• MCP/mcp-agent

• Py/Lib/neo4j-rust-ext is 3-10x speedup built in #Rust

• Cohere has Embeddings specifically for clustering
• Prompt/Category
• AI/LLM/Technique/LLM System Eval term Grading Party

• Crypto/Smart Contracts expert with statistical enforcement

• GitHub/codekiln/project/ai-coding-template, a project template that has github statuses for issues inspired by the workflow in Person/Harper Reed/Blog/25/02/My LLM codegen workflow atm
• GitHub/codekiln/project/ai-coding, a GitHub/Project for managing AI coding todos. Created some custom Github project statuses
  • https://github.com/users/codekiln/projects/2/settings/fields/Status

• #Term "GitHub App" - GitHub/App
• GitHub/Issue/Draft

• GitHub/CLI/Q/Is it possible to scope gh CLI permissions by directory or repo

• #Learned JetBrains IDEs w/ CoPilot now have codebase #AI/RAG - Boost your productivity with GitHub Copilot in JetBrains IDEs, Introducing @project context, AI-generated commit messages, and other updates - GitHub Changelog Blog/post
  • @project context: Ask questions about your entire project and get intelligent references to relevant files and symbols. - GitHub/CoPilot/@/project
    • #Q how it compares with CursorAI/@/Workspace
  • git/commit/message with #AI - finally!

• #Filed
  • AI/Coding/Todos for learning the tools Harper Reed referenced

• Ingest changes directly into a knowledge base - Amazon Bedrock
  • Amazon Bedrock Knowledge Bases also offers a set of IngestionJob API operations that relate to syncing your data source. When you sync your data source with a StartIngestionJob request, Amazon Bedrock Knowledge Bases scans each document in the connected data source and verifies whether it has already been indexed into the vector store set up for the knowledge base. If it hasn't, it becomes indexed into the vector store.
  • Add documents into your S3 location or delete documents from it. Then sync your data source in the AWS Management Console or submit a StartIngestionJob request in the API. For details about syncing and the StartIngestionJob operation, see Sync your data with your Amazon Bedrock knowledge base.
  • Ingest S3 documents into the knowledge base directly with an IngestKnowledgeBaseDocuments request. For details about directly ingesting documents, see Ingest documents directly into a knowledge base.

• ivy.ai
• classbuddy.ai
  • See also EDUCASE/Conference/2024 exhibitors directory here EDUCAUSE Annual Conference 2024: Exhibitors
  • classbuddy.ai

    • Teaching with AI: Revolutionize Learning with ClassBuddy
      • ClassBuddy streamlines faculty workflows with multiple AI technologies.
      • The ClassBuddy AI-powered Teaching/Assistant transforms your #Course materials into interactive #AI experiences. Designed to improve the student experience by creating a Digital Twin of the instructor’s course material, the platform enhances teaching with AI by curating a unique AI experience for every course.
      • 

• can create #GitHub/Project

• MCP/Idea/MCP Metatool

  • 
  • Idea for a "Metatool" to generate Model Context Protocol servers, given specifications of existing tools, in order to be able to consume them in CursorAI, GitHub/Actions or in CLI prompting

• • Awesome overview of a CLI-centric workflow for AI coding. solid advice.
    • Tools: mise, aider, llm-cli, Repomix added to AI/Coding/Todos

• 📦 Repomix (formerly Repopack) is a powerful tool that packs your entire repository into a single, AI-friendly file. Perfect for when you need to feed your codebase to Large Language Models #LLMs or other AI tools like Claude, ChatGPT, DeepSeek, Perplexity, Gemini, Gemma, Llama, Grok, and more.
  

• Slack channels grouping image

• #oclif - #Salesforce built this Open CLI Framework

• • mise/About

    • mise (pronounced "meez") or mise-en-place is a development environment setup tool.
      • name refers to French culinary phrase roughly translating to "setup" or "put in place"
        • before one begins cooking, a professional chef should have all their utensils and ingredients ready to go and in their place

    • Key Ideas for mise

      • Declar/at/ive configuration

        • The main idea of mise is that mise/Config/mise.toml can let either a project or a user declare the
        • mise.toml describes consistent way to setup and interact with projects across languages
        • mise.toml is a file type used by the mise cli that lets developers globally declare or individual projects locally declare the programming languages, the package manager packages, the environment variables, and the common tasks that need to be run

      • Package/Manager/Meta

        • Mise integrates with multiple Meta Package Managers or Universal Installers. In that sense, it's a meta-meta-package-manager (LOL).

    • The Three Core Jobs to be Done or Main Use Cases for mise

      • mise/JTBD/1 - Dev Tool Installer

        • Job/to be Done 1: as a Declar/at/ive mise Dev Tool installer of Programming Languages and Package Managers packages
          • installs versions of NodeJS, Py, tf as well as any package from those ecosystems
          • specify versions of tools per project or globally
          • mise supports hundreds of dev tools
          • Person/Shunsuke Suzuki created aqua as a more secure Meta Package Manager; mise uses it as a default backend for verified OSS binaries
          • mise/JTBD/1 - Dev Tool Installer/Card/How do I upgrade my global mise Tools

            • How do I upgrade my global mise Tools

              • mise mise/JTBD/1 - Dev Tool Installer
                • How do I upgrade my global mise/Tools? Card
                  • Just use mise/upgrade.
                  • My Notes
                    • AFAIK there's no dedicated global upgrade subcommand that just upgrades global mise tools, but there might be a way to call a command only on a particular (global) mise/Config/mise.toml
                    • Initially I thought you had to be in a directory that didn't have a local mise/Config/mise.toml to upgrade just the global tools, but then I asked mise/Q/Will calling mise upgrade in a directory that has a local mise.toml upgrade global mise Tools? and realized that it does actually upgrade global dependencies even if you are in a directory with a local mise config.
      • mise/JTBD/2 - Environment Manager

        • mise Job/to be Done 2: as a Declar/at/ive environment manager - mise/Environment
          • manages EnvVars for project or globally
          • lets you specify configuration like AWS_ACCESS_KEY_ID that may differ between projects. It can also be used to automatically activate a Python virtualenv when entering projects too.
      • mise/JTBD/3 - Task Runner

        • mise Job/to be Done 3: as a task runner to share common tasks within a project
          • for example, run a task when a file changes
    • mise/Docs/Guides/Getting Started
      • mise/Todos
    • mise/Docs/Guides/Walkthrouh

      • mise commands

        • mise/install

• {{tweet https://x.com/jdxcode/status/1891606050119278853}}

• Prompt engineering - OpenAI API

• Person/Devine Lu Linvega
• Person/Rek Bell

• • Excerpt

    • A woman uses Hollerith’s pantographic card punch to record data from a handwritten 1920 US census form mounted on a roll.
      

    • 

• Perma/Computing/.net/Programming Languages
  • principles of #Permaculture should compel one to consider the energy impact of programming language choice or even microchip choices
• Perma/Computing/.net/Principles

• Zine/Lovers Magazine

Think of #MCP like a USB-C port for AI/Applications. Just as USB-C provides a standardized way to connect your devices to various peripherals and accessories, MCP provides a standardized way to connect AI models to different data sources and tools.

• • Key Insight
    • Both more context and more tools degrade agent performance
    • Agents that require longer trajectories degrade more quickly
    • #o1, #o3-mini, and #Claude 3.5 Sonnet are comparable and in a different league than #4o and Meta/AI/Model/llama/3.3-70B
    • #o3-mini performs as well as #o1 and #Claude 3.5 Sonnet with smaller context, but sees a steeper performance drop as context grows

• • Idea - develop a GitHub Action which uses MCP to interact with GitHub

    • As a result of the above, we could develop a GitHub Action which is itself an MCP client that could utilize a #GitHub MCP server in the action itself to develop more advanced planning abilities. For #Example -
      • an execution plan for each issue
      • filing issues or sub-tasks
      • organizing the project backlog to sequence work
    • An API key with access to a reasoning model could be used to execute planning in the issues.
    • A Github Scheduled Workflow #cron could "wake up" and do Backlog Grooming on the project
    • When a git commit is pushed, it could trigger a workflow that would execute a "plan" with an LLM Reasoning Model against the Best Next Action, storing an Intermediate Work Product somewhere in the GitHub Project, such as in an Issue Comment
    • The local CursorAI model could use its own access to MCP to access the Intermediate Work Product left in the project to start from the instructions the LLM Reasoning Model left.

• • The difference between System 1 vs System 2 Thinking may be mirrored in fast, intuitive Local Cursor usage vs slow, CICD-initiated use of LLM Reasoning Models to conduct advanced Backlog Grooming and initiate CursorAI/Technique/Frontload Design

    • Inference Time Compute cost and latency grows with the length of the Chain of Thought. It may eventually be structurally important to bifurcate when and where we use reasoning models.
      • The cost structure of reasoning models encourage Cursor and likely also other AI Coding Tools to develop licensing models that restricts the use of reasoning models in their agent mode.
    • But there remains an important need to develop a well-reasoned plan on what to do. CICD may have a role in doing some System/2 Thinking pre-work and sequencing to help the System/1 Thinking CursorAI/Agent make the most of its resources.

• ReflectApp

• Person/Lyz
• Person/Nikita Voloboev

• Person/Sebastian Raschka

• #Updated
  • CursorAI/Idea/Proj Rules GitHub CLI AI SLDC/MCP

• #Updated
  • Person/Kevin Leneway/YouTube/Build Cursor on Steroids in 20 Minutes with MCP
• #Filed
  • Person/Kevin Leneway/YouTube/You HAVE to Try Cursor + o3 + Storybook

• CursorAI/Forum/24/02/How to use MCP Server

• #Filed
  • Person/Stephen Akinyemi/GitHub/awesome-mcp-servers
  • MCP/GitHub and child pages; list of repos

• #Filed
  • Person/Tim Rogers

• smithery.ai Smithery - Model Context Protocol Registry
  • has a "generator" for cursor
  • #Example - smithery.ai/smithery.ai/server/mcp-obsidian Obsidian Reader | Smithery
    • 

• {{tweet https://x.com/rasbt/status/1890842082756935853}}
• Person/Sebastian Raschka/GitHub/LLMs-from-scratch
  • LLMs-from-scratch/setup/01_optional-python-setup-preferences at main · rasbt/LLMs-from-scratch