Overview
Jevlin is SuperSearch for coding agents. SuperSearch asks every search provider at once, says which ones found each result, and gives you the receipt. Jevlin asks eight providers in one call and answers with one list. Search is billed at each provider's own price with no markup. Available in Claude Code, Cursor, Codex, opencode, Pi and Hermes.
Every search is observable on the platform. A trace shows one search with a receipt per provider: what each returned, how long it took, what it cost. A trajectory shows one thread, an agent's session, as the path it took, turn by turn: what the agent was working on when it searched, what came back, and what it concluded. Each search carries the context that makes this possible, hashed and scrubbed before it leaves the machine. See Trajectory observability.
Setup registers you with the search platform and gets a key, with no browser. A new account starts with $10 of credit; see Pricing and credit and How an agent gets an API key.
Get started
Install it, then run setup. Setup registers your installation, writes a skill and hooks into each coding agent it finds, and prints a link to claim your agent. The quickstart walks through it.
- npm (recommended)
- Native install
- Manual download
- From a marketplace
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.
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 installs patch releases of its own minor by itself, and a new minor with jevlin upgrade; see Upgrading.
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.
Let the agent do the install. Each marketplace carries the same setup skill: it installs the client and runs jevlin setup, which writes the agent's own search skill and hooks. Without setup there is no search.
Claude Code (2.1.275 or later), inside a session:
/plugin install jevlin --marketplace jevlinai/jevlin-go
Codex CLI, then pick Jevlin from /plugins:
codex plugin marketplace add jevlinai/jevlin-go
Cursor: open the Marketplace in Cursor and install Jevlin. See Cursor.
Any agent that reads skills (skills.sh):
npx skills add jevlinai/jevlin-go
Then ask the agent to set up Jevlin. An agent handed a link does the same from jevlin.ai/agents.md.
What you can do
Here are some of the ways you can use Jevlin:
Search the web from your agent
The skill makes Jevlin the default search in Claude Code, Cursor, Codex, Pi and Hermes, and the rules block you paste into opencode's AGENTS.md sends its public-web searches here too, so an ordinary question that needs the web is enough. Name it to be explicit:
/jevlin what changed in Vite 7's rollup migration
Ask eight providers at once
A balanced search asks four independent search engines and a max search asks all eight (Exa, Brave, Parallel, Serper, TinyFish, Perplexity, Ceramic and Seltz), and merges what they return into one list deduplicated by page. Each entry says which providers found it, so agreement between independent indexes is evidence the agent can read.
{"version":1,"query":"postgres 18 uuidv7 default column performance","tier":"balanced"}
See Providers and tiers.
Inspect every search as a trace
Each search appears on the platform with a receipt per provider: whether it answered, how long it took, how many results it returned and what it cost. Open one when an answer looks thin and see which arm let it down.
Follow a thread as a trajectory
Searches carry hashed session, turn and call ids and the assistant text that led to them, so the platform shows a thread, one agent session, as the path the agent took: what it was working on when it searched, what came back, and what it concluded, turn by turn, across compactions and subagents.
Keep queries and secrets off the wire
The query travels as JSON on stdin, never on the command line. The context that travels with a search is scrubbed of anything shaped like a credential, a key block, an email address or your account name before it leaves, and JEVLIN_TRACE=off sends none of it.
export JEVLIN_TRACE=off
Tune a search per request
Besides query and tier, a request can carry objective, search_queries, recency, domain_filter, max_results, merged_limit, max_chars, page_chars, cache and providers. Every field is in the stdin request.
{"version":1,"query":"array flatten method","domain_filter":["developer.mozilla.org"],"max_results":5}
See Request options.
Report what a turn concluded
With turn_end on, the agent's end-of-turn hook also sends what you asked, the final answer, and each tool called by name, duration and outcome, never a tool's input or output, and only for turns that searched.
[search]
turn_end = true
See The turn end.
Script it from a shell
The same binary answers a person or a script. --stdin is the versioned contract; status, doctor, connect and limits take -json.
jevlin search --stdin <<'JSON'
{"version":1,"query":"what is proof of authority consensus"}
JSON
jevlin status -json
See Search from a shell.
Use Jevlin everywhere
One installation serves every agent on the machine: the same key, the same tier, the same sessions directory. Setup finds the agents on PATH and writes what each one needs.
| What I want to do | Best option |
|---|---|
| Search from Claude Code | Claude Code: a skill, hooks and allow rules in settings.json |
| Search from Cursor | Cursor: a skill and hooks, one lineage file per conversation |
| Search from Codex | Codex: a skill, hooks and a permission profile that opens only the search hosts |
| Search from opencode | opencode: an in-process plugin and a rules block for AGENTS.md |
| Search from Pi | Pi: a skill and an auto-discovered extension |
| Search from Hermes | Hermes: a skill and one hook in config.yaml |
| Use it from an agent that is not listed | Any other agent: paste the rules block |
| Call it from a script, CI or my own shell | Search from a shell |
| Make the agent's own search the default again | /jevlin off in the agent, or jevlin agents prefer off; see Search from your agent |
| Ask for a wider search on a hard question | /jevlin tier balanced; see Choosing a tier |
| See what my agents searched, and why | platform.jevlin.ai, Traces and Trajectories; see Trajectory observability |