symbex

If you code is well designed and has reasonable documentation that could be enough for the LLM to understand it. https://github.com/simonw/symbex is my CLI tool for that https://simonwillison.net/2025/Apr/23/llm-fragment-symbex/ is a tool I released this morning that turns Symbex into a plugin for my LLM tool. I use my https://llm.datasette.io/ tool a lot, especially with its new fragments feature: https://simonwillison.net/2025/Apr/7/long-context-llm/ This means I can feed in the exact code that the model needs in order to solve a problem. Here's a recent example: llm -m openai/o3 \ -f https://raw.githubusercontent.com/simonw/llm-hacker-news/refs/heads/main/llm_hacke… \ -f https://raw.githubusercontent.com/simonw/tools/refs/heads/main/github-issue-to-mar… \ -s 'Write a new fragments plugin in Python that registers issue:org/repo/123 which fetches that issue number from the specified github repo and uses the same markdown logic as the HTML page to turn that into a fragment' From https://simonwillison.net/2025/Apr/20/llm-fragments-github/ - I'm populating the context with the exact examples needed to solve the problem.

- llm: - ttok - symbex - shot-scraper " As of my last knowledge update in September 2023, here is the information on the CLI tools you are asking about: 1. *llm*: - I couldn't find a specific command line tool named "llm" that is widely recognized or used. It could be a lesser-known tool, a new tool, or potentially a typographical error. Please verify the tool's name and provide additional details if possible. 2. *ttok*: - As with "llm," there isn't any widely known CLI tool named "ttok." (Truncated) llm -m 4o "Tell me about these cli tools and link to them: - llm: - ttok - symbex - shot-scraper " Sure! Here are brief descriptions of the CLI tools you mentioned along with links to their official repositories or webpages: ### 1. llm `llm` is a command-line interface (CLI) tool to interact with large language models like OpenAI's GPT-3. It allows you to query these models directly from the terminal, making it easy to integrate AI capabilities into your workflow or automate tasks. - *Link*: [llm GitHub Repository](https://github.com/simonw/llm) ### 2. ttok `ttok` is a CLI tool for working with tokenizers. It's a tool under development aimed at helping users understand how tokenization processes text, which is essential for preparing data for machine learning models, especially in NLP applications. - *Link*: [ttok GitHub Repository](https://github.com/simonw/ttok) ### 3. symbex `Symbex` is a CLI tool for performing symbolic execution on Python bytecode. It can analyze Python code to find potential bugs, vulnerabilities, or logical errors by exploring all possible execution paths. - *Link*: [symbex GitHub Repository](https://github.com/simonw/symbex) (Truncated) llm -m 4o "Tell me about these cli tools and link to them: - llm: - ttok - symbex - shot-scraper " Sure, here is a brief overview of each CLI tool along with links to their respective repositories or documentation: 1. *llm (Language Model CLI)* - *Description*: The `llm` command-line tool leverages large language models, such as OpenAI's GPT-3, to make it easier to incorporate AI functionalities into your command-line tasks. You can use it to generate text, answer questions, and assist with coding or other language-based tasks directly from your terminal. - **Link**: [llm on GitHub](https://github.com/simonw/llm) 2. *ttok* - *Description*: `ttok` is a simple command-line utility that provides tokenization for text, particularly useful for breaking down input for language models. It helps to preprocess text, count tokens, or manage tokens more efficiently from the command line. - **Link**: [ttok on GitHub](https://github.com/simonw/ttok) 3. *symbex (Symbolic Execution)* - *Description*: `symbex` is a CLI tool designed for searching codebases. It employs symbolic execution to analyze code paths and find functions, variables, or other code elements. This can be particularly useful for developers looking for higher-precision searches in large codebases. - **Link**: [symbex on GitHub](https://github.com/paulgb/symbex) (Truncated) Clearly, openai did a lot more web scraping for this model.