StackMap
Subscribe

cocoindex-code vs jevgrep

AST-based semantic code search for coding agents: pipx install, zero config, local embeddings out of the box — a CLI/skill/MCP that cuts agent context ~70% vs grepping. Built on CocoIndex. — versus — Find code by asking what it does: `jg` uses the Jev decision model to judge folders, files and declarations, returning relevant files plus verbatim excerpts for coding agents. CLI + skill.

The curated verdict

Both answer 'where does this behavior live' for coding agents by meaning, not exact text; cocoindex-code builds a local AST + embedding index, jevgrep judges relevance at query time with Jev and needs no index.

cocoindex-codejevgrep
Stars2.8k2.6k
Forks228189
LanguagePythonTypeScript
LicenseApache-2.0MIT
Last activity5 days ago9 days ago
Topicscode-intel, localcode-intel, coding
Curated connections93

cocoindex-code — the curator's take

The lowest-friction entry in the code-context-server category: one pipx install, zero config, and the [full] variant ships local embeddings so there's no API key before first search. AST-aware chunking plus the CocoIndex engine underneath means the index stays fresh incrementally instead of rebuilding. Integrates as a skill or MCP with Claude Code, Codex, Cursor. NOT the deepest graph: it's semantic search, not call-graph analysis — no callers/blast-radius queries (that's TokenSave or codegraph-mcp territory) — and the slim install quietly requires a cloud embedding key while [full] costs ~1GB of torch.

jevgrep — the curator's take

Use it when your agent lands in an unfamiliar repo and burns turns grepping for where a behavior lives — no index to build, and measured ~26% lower total cost at the same solve rate on its own 10-task SWE-bench run. Skip it when you already know the symbol or path (plain `rg` wins), or when you want zero per-query spend: every search is a paid Jev call through Vercel AI Gateway, TypeSafe, OpenRouter or a compatible endpoint. Install the skill too, or agents won't call it.