RLed it in a different way
Re:Working on multiple tasks in parallel using 1 OpenClaw Agent
on Monday March 02, 2026 @10:44PM (#47227747)
In this article i've proposed a simple way to work on multiple tasks in parallel using 1 OpenClaw agent.
The trick is to create multiple groups in Telegram, add you agent there with require_mention=false and work in them.
This way, context for each session is stored separately and you don't need to way for a result on one task to work on another one, while memory is still unified, which allows to cross reference conversations.
Show HN: Bing Webmaster CLI for Agents and LLMs
https://github.com/NmadeleiDev/bing_webmaster_cli
Created this CLI client for Bing Webmaster to let my agents automate SEO reporting and improvements on Bing.Works via API key auth (from ENV of CLI argument).Repo includes a skill that can be installed in your OpenClaw agent.I also have a CLI for Google Search Console: https://github.com/NmadeleiDev/google-search-console-cli- from the developer of https://openclaw-setup.me
Re:Destroy My Startup
on Wednesday February 25, 2026 @01:38AM (#47148120)
hahah that's awesome!!
Show HN: Google Drive CLI for LLMs / Coding Agents
https://github.com/NmadeleiDev/google-drive-cli
Built google-drive-cli-for-agents: a small Python CLI for Google Drive.It supports ls by folder link/ID, file upload, download, and trash by link/ID, with OAuth login (gdrive auth login) and pipx install support.
Show HN: Google Search Console CLI
https://github.com/NmadeleiDev/google-search-console-cli
Sharing this GSC CLI built on python. Great to use in your agents, e.g. OpenClaw (just tell it to install and authentificate).Once done, you/your agent can view you organic traffic statistics and opmitize your website.
Show HN: Connect Slack to Your OpenClaw – Tutorial and Hosting
https://openclaw-setup.me/tutorials/slack/
Openclaw Setup just added an integration with Slack.Check out our tutorial for setting this up: https://openclaw-setup.me/tutorials/slack/OpenClaw setup also provides a free and feature-rich managed hosting for OpenClaw: secure setup, Telegram + Slack, ENV and agent state management, CLI tooks authentification and much more: https://openclaw-setup.me
Show HN: Secure managed hosting for OpenClaw (free and BYOK)
It’s managed hosting for OpenClaw aimed at people who want an always-on personal AI assistant but don’t want to self-host / debug infra.What it does- 1 minute setup: sign in with Google → connect Telegram → connect your LLM provider - Isolated runtime: your OpenClaw instance runs isolated (smaller blast radius vs “run on your laptop/VPS”) - Access control: allowlist who can message your bot...
Show HN: Moltbot state observability and persistance daemon
https://github.com/NmadeleiDev/moltbot_config_watcher
Created a tool for observability psychos like me :)I wanted to track every change that MoltBot does to it's own system files (memories) in git and notify me with the exact diffThis tool watches a git repo (e.g. /Users/<username>/clawd/), auto-commits/pushes on changes, and sends the diff to TelegramOne command setup
Re:Show HN: RAG Architecture for optimizing retrieval volume/relevancy...
on Thursday January 15, 2026 @05:46AM (#46630731)
we consider this a separate issue that should be addressed using special approaches. however, the proposed technique generally tends to decrease the probability of something being lost in the middle by minimizing the total size of the retrieved documents.
Re:Personal Taste Is the Moat
on Wednesday January 14, 2026 @12:46AM (#46612768)
couldn't agree more. It's also correct for other fields: design, analytics, marketing, etc. When cost of implementation goes to zero, what you do and why is the most important thing.
Show HN: RAG Architecture for optimizing retrieval volume/relevancy tradeoff
https://github.com/darwinapps/nestedRAG
We propose a RAG architecture that uses hierarchical semantic chunking and graph-based context exclusion to maximize relevant information while minimizing the total volume of retrieved context.The system recursively splits documents into a hierarchical tree structure and dynamically selects the most optimally-sized chunk from each branch by identifying and excluding redundant ancestors and...
Show HN: AI tutor to study and practice STEM books
Study Junkie is an AI tutor that turns any textbook or document you upload into an interactive course with lectures, discussion-based chat, practice assignments of various difficulty, and audio narration.How it's different from similar toolsIt seems like similar tools are mostly optimized for a quick preparation for an exam or job interview, which is not optimal if you want to really understand...