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
marcoaapfortes/Mantic.sh
Mantic is a local code search engine that ranks results by relevance rather than competing on raw scan speed, built as a context retrieval layer for AI coding agents. Instead of reading file contents exhaustively, it infers intent from repository structure, file paths and metadata, which lets it return a short ranked list quickly and, the authors report, cut the tokens an agent spends on irrelevant files by a large margin. Everything runs locally with no data leaving the machine. Retrieval is hybrid: heuristic scoring handles the common case, and an optional semantic reranking mode uses local embeddings through transformers.js to surface conceptually related code when the query shares no keywords with the target. A Tree-sitter layer adds code intelligence commands, so a go-to-definition query returns the exact file and line for a symbol across a monorepo and a references query lists every usage while respecting gitignore rules. A learned-context feature records which files resolved previous queries into a JSON file inside the repository, which can be committed so a team shares the accumulated patterns. Dependency-graph support covers JavaScript, TypeScript and Python imports. The project ships as a command-line tool, as an MCP server for editors and agents such as Claude and Cursor, and as a VS Code extension, and it includes regex denial-of-service protection on user input, command injection mitigations in the extension, and an allow-listed extension scan as a fallback in directories that are not git repositories. The README publishes benchmarks against ripgrep and fzf on cal.com, Next.js, TensorFlow, Supabase and Chromium, and is candid that Mantic is slower than ripgrep on raw matching while claiming better ranking, with sub-two-second results on a 481,000-file checkout.
https://github.com/marcoaapfortes/Mantic.sh
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.