tokensaveCode-intelligence MCP server for coding agents — a pre-indexed semantic graph (libSQL + FTS5) they query instead of grepping: symbols, callers, impact radius in one call. 100% local, 50+ languages.
Why switchSame job — replace agent grepping with a pre-built local index. TokenSave answers structural questions (symbols, callers, impact radius) from a semantic graph; cocoindex-code answers 'where is the code that does X' via AST-chunked embedding search.
Full comparison → zvec-grepzg: ripgrep, BM25 and vector search behind one local-first CLI for humans and agents — index a workspace once, search code, docs and data by meaning, then verify with exact text or regex.
Why switchBoth give coding agents local semantic search with zero-config embeddings. cocoindex-code is AST-aware and code-only; zg is text-level across code, documents and data, and pairs the vector hit with grep to verify.
Full comparison → codegraph-mcpNo-train, on-prem code knowledge graph served to AI agents over MCP — symbols, call edges, cross-language links and blast-radius queries, with a hash-chained audit log of every read.
Why switchBoth serve codebase context to agents over MCP. codegraph-mcp builds a cross-language knowledge graph with audit logging for on-prem rigor; cocoindex-code trades graph depth for zero-config semantic search that installs in a minute.
Full comparison → codebase-memory-mcpCode intelligence MCP in pure C: tree-sitter knowledge graph over 158 languages, average repo indexed in milliseconds, sub-ms queries, 10x fewer tokens. Single static binary, zero deps.
Why switchThe two query styles of agent code context: cocoindex-code embeds AST chunks for semantic 'find the code that does X'; codebase-memory graphs symbols for structural 'who calls this and what breaks'. Different questions — many stacks want both.
Full comparison → code-graph-ragParses a polyglot monorepo with Tree-sitter into a Memgraph knowledge graph: query it in plain English (NL→Cypher), trace data flow, find dead code, edit via AST-surgical patches.
Why switchTwo shapes of code retrieval for agents: cocoindex-code does AST-aware semantic search with local embeddings (pipx install, zero infra); code-graph-rag builds an explicit relationship graph you can walk and mutate. Search-and-read → cocoindex; structure queries and edits → this.
Full comparison → serenaThe IDE for your coding agent: an MCP toolkit giving symbol-level retrieval, editing, refactoring and debugging over real language servers — or a JetBrains plugin backend.
Why switchRetrieval by meaning versus retrieval by structure: cocoindex-code does AST-aware semantic search with local embeddings and zero config, Serena resolves actual symbols and references through the language server. Search when you don't know the name, Serena when you do.
Full comparison →