tokensave vs zvec-grep
Code-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. — versus — zg: 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.
Both exist so the agent stops re-reading files. tokensave serves a pre-indexed semantic graph over MCP; zg serves ranked search from a CLI. Graph queries vs search queries over the same workspace.
| tokensave | zvec-grep | |
|---|---|---|
| Stars | 616 | 2.8k |
| Forks | 61 | 144 |
| Language | Rust | TypeScript |
| License | MIT | Apache-2.0 |
| Last activity | 2 days ago | yesterday |
| Topics | code-intel, local | code-intel, rag, local |
| Curated connections | 15 | 4 |
tokensave — the curator's take
Use it to stop agents burning tokens on grep/glob/read exploration: one MCP call returns the symbols, relationships and snippets a task needs, and it's local (libSQL, no cloud). Broad reach — 50+ languages, 12+ agent integrations. NOT worth it on small repos where a couple of greps suffice, and it's an index you must keep fresh (re-index on change) — a stale graph misleads the agent. 80+ tools is a lot of surface; most tasks touch a handful.
zvec-grep — the curator's take
Give it to a coding agent that wastes tool calls grepping: `zg index` builds a local index (embeddings can stay local — potion-retrieval-32m is the default), then `zg query` returns ranked, source-linked results across code, Markdown and structured files, and the agent drops to exact/regex only to confirm. Fewer calls, fewer tokens, nothing leaves the machine unless you allow a remote embedder. Built on Alibaba's zvec engine; direct and server modes. NOT a symbol-aware tool — it doesn't know what a function is, only what text means — and NOT a graph: for call edges and blast radius use a code-intelligence server.