51 tagged code-search, measured the same way as everything else here.
Browse within: cursor 15embeddings 15call-graph 11ai-skills 10cli 9code-intelligence 9claude-code-plugin 7mcp-server 6coding-agents 5
jarvis-intelligence/jarvis-index
Plugin Claude Code
Bundles 3 skills, 2 commands, 1 agent, 1 hook, 1 MCP server · 233 tokens together
Local-first structural code intelligence over your own indexed repositories, with skills that teach Claude to prefer structural queries over grep.
marcodavidd020/cerebro-code-memory
Plugin Claude Code
Bundles 1 skill, 5 agents, 4 hooks, 1 MCP server · 597 tokens together
Persistent code-knowledge memory: an MCP brain that caches a codebase's structure and summaries so AI sessions query it instead of re-reading files. Bundles the MCP server, cerebro-first subagents, and session hooks.
Plugin Claude Code
Bundles 2 commands, 1 hook, 1 MCP server · 16 tokens together
Local-first Context7 alternative — indexes JS/TS dependency docs with a 4-stage RAG pipeline (vector + BM25 + RRF + cross-encoder reranking). Uses TEI Docker containers for GPU-accelerated embeddings and reranking.
Plugin Claude Code
Bundles 8 skills, 8 commands, 3 hooks · 1,109 tokens together
The grep-native language for agentic systems — more accurate, more efficient, at any scale.
Plugin Claude Code
Bundles 9 skills, 2 agents, 1 hook · 802 tokens together
Progressive codebase knowledge base — clone git repos, auto-generate documentation, and build a searchable knowledge cache that grows smarter with every query.
Plugin Claude Code
Bundles 5 skills · 292 tokens together
Local-first codebase memory for coding agents: AST-aware context, durable decisions, failure records, review packs, and a local graph GUI. Twenty tools are advertised by default; writefile, patchfile, prompt compression, and bash are opt-in. Discipline protocols ship as MCP prompts rather than tools. Pre-2.0 tool nam.
WangChangxin0809/repo-agent-harness
Plugin Claude Code
Bundles 6 skills, 1 agent, 4 hooks · 815 tokens together
Lay the foundation that makes a repository teach coding agents how to work in it: delivery moments wired to hooks, a layered docs truth source, CI gates plus tool-call guards, a rebuildable repo graph, and a consolidation pass. Bootstraps once, then the repo stands on its own.
Plugin Claude Code
Bundles 1 skill, 4 commands · 138 tokens together
Local explainable codebase RAG indexing and retrieval for coding agents.
Plugin Claude Code
Bundles 4 commands · 96 tokens together
Claude Code integration for cocoindex-code (ccc). Slash commands for onboarding, reset, and re-index; git hook installer for automatic incremental indexing; standard exclude presets that avoid common retrieval noise (tests, plans, compiled views, ML embedding data).
chrisfentiman/claude-context-cli
Plugin Claude Code
Auto-indexing for claude-context-mcp. Keeps your codebase index fresh on session start, after git operations, and on session end. Includes /insights skill for promoting memsearch patterns to auto-memory.
Plugin Claude Code
Replaces whole-file reads with ranked, token-budgeted code slices.
harshithsunku/mcp-gtags-server
Plugin Claude Code
Bundles 1 skill, 1 MCP server · 59 tokens together
Indexed C/C++ code navigation for coding agents, powered by GNU Global (gtags): who calls a function (with each call site's source line), every usage grouped by file, call chains, and definitions with their #ifdef guard stacks — filterable by a real kernel .config. Resolves macro-generated kernel symbols (sysread to i.
Plugin Cursor
Bundles 1 skill, 1 MCP server · 46 tokens together
Semantic code search for AI agents. Search code by meaning, not text patterns. Replaces grep/ripgrep for 95% of code exploration tasks.
ChristopherDavenport/github-twin
Plugin Claude Code
Personal RAG over your GitHub history (commits, code, review comments), served to Claude Code over MCP. Tools: findcode, findreviews, predictreviewoutcome, houserules, developerprofile, and related retrieval surface.
Plugin Claude Code
Bundles 26 skills, 4 agents, 9 hooks · 318 tokens together
Estelle — code memory + the grounding gate, always on. The trust layer under your AI coding agents: it grounds every model in your real codebase and refuses to ship what isn't true.