By iliaal
Onboard projects to CodeSage for semantic code search, dependency analysis, and impact analysis, then run parallel feature-slice reviews with adversarial verification and persistent findings tracking.
Run CodeSage retrieval benchmarks on all corpora, save timestamped scorecards, print a summary
Evaluate CodeSage effectiveness on a project by mining session-based eval cases and running the bench runner
Onboard a project to CodeSage (global MCP registration, init, index, git hooks, agent hint)
Print a system-prompt fragment that steers Claude Code to prefer CodeSage's MCP tools over Grep for retrieval-shape tasks
Force an incremental codesage re-index (use when git hooks didn't fire). Auto-cleans orphan vec tables if the config model has changed.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Executables (bin/) — files in this plugin's bin/directory are added to the Bash tool's PATH while the plugin is enabled.

CodeSage is a code intelligence engine for AI coding agents. It combines structural graph queries (symbols, references, dependencies) and semantic search (embedding retrieval with cross-encoder reranking) in a single Rust binary, usable as a CLI or over MCP. Nine languages today (PHP, Python, C, C++, Java, Rust, JavaScript, TypeScript, Go). On the semble retrieval corpus, codesage search scores recall@10 = 0.932 / NDCG@10 = 0.788 across 602 queries on the 8 supported-language repos (see External-corpus benchmark below).
ext/*, Next.js app/**, CMake/CUDA targets, Python __main__, Go cmd/*, etc.).network, filesystem, process-exec, secrets, database, user-input, external-api, serialization, auth, concurrency) derived from imports/includes/calls; same signal folds into assess_risk and surfaces as security-review notes when ≥3 boundaries are crossed.Concrete answers to the questions a code-intelligence tool earns its keep on. The axes are the ones the broader ecosystem (GitNexus, SocratiCode, code-review-graph, claude-context, repowise) converges on; the right-hand column is what CodeSage actually ships.
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).
npx claudepluginhub iliaal/codesage --plugin codesage-toolsSemantic code search and codebase graph tools for Claude Code
Graph-first code intelligence for AI agents. SurrealDB knowledge graph + 52 MCP tools replace Read/Grep/Glob with deterministic graph traversal. 80–95% fewer tokens on code context. Rust-native, fully local.
Codebase intelligence — semantic search workflows, dependency graph analysis, and context artifact exploration for SocratiCode
Code graph navigation and semantic search for LLM coding agents
Local-first hybrid semantic code search with dependency graphs and cross-repo search. Powered by CocoIndex, Tree-sitter, pgvector, and Ollama.
Local codebase intelligence + change-safety gates for coding agents. Pre-indexes your repo's symbols, call graph, deps, and git history into SQLite (28 languages, 100% local, zero API keys), then exposes a lean 16-tool MCP core preset: graph-precise search, callers/impact blast radius, coupling, dead code, taint reachability, and pre-merge verify/critique gates that catch regressions, broken references, AI-slop duplication, and convention drift before they ship.