semantic code search for AI coding agents
Claude Context is an MCP plugin that gives AI coding agents like Claude Code semantic code search over the entire codebase using embeddings and a vector database.
Same problem, same approach. Swapping one for another is a config change, not a rewrite.
drop-in peer for semantic code retrieval via MCP; choose if you want fast, cheap context for multiple agents.
Turbocharge Claude Code, Cursor, Codex, Gemini & every coding agent: faster, cheaper, with contextual understanding specific to your codebase.
drop-in MCP with semantic retrieval plus editing tools; choose if you need an agent IDE within the server.
A powerful MCP toolkit for coding, providing semantic retrieval and editing capabilities - the IDE for your agent
same-class MCP with hybrid semantic search and dependency graphs; choose for enterprise-scale (40m+ LOC) codebases.
Enterprise-grade (40m+ LOC) codebase intelligence, zero-setup, local & private Plugin/Skill/Extension or MCP: hybrid semantic search, polyglot dependency graphs, symbol-level impact analysis & call-flow, interactive HTML viewer, cross-project & branch-aware search, DB/API/infra knowledge. 61% less tokens, 84% fewer calls, 37x faster. Cloud in beta.
same-class local semantic search with call graphs via MCP; choose for fully local retrieval.
Semantic Search & Call Graphs for AI Agents (100% Local)
Solves the same problem with a different architecture or at a different layer. Expect to rewrite the integration.
choose it when you prefer a pre-indexed knowledge graph over semantic embeddings; it auto-syncs and supports multiple agents.
Pre-indexed code knowledge graph, auto syncs on code changes, for Claude Code, Codex, Gemini, Cursor, OpenCode, AntiGravity, Kiro, CoPilot, and Hermes Agent — fewer tokens, fewer tool calls, 100% local
choose it when you want a deterministic AST-based knowledge graph with docs/SQL/PDF support, not embeddings.
Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Cursor, Codex, and Gemini CLI: local deterministic AST parsing, every edge explained, no vector store.
choose it for a high-performance graph-based MCP with millisecond indexing and 158 languages.
High-performance code intelligence MCP server. Indexes codebases into a persistent knowledge graph — average repo in milliseconds. 158 languages, sub-ms queries, 99% fewer tokens. Single static binary, zero dependencies.
choose it for a local-first graph MCP focused on code review context reduction.
Local-first code intelligence graph for MCP and CLI. Builds a persistent map of your codebase so AI coding tools read only what matters, with benchmarked context reductions on reviews and large-repo workflows.
choose it for a graph-RAG approach to monorepo understanding, with editing via MCP.
The ultimate RAG for your monorepo. Query, understand, and edit multi-language codebases with the power of AI and knowledge graphs
choose it for a high-performance graph-based engine exposed via MCP/CLI/API, supporting many languages.
High-performance code-intelligence engine for AI agents and IDE, supports 257 languages, multi repositories, based on graph, with access via CLI, MCP Server, and API. AI coding agents teammate - expose only needed information, cutting token usage up to 50x. 100% local. Discord: https://discord.gg/39MFHu3J5d
choose it for AST-based symbol-level GitHub code retrieval with extreme token savings.
Cut AI token costs 95%+ on code exploration. The leading MCP server for precise, symbol-level GitHub code retrieval via tree-sitter AST. Works with Claude Code, Cursor & any MCP client. 313B+ tokens saved.
choose it for a code research platform that spans local and GitHub, but with a different retrieval architecture.
Code research platform for AI agents; find, understand, and prove context across your code and all of GitHub, in a fraction of the tokens. One toolset, MCP or CLI
choose it for a graph-powered code intelligence engine with MCP and CLI.
Graph-powered code intelligence engine — indexes codebases into a knowledge graph, exposed via MCP tools for AI agents and a CLI for developers.
choose it for a local code intelligence MCP server and CLI, but without the embedding-specific approach.
Local code intelligence MCP server and CLI for AI coding agents
choose it for a Rust-native graph-RAG implementation with AST parsing and SurrealDB; last pushed 9 months ago.
100% Rust implementation of code graphRAG with blazing fast AST+FastML parsing, surrealDB backend and advanced agentic code analysis tools through MCP for efficient code agent context management
choose it for a deep engineering-context tool, though its approach is not explicitly semantic-embedding based.
Your entire engineering context, deeply understood
choose it for a lightweight AST-based embedded code search CLI; simpler but same agent-context job.
A super light-weight embedded code search engine CLI (AST based) that just works - improves speed and efficiency for coding agent 🌟 Star if you like it!
These projects were analysed and named claude-context among their alternatives. The relationship is not symmetric — how claude-context rates them is a separate judgement, made when claude-context is analysed in its own right.
calls claude-context “Choose for semantic code search via MCP instead of explicit graph traversal.”
Graphs that teach > graphs that impress. Turn any code into an interactive knowledge graph you can explore, search, and ask questions about. Works with Claude Code, Codex, Cursor, Copilot, Gemini CLI, and more.
calls claude-context “if you want a lightweight, TypeScript code-search MCP without graph-based structural queries”
High-performance code intelligence MCP server. Indexes codebases into a persistent knowledge graph — average repo in milliseconds. 158 languages, sub-ms queries, 99% fewer tokens. Single static binary, zero dependencies.
calls claude-context “Use when you prefer vector/Milvus-based code search over a persistent AST graph.”
Local-first code intelligence graph for MCP and CLI. Builds a persistent map of your codebase so AI coding tools read only what matters, with benchmarked context reductions on reviews and large-repo workflows.
calls claude-context “Code search MCP for Claude Code; choose when you want a dedicated code-context search over general context management.”
Context window optimization for AI coding agents. Sandboxes tool output (98% reduction), persists session memory, and enforces routing across 17 platforms via MCP + hooks.
calls claude-context “Choose when you want a vector-search MCP tailored for Claude Code rather than a local DuckDB index.”
Your entire engineering context, deeply understood
calls claude-context “Pick it for pure vector-embedding code search, at the cost of running Milvus and an embedding provider.”
Code research platform for AI agents; find, understand, and prove context across your code and all of GitHub, in a fraction of the tokens. One toolset, MCP or CLI
calls claude-context “choose for a lighter code-search MCP when full graph coverage is overkill.”
Pre-indexed code knowledge graph, auto syncs on code changes, for Claude Code, Codex, Gemini, Cursor, OpenCode, AntiGravity, Kiro, CoPilot, and Hermes Agent — fewer tokens, fewer tool calls, 100% local
calls claude-context “Code-search MCP for full-codebase context; choose it only when search/context is enough.”
A powerful MCP toolkit for coding, providing semantic retrieval and editing capabilities - the IDE for your agent