Awesome AI AgentsCode Search Engines

Context-Engine-AI/Context-Engine

⭐ 400 Python repository created 2025-10-08

Context Engine is a code intelligence layer for AI coding assistants, delivered as a set of Model Context Protocol tools plus the agent skills that teach an assistant when to call them. Indexing runs over a workspace and then serves a default search tool that routes a query to the most suitable backend, whether semantic search, question answering, the symbol graph, tests or configuration. A symbol_graph tool navigates code structurally, resolving callers, callees, definitions, importers and subclasses, while pattern_search finds structural idioms such as retry loops, error handling or singletons across languages. Batch variants of search and graph queries exist specifically to cut token usage on repeated lookups. Persistent memory is provided by memory_store and memory_find, so knowledge survives between sessions, and cross_repo_search traces flows across repository boundaries. Git history is searchable through commit and path-history tools. Distribution is deliberately assistant-agnostic: the repository doubles as a Claude Code plugin marketplace, ships a .cursorrules file, a Codex skill directory, Windsurf and Augment layouts, and a GEMINI.md, and the plain SKILL.md works with any assistant that accepts custom instructions. For terminal workflows an MCP bridge installs from npm as ctxce, which authenticates, indexes a workspace, optionally watches it as a background daemon and then serves the tools over stdio or HTTP. The service side requires an account on the vendor''s site, and indexing can also be driven from a Visual Studio Code extension. The audience is developers working in large or multi-repository codebases where an assistant''s built-in file search is too shallow or too expensive in tokens.

https://github.com/Context-Engine-AI/Context-Engine

ai-agentscode-searchsemantic-searchmcpmcp-serversymbol-graphmemorycontext-engineeringcoding-assistantcursorcodexclaude-code

Also in Code Search Engines

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.

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.