codebase-memory-mcp vs tokensave
Code 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. — versus — 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.
The same exact job — pre-indexed structural code intelligence over MCP so agents stop grepping. TokenSave is a libSQL semantic graph across 50+ languages; codebase-memory is a zero-dependency C binary betting everything on speed: 158 languages, sub-ms.
| codebase-memory-mcp | tokensave | |
|---|---|---|
| Stars | 34k | 477 |
| Forks | 2.6k | 43 |
| Language | C | Rust |
| License | MIT | MIT |
| Last activity | yesterday | today |
| Topics | coding, local | coding, local |
| Curated connections | 3 | 9 |
codebase-memory-mcp — the curator's take
The performance ceiling of the code-context-server category: pure C, single static binary, the Linux kernel indexed in 3 minutes, structural queries under a millisecond — with a peer-reviewed preprint (83% answer quality, 10x fewer tokens across 31 repos) instead of vibes. Hybrid LSP adds real type resolution for the 12 languages that matter most, and 43 client surfaces means it plugs into whatever agent you run. NOT semantic search — it answers structural questions (call chains, routes, blast radius), not 'where's the code that does X'; pair it with an embedding tool for that. And note its own disclosure: it writes to your agent config files by design — audit posture is unusually good (SLSA 3, OpenSSF, per-release VirusTotal), use it.
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.