An AI coding agent for the terminal. Built to study how coding models fail.
<!-- <CENTERED SECTION FOR GITHUB DISPLAY> --> <div align="center"> <img src="assets/logo.svg" width="120" alt="Codesm logo" /> <h1>Codesm</h1> **An AI coding agent for the terminal. Built to study how coding models fail.** </div> > [!TIP] > > Talks to Anthropic, OpenAI, OpenRouter, and local Ollama. Ships with 30 built in tools, speaks Model Context Protocol, runs parallel and pipelined subagents, integrates with Language Server Protocol for real code intelligence, compacts its own context, and logs every permission decision to an audit trail. <br /> > Built to answer one question: *where exactly do coding models break down when you try to use them as real engineers?* > > | [<img alt="GitHub Follow" src="https://img.shields.io/github/followers/Aditya-PS-05?style=flat-square&logo=github&labelColor=black&color=24292f" width="156px" />](https://github.com/Aditya-PS-05) | Follow [@Aditya-PS-05](https://github.com/Aditya-PS-05) on GitHub for more projects. Hacking on AI coding agents, agent infrastructure, and model evaluation tooling. | > | :-----| :----- | <div align="center"> [](https://www.python.org/) [](https://textual.textualize.io/) [](https://www.anthropic.com/) [](https://openai.com/) [](https://ollama.com/) [](https://modelcontextprotocol.io/) [![GitHub Contributors](https://img.shields.io/github/contributors/Aditya-PS-05/codesm?co
Google's AI-powered research notebook that ingests your documents and becomes an expert on your content. Generates audio overviews, study guides, FAQs, and interactive discussions from uploaded sources.
Google DeepMind's experimental AI agent that can navigate websites, fill forms, and complete multi-step browser tasks autonomously. Uses Gemini's multimodal understanding to interact with web interfaces.
Google DeepMind's universal AI assistant prototype that can see, hear, and respond in real-time through your device camera and microphone. Demonstrates the future of multimodal AI interaction.
Google Cloud's enterprise platform for building, deploying, and managing AI agents powered by Gemini. Supports multi-agent orchestration, tool integration, and enterprise governance.
Gemini's agentic research capability that autonomously browses the web, synthesizes information from dozens of sources, and produces comprehensive research reports on any topic.
Interactive coding and content creation agent that generates, previews, and iterates on code, documents, and interactive applications in a side panel. Supports HTML/CSS/JS, Python, and more.