Code Context

code-context is the retrieval layer under your coding agent: one local index over the whole repo (keyword, semantic, hybrid, and SQL), reached through a CLI and an MCP server, with the index living in plain files inside your repo. Your agent answers questions about the codebase without reading it file by file.

The rule of thumb: the more a question spans the repo, the more this saves, because the answer comes from a ranked index instead of pulling source into context one file at a time.

Up to 22× fewer tokens. One query, "break this repo down by language," is ~6K tokens with code-context versus ~140K reading files. The harness is in the repo, so you can reproduce it on your own codebase.

• 🔎 Find code by words or meaning. One ranked pass fuses exact keyword matching with semantic similarity, and every hit carries the code with path:line citations.
• 📊 Ask questions grep can't answer. Search works as a SQL table function, so "which files have the most code about X" is one query: ranked by relevance, tallied by GROUP BY.
• ⚡ Searching in seconds, fresh forever. The keyword index commits before the embedding model even finishes downloading, vectors backfill in the background, and edits re-sync incrementally: only changed files re-chunk and re-embed.
• 🔒 Nothing leaves your machine. No accounts, no API keys, no database server, no telemetry. Embedding is a small local model, downloaded once; after that everything works offline.

Built on infino, a fast retrieval engine that runs SQL, full-text search, and vector search over a single copy of your data. Text and numeric data is stored as spec-compliant Parquet, and the same engine handles logs, docs, and agent memory.

cx demo: index, search, SQL aggregation, incremental sync

Quick start

npm install -g @infino-ai/code-context
cd your-repo
cx install && cx index      # keyword search live in seconds on typical repos

Or zero-install, straight into Claude Code with one command:

claude mcp add code-context -- npx -y @infino-ai/code-context mcp

(ask the agent to "index this codebase": the reindex tool bootstraps an unindexed repo in-chat, and search works while indexing runs)

CI-tested on Linux x64 (glibc) and macOS arm64; linux-arm64, musl, and Windows-via-WSL are expected to work through the engine's prebuilt bindings but are not CI-covered.

Evaluation

Real agent runs over a codebase-Q&A suite: same model (claude-opus-4-8), same turn budget, the same prompt for both lanes, stock file tools (Glob/Grep/Read/LS) as the baseline. Its sharpest edge is whole-repo relevance aggregation, which file tools cannot express at any budget: up to 22× fewer tokens (that "break down by language" query is ~6K vs ~140K), and 6.5× on aggregation questions overall. Across the whole suite: 55% fewer tokens and 71% fewer tool calls, at answer quality a blind pairwise judge could not tell apart (8 vs 12 of 20, within noise).

Benchmark: tokens per question, code-context vs stock file tools

Full methodology and per-question tables are in docs/benchmark.md, with the harness in bench/ so you can run the same lanes on your own repo.

What you get

One binary (code-context, or cx for short), one index, and a deliberately small tool surface for agents:

Three tools is a deliberate design: one way to find, one way to count, one way to stay fresh. Every additional near-duplicate retrieval tool worsens an agent's tool selection, and hybrid search's keyword half already ranks exact identifier terms highly, so a separate lexical tool has no job left.

The SQL move

Search-as-a-table composes with aggregation. Ranked by relevance, tallied by SQL, one engine pass:

SELECT path, SUM(end_line - start_line + 1) AS lines, COUNT(*) AS chunks
FROM bm25_search('chunks', 'content', 'vector index quantization', 300)
GROUP BY path ORDER BY lines DESC LIMIT 15

hybrid_search(...) and vector_search(...) work the same way. The CLI and MCP server embed {{name}} placeholders server-side, so agents never handle raw vectors.

Staged readiness

cx index commits the keyword (BM25) index first. On a ~3,000-chunk repo that takes under a second, so search works before any embedding model even exists on the machine. Vectors backfill in the background with a local model (downloaded once, no key; about two minutes for that same repo), and hybrid/semantic ranking unlocks automatically when they land. If the vector stage fails, keyword search stays live and the index says so honestly.

The default model optimizes quality-per-minute. See docs/embedder-eval.md for how it was chosen.

Your index is just files

Everything lives in .infino/ in your repo root (gitignored by cx install): plain files you can copy, cache in CI, or put on object storage. It's a live index the engine queries in place, not a snapshot you export and pass around.

Setup for agents

cx install drops steering into the repo so agents actually use the index:

cx install            # Claude Code: project skill + MCP server + status hook; AGENTS.md section
cx install --cursor   # + Cursor rules and MCP config

Any MCP client works; the server is stdio.

claude mcp add code-context -- npx -y @infino-ai/code-context mcp

{ "mcpServers": { "code-context": { "command": "npx", "args": ["-y", "@infino-ai/code-context", "mcp"] } } }

[mcp_servers.code-context]
command = "npx"
args = ["-y", "@infino-ai/code-context", "mcp"]

{ "mcpServers": { "code-context": { "command": "npx", "args": ["-y", "@infino-ai/code-context", "mcp"] } } }

{ "mcpServers": { "code-context": { "command": "npx", "args": ["-y", "@infino-ai/code-context", "mcp"] } } }

Tools: search, sql, reindex (incremental sync: an unchanged repo is a fast no-op, and the server also auto-syncs in the background as queries arrive, so results track your edits without anyone asking).

CLI

cx index [path]           sync the index (incremental; --full rebuilds, --watch follows edits)
cx search <query>         exact terms + meaning, one ranked pass           (-k hits)
cx sql <statement>        read-only SQL; --embed q="text" fills {{q}}
cx status                 what the index holds, how fresh, vector readiness
cx mcp                    serve the MCP tools over stdio
cx install                drop agent steering into the repo

Configuration

What it is, and what it isn't

code-context's lane is ranked content retrieval and content-relevance aggregation: find code by words or meaning, rank whole files by how much they're about a topic, always with path:line receipts. It deliberately does not do structural code intelligence (call-graph tracing, dead-code detection, type resolution). Tools that do are complementary: MCP servers stack, so run both.

Architecture

• Chunking: tree-sitter (WASM, no native compiles) cuts at definition boundaries for TypeScript/JS, Python, Rust, Go, Java, C/C++, Ruby, C#, PHP; Markdown splits at headings; everything else falls back to fixed windows. Every chunk carries path, start_line, end_line, lang, content.
• Index: infino tables in .infino/: BM25 (FTS) and IVF vector indexes over a single copy of the data, queried in-process through the Node binding. No server.
• Embeddings: always local. A small model (chosen by a measured eval) downloaded once; no key, no per-query network, code never leaves the machine. Queries embed with the same model the index was built with, and a mismatch is a clear error, not silently wrong results.
• Freshness: incremental by design. A per-file state map (size/mtime prefilter, then content hash) means a sync re-chunks and re-embeds only the files that changed: on a ~3,000-chunk repo an unchanged tree checks in ~20ms and a one-file edit syncs in ~0.7s with vectors kept current (larger-repo numbers in the benchmark). The MCP server auto-syncs in the background as queries arrive (never blocking a query), cx index is incremental by default (--full to rebuild), and cx index --watch syncs on file events.

Learn more

• Code search for coding agents - the crawl-vs-retrieve model and when an index saves tokens.
• FAQ - what it is, when to use it, local-only guarantees, freshness.
• Tradeoffs - the honest limits.
• Benchmark - measured results, with a harness to reproduce them on your own repo.

License

Apache-2.0