Code Context

SuperGrep

Retrieval + inference offload for AI coding agents. Help your agents find answers faster and at lower cost, while keeping the same answer quality. Particularly useful for cheaper models.

[Try it live at infino.ai/supergrep](https://infino.ai/supergrep) - put a question to a real codebase and watch the same model answer it with and without SuperGrep, side by side, with the bill for each. Supergrep uses Infino for retrieval, which tightly integrates small language models with indexes for scalable agent retrieval on object storage.

SuperGrep offers agents four tools over an Infino index, kept in two places. find and plain sql run on your machine, over the keyword index. Conversely, anything with meaning in it - search, a sql statement with a ranked search inside it, and ask - runs in the Infino cloud, so heavy compute and embeddings stays off your laptop. Infino also embeds inference models in its service, so several small models work the index at once and hand your agent the rows they found. Your agent keeps the reasoning, writes the answer, and decides when to use SuperGrep. No configuration.

The four tools, one line each - for the agent reading this

What people use it for

• Code review. The reviewer's question is "what else calls this, and what breaks if it changes". find answers with every caller and the counts in one call, and ask reads the paths that matter, so the review is about the change rather than about finding it.
• Big explorations. "How does X work end to end" spawns fifty look-ups. With SuperGrep they run as fifty asks in parallel against the index, instead of fifty subagents reading the tree into your bill.
• Several codebases at once. Every local tool takes a repository path, so one session roams across every repo it touches - the service, the client, the shared library - without a checkout per question.
• Code, logs and issues together. Index the logs, the test output and the issue export beside the source, and "why did this integration test start failing?" is one question over all of them.

Your agent reaches for it on its own

The model's own file tools stayed available throughout. What it had from SuperGrep was the server's instructions, which say which tool fits which kind of question; the choice on each call was the model's. The calls that are not SuperGrep are mostly Read: the model opens a file *after* the index has told it which one, rather than instead of asking. That is the shape you want - the index does the finding, and the model still opens what it needs to quote.

Go beyond code - index your entire laptop or any corpus

SuperGrep looks across all the files a question needs, not just the source. Logs, test output, stack traces, CI output, configuration and docs go in beside the code - .log, .out, .err, .jsonl and .ndjson are chunked at record boundaries, so a stack trace stays with the message that explains it - and the same four tools run over all of it: find for an exact stack frame, search for a failure you can only describe, sql to count and rank across a run, ask for the question that spans several of them at once.

That matters most where a frontier model is weakest. A log is the pathological case for a context window - large, repetitive, mostly irrelevant, and paid for again on every turn it stays in the transcript. An index collapses it to the spans that matter before the model sees any of it. On a public benchmark of CI-failure diagnosis, scored by the benchmark's own judge, that puts SuperGrep second on the score and first by a distance on score per token of context:

For files that don't fit on your laptop - write them out to Parquet files in object storage and point SuperGrep at them without ever loading them onto your laptop (how). You can search them together with your code or laptop files using the same tools.

What it saves

The same model, the same 36 questions about a 256,000-line codebase, with and without SuperGrep. Every answer was checked against the code. Fully correct means every claim held and the whole question was answered. The bill is everything you pay: your model, its subagents, and SuperGrep.

How the runs were set up

Real agent runs through the Claude Agent SDK, the same minimal prompt in every arm, on the infino engine repository, measured 2026-09-24. Thirty-six questions in five categories: aggregation (10), comprehension (6), by meaning (6), pinpoint (8), known file (6). The file-tools arm is stock Claude Code: Glob, Grep, Read, LS, Bash, and the Agent tool with the built-in Explore subagent. The SuperGrep arm is the same plus the four tools above. The judge is Opus 5.5.

Your mileage will vary with the model.

• Cheaper on every model. Haiku 41% off the total bill, Sonnet 58%, Opus 26%, Fable 14%.
• Quality increases on the cheaper models. Haiku gets eight more fully correct answers with SuperGrep than without. On Sonnet, Opus and Fable the answers are level: the judge is itself a model, and graded four times the same answers came back with 19, 20, 17 and 23 claims it could not verify, so a difference under about six answers in 36 is noise, and those three are inside it.
• No surprise bills. On about a third of the questions, Sonnet with file tools sends a subagent off to read through the repository. That one question then costs four to five times as much and takes four times as long. With SuperGrep it asks the index instead. Over the 36 questions that is $3.66 against $8.73 and 20 minutes against 41, with 20 fully correct answers against 18.
• On your own code the gap is wider. These runs are on a public, open-source repository, because that is a test anyone can repeat - and the large models have seen it in training, which is a head start for reading files. On a private codebase the model has never seen, the index does more of the work, and the effect of SuperGrep is larger.

Where it wins, and where it does not

It wins on questions about the whole codebase: counts, rankings, every occurrence. Grep gives the first forty matches; an index gives the total. It loses on finding one named thing with a large model, which reads whole files well.

The cheapest model with SuperGrep against the most expensive without

23 correct answers to their 25, for $1.09 instead of $6.32 (Opus) or $19.36 (Fable).

Install

Two commands, once per machine. You need Claude Code and node 22 or newer, on macOS or Linux.

claude plugin marketplace add infino-ai/supergrep

claude plugin install supergrep@infino-ai

(The plugin was called code-context before; an earlier install is replaced with claude plugin uninstall code-context@infino-ai and the two commands above. The MCP server inside keeps its name, so nothing the agent learned changes.)

That is the setup. Open Claude Code in any directory - a repository, a folder of logs, your notes, anything - and ask a question. The first question indexes the directory, and find, sql and read answer from then on. Nothing is configured per directory, no account exists yet, and nothing has left your machine.

search and ask are the cloud half - the embeddings and the retrieval loop run on the Infino platform, over a copy of the index kept there - and they need an account. The first time a question needs them, Claude tells you the one command and does not run it, because it is yours to run. Once, in a terminal:

npx -y @infino-ai/code-context login --platform https://api.supergrep.infino.ai

A free account, no credit card required. There is no form, no email, no password and no card, and nothing is created without your say-so: the command tells you that the contents of the directories you use search and ask in will be uploaded to Infino, asks, and only on your yes creates the account and stores its key at ~/.infino/key, mode 600, readable only by you. No config file ever holds a key or a path to one. Infino is SOC 2 Type 2 certified.

Keep that key. Because the free account asks for no email and no card, the key is the only thing that identifies you: it is how you get back in, and nothing else can. Back it up somewhere safe. When you add your details in the Infino console the same account gains a sign-in, and keys can be managed from there.

Restart the session and every directory you open has all four tools. Each one gets its own database on your account, named after the directory and loaded the first time you use search or ask there - a directory you only ever find in is never uploaded. One server answers for every directory a session touches: the tools take a path, so a session that spans several projects names the one it means. When the free credit runs out, ask says so and tells you how to add billing details and a card to the same account; find and plain sql keep working throughout.

If you already have an Infino account

Sign in once per machine instead. The key comes from a file or standard input, never from an argument - argv is readable by every process on the machine - and --yes is the same agreement the sign-up asks for, since a piped key leaves no terminal to ask on:

npx -y @infino-ai/code-context login --db https://api.supergrep.infino.ai --yes < keyfile

Other MCP clients, and one entry per repository

Cursor, Codex CLI, Gemini CLI, Windsurf and Cline take the same server over stdio. cx install in a repository writes its entry into .mcp.json there (--config for another client's file); with the account stored it names the repository's database and nothing else, --local-only writes the keyword-only entry, and install --platform https://api.supergrep.infino.ai is the sign-up and the entry in one for a ma