Aider-AI/aider
Aider is an AI-powered pair programming tool that integrates with your terminal and codebase to assist developers by leveraging large language models for coding, testing, and project management.
Awesome AI Agents › Code Search Engines
ajhous44/cody
Cody is an AI-powered coding assistant designed to help developers interactively query and navigate their codebase using natural language. It leverages advanced techniques such as vector embeddings, chunking, and OpenAI's language models to provide efficient and intuitive codebase exploration. The assistant continuously updates its knowledge base every time a file is saved, ensuring that the information it provides is always current and relevant. Users can customize Cody by specifying directories or files to ignore during monitoring, which helps optimize performance and relevance. The project features real-time file monitoring across the entire project directory and its subdirectories, creating a dynamic and up-to-date knowledge base from the contents of text and JSON files. This knowledge base is built using OpenAI embeddings and stored with the FAISS library for efficient similarity search. Cody supports interactive Q&A, allowing users to ask questions about their code and receive intelligent responses generated from the knowledge base. Cody also supports both text chat via terminal and conversational speech input/output, making it versatile for different user preferences. The assistant uses several dependencies including dotenv for environment variable management, langchain-community and langchain_openai for language processing and embeddings, litellm for calling LLM APIs, watchdog for real-time filesystem monitoring, openai for generating responses, speech_recognition for speech-to-text conversion, gtts for text-to-speech, and pygame for audio playback. The project provides detailed instructions for setup, including environment configuration and API key integration. It also offers guidance on configuring the ignore list to exclude specific files or directories from monitoring, which is useful for ignoring large or irrelevant files such as virtual environments, caches, or downloaded libraries. This customization helps maintain optimal performance and relevance of the assistant's knowledge base. Overall, Cody is a powerful tool for developers seeking an AI assistant that can understand and interact with their codebase in a natural and efficient manner, enhancing productivity and code comprehension.
https://github.com/ajhous44/cody
Also in Code Search Engines
zilliztech/claude-context
Claude Context is an MCP plugin that provides semantic code search to AI coding assistants, enabling them to use the entire codebase as context for improved code understanding and generation.
BloopAI/bloop
Bloop is a fast, AI-powered code search engine that enables natural language queries, code understanding, and generation to boost developer productivity using existing codebases as context.
AbanteAI/archive-old-cli-mentat
This repository contains an archived and unsupported version of an old command-line tool named Mentat, now replaced by an AI-powered GitHub bot available at mentat.ai.
dot-agent/nextpy
Nextpy is a cutting-edge framework for building self-modifying AI software with advanced prompt engineering, modularity, and significant performance optimizations.
melih-unsal/DemoGPT
DemoGPT is an open-source all-in-one library that automates the creation of interactive LLM agent applications by generating LangChain code and transforming it into Streamlit apps, leveraging GPT-3.5-turbo and supporting future autonomous API integration.
chunkhound/chunkhound
Local-first codebase intelligence CLI that indexes a repository for regex and semantic search and answers architecture questions with citations from code, git history and technical web research.
instructa/ai-prompts
Instructa AI Prompts is an open-source repository providing curated AI prompts and rules to enhance AI-assisted coding workflows across multiple popular AI coding tools.