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
bigcode-project/bigcodebench
BigCodeBench is a comprehensive and easy-to-use benchmark designed to evaluate the code generation capabilities of large language models (LLMs) in practical and challenging programming tasks. It focuses on assessing the true programming skills of LLMs through function-level code generation tasks that involve complex instructions and diverse function calls, making it more realistic compared to simpler benchmarks like HumanEval. The benchmark is divided into two main splits: 'Complete', which tests code completion based on detailed docstrings, and 'Instruct', which is tailored for instruction-tuned and chat models that generate code snippets from natural language instructions requiring complex reasoning. BigCodeBench has gained significant trust and adoption from leading AI research teams and companies such as Meta AI, Amazon AWS AI, Alibaba Qwen, Cohere AI, and the Allen Institute for Artificial Intelligence, among others. It provides precise evaluation and ranking of models, with a publicly accessible leaderboard hosted on Hugging Face that showcases the performance of over a hundred models. The benchmark also offers pre-generated code samples from various models to accelerate research without the need for repeated expensive benchmarking runs. The project supports remote evaluation through APIs and offers multiple backends for code execution, including vLLM, OpenAI, Anthropic, Google, Mistral, and Hugging Face inference. It provides tools for batch inference and detailed result storage, including generated code samples, evaluation results, and pass@k metrics. The benchmark is continuously updated with new releases and improvements, and it includes a subset called BigCodeBench-Hard, which focuses on more real-world aligned programming tasks. BigCodeBench aims to push forward the frontier of AI for software engineering by providing a rigorous, reproducible, and scalable platform for benchmarking code generation models, facilitating advancements towards artificial general intelligence (AGI) in programming.
https://github.com/bigcode-project/bigcodebench
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.