Quickstart

Five minutes from nothing to a coding agent that searches through Jevlin.

Install

npm (recommended)

npm install -g @jevlinsearch/jevlin
jevlin setup

Install it globally, never with npx. Setup writes the binary's path into your agents' skills and hooks, and npm throws away an npx cache or a project's node_modules. An npm install is updated with npm install -g @jevlinsearch/jevlin@latest.

Native install

macOS, Linux, WSL:

curl -fsSL https://jevlin.ai/install.sh | sh

Windows PowerShell:

irm https://jevlin.ai/install.ps1 | iex

Windows CMD:

curl -fsSL https://jevlin.ai/install.cmd -o install.cmd && install.cmd && del install.cmd

The installer downloads the latest release for your machine from the project's GitHub releases, checks the project's signature on that release and the archive's checksum, puts the binary at ~/.jevlin/bin/jevlin, and starts jevlin setup. The signature check uses openssl, node or python3 with cryptography, whichever is present; on Windows it uses node. Set JEVLIN_VERSION to install an exact release, or JEVLIN_NO_SETUP=1 to stop after the binary. A native install keeps itself current; see Upgrading.

Manual download

Download the archive for your OS and architecture from the releases page and verify it against that release's checksums.txt. Put jevlin in a directory only you can write, such as ~/.local/bin, and run jevlin setup from there.

tar -xzf jevlin_<version>_<os>_<arch>.tar.gz
mkdir -p ~/.local/bin && mv jevlin ~/.local/bin/
~/.local/bin/jevlin setup

Setup refuses a binary under the temp directory, or in a directory another user owns or every user can write, because your agents' hooks and your PATH will name that path.

Set up

jevlin setup

Setup registers with the search platform and stores the key it gets back. There is no key to copy. It then asks a few questions, each with a sensible default:

question	what your answer does
Enable mining rewards?	No, the default, gives you search. Yes also enrolls this installation in mining and asks for a payout address. See Earning with mining.
Add them to ~/.zshrc?	Or whichever profile your shell reads. Puts jevlin on PATH and sets JEVLIN_CONFIG. On Windows it asks Set them for your user? instead.
Set up the coding agents found on this machine now?	Writes a skill and hooks into each agent's own config, after showing you the plan.

Setup then prints a link where you claim your agent on platform.jevlin.ai. You need not do it now: search already works, and using an agent later finishes the claim. Setup in detail explains every question and the flags that answer them for you.

Check

jevlin status          # what this installation has and has not completed
jevlin agents status   # which agents are set up
jevlin search -format model "what is proof of authority consensus"

It is working when the search prints results and agents status lists your agents as installed. Restart any agent that was already open.

Search from your agent

Open Claude Code, Cursor, Codex, Pi or Hermes and ask it something that needs the web. The skill makes Jevlin the default search, so an ordinary question is enough. To be explicit:

/jevlin what changed in Vite 7's rollup migration

The agent sends one JSON request on stdin, reads one JSON envelope back, and answers from the merged list. Set the band every search carries with /jevlin tier balanced, or leave it to the router's default. See Search from your agent.

What your agent sends

The agent never puts your query on the command line. It pipes JSON:

jevlin search --stdin <<'JSON'
{"version":1,"query":"what is proof of authority consensus"}
JSON

The answer is one JSON object with result.merged, the citations of every provider that answered, deduplicated by page, each with found_by naming the providers that agree on it. See The stdin request and the envelope.

Next steps

Providers and tiersWhich providers run, and when fast, balanced or max is right.Trajectory observabilityHow a session's searches line up into one path on the platform.Your agentWhat was written into it, and what to know.