惯性聚合 高效追踪和阅读你感兴趣的博客、新闻、科技资讯
阅读原文 在惯性聚合中打开

推荐订阅源

Martin Fowler
Martin Fowler
Y
Y Combinator Blog
M
MIT News - Artificial intelligence
The Cloudflare Blog
WordPress大学
WordPress大学
H
Hackread – Cybersecurity News, Data Breaches, AI and More
博客园 - 司徒正美
小众软件
小众软件
Blog — PlanetScale
Blog — PlanetScale
雷峰网
雷峰网
奇客Solidot–传递最新科技情报
奇客Solidot–传递最新科技情报
J
Java Code Geeks
云风的 BLOG
云风的 BLOG
C
Check Point Blog
D
DataBreaches.Net
T
The Blog of Author Tim Ferriss
V
V2EX
F
Fortinet All Blogs
B
Blog
大猫的无限游戏
大猫的无限游戏
N
Netflix TechBlog - Medium
B
Blog RSS Feed
A
About on SuperTechFans
Cyber Security Advisories - MS-ISAC
Cyber Security Advisories - MS-ISAC

Hacker News - Newest: "LLM"

GitHub - lechmazur/position_bias: A benchmark for testing whether LLM judges keep the same preference when two lightly edited versions of the same story are shown in opposite orders. Flex routing (EU and EFTA) Dark Factories: Retooling for LLM Velocity Ask HN: What would be the impact of a LLM output injection attack? GitHub - Oaklight/llm-rosetta: Production-ready LLM API translation layer for Python — bidirectional conversion between OpenAI, Anthropic & Google formats via hub-and-spoke IR. Optional API gateway. Streaming & non-streaming. Zero core deps. Contributions welcome! GitHub - browser-use/browser-harness: Self-healing browser harness that enables LLMs to complete any task. GitHub - moeen-mahmud/remen: Remen turns thoughts into something you can return to Analyzing 156 LLM Launch Posts on Hacker News ChatGPT vs Gemini vs Claude: The Best LLM Subscription You Should Buy GitHub - salaamalykum/quran-semantic-search: High-density RAG Semantic Search Engine & Quran Corpus (GEO/SEO Architecture) GitHub - NVIDIA/TensorRT-LLM: TensorRT LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and supports state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorRT LLM also contains components to create Python and C++ runtimes that orchestrate the inference execution in a performant way. The State of LLM Bug Bounties in 2026 Operational Readiness Criteria for Tool-Using LLM Agents Meshcore: Architecture for a Decentralized P2P LLM Inference Network How an LLM becomes more coherent as we train it GitHub - seetrex-ai/laimark GitHub - Jossifresben/BibCrit: AI-assited biblical textual criticism GitHub - wastedcode/memex: File system based wiki, maintained by Claude 99helpers.com GitHub - cliver-project/AITrigram GitHub - unbody-io/adapt: A self-evolving memory layer for AI agents. GitHub - hb20007/awesome-gen-ai-fails: A list of incidents where reliance on generative AI and LLMs resulted in harm to companies, individuals, or society GitHub - nevenkordic/localmind: Run any local LLM with persistent memory and context. CLI agent over Ollama with SQLite-backed hybrid recall. No cloud. Ask HN: What are the machine requirements for a LLM like Llama-3.1-8B? Faster LLM Inference via Sequential Monte Carlo grpo explained: group relative policy optimization for llm finetuning - cgft Stop comparing price per million tokens: the hidden LLM API costs · TensorZero Andrej Karpathy's LLM Wiki Is a Bad Idea GitHub - GG-QandV/mnemostroma: Offline RAM-first cognitive leer/coprocessor for AI agents and robotics. Solves "Context Abandonment" with 20-80ms latency using a dual-thread biomimetic memory architecture (ONNX + SQLite WAL). mempalace/agent at agent · skorotkiewicz/mempalace
GitHub - XTraceAI/memhub-llm-wiki-guide: Guide: ChatGPT /...
TristanX · 2026-05-02 · via Hacker News - Newest: "LLM"

Turn your ChatGPT, Claude, and Gemini history into an Andrey Karpathy's LLM-Wiki mindmap — structured Markdown you can browse in Obsidian-style tools and explore as a graph in MemHub.

MemHub is your context control panel for AI agents. This guide walks through exporting chat history, importing it into MemHub, exploring the Mindmap, and downloading a Markdown ZIP (“Mindmap Markdowns”) for your second brain — without writing code or using Claude Code.

MemHub extracts AI memory and context from your chats, stores it in an encrypted vector database, and organizes it in a file layout that tools like Obsidian work well with.


Watch

Video walkthrough

Open on YouTube →

XTrace MemHub on Product Hunt


Quick links

Link Description
MemHub Web app
MemHub Chrome extension Capture context from the browser (including Gemini in-product)

1. Install the Chrome Extension

These steps match the in-product Instructions panel when ChatGPT is selected in MemHub.

  1. Go to MemHub Chrome extension
  2. Add XTrace Memory to your browser.

2. Export from ChatGPT (OpenAI) / Claude (Anthropic) / Gemini (Google)

  1. Open ChatGPT/Claude/Gemini in your browser.
  2. Click the XTrace Memory extension in the Extensions.
  3. Sign in
  4. You would see a Memory button at your top right, click it
  5. Click export the last N chats you have. Recommend you to put a smaller number if you not sure how much

3. Go to MemHub and Wait

It could take a few minutes for AI to search through your data and extracts memories. Go to MemHub to see your memories getting created in realtime


4. Export Markdown (LLM-Wiki ZIP)

  1. On Memories, click Export (download icon).

  2. The modal title is Export Markdown — subtitle ZIP for Mindmap Markdowns.

  3. Adjust optional filters:

    • Scope: Beliefs (facts), Artifacts, Episodes
    • Date range (leave empty for all time)
    • Platform: memhub, chatgpt, gemini, claude, other
    • Belief type / Artifact type
    • Content density: Full (YAML + body) vs Compact
    • Link style: Standard vs Relationship (wikilinks for supersession, linked facts, etc.)
    • We suggest keep everything as default
    image
  4. Click Confirm export and save the ZIP.

  5. Unzip into your Obsidian vault or any Markdown wiki.


5. View on Obsidian

  1. Make sure your downloaded file is unzipped
  2. Open your Obsidian app
  3. On the top of the window, File -> Open Vault -> select the unzipped folder -> Open
image image 4. On the left sidebar, click Open graph view image

License

Documentation in this repository is licensed under CC BY 4.0.

XTrace, MemHub, and related trademarks belong to their owners. This repo is an unofficial community/education guide unless explicitly published by XTrace.