justrach/kuri: Browser automation and web crawling for AI agents. Zig-native, token-efficient CDP snapshots, HAR recording, and a standalone fetcher. · GitHub

Browser automation & web crawling for AI agents. Written in Zig. Zero Node.js.

CDP automation · A11y snapshots · HAR recording · Standalone fetcher · Interactive terminal browser · Agentic CLI · Security testing

Quick Start · Benchmarks · kuri-agent · Security Testing · API · Changelog

Why teams switch to Kuri: 464 KB binary, ~3 ms cold start. On Google Flights, a full agent loop (go→snap→click→snap→eval) costs 4,110 tokens vs 4,880 for agent-browser — 16% less per cycle, compounding across multi-step tasks.

Most browser tooling was built for QA engineers. Kuri is built for agent loops: read the page, keep token cost low, act on stable refs, and move on.

• The product story is not “most commands.” It is “useful state from real pages at the lowest model cost.”
• A tiny output only counts if the page actually rendered. Empty-shell output is a failure mode, not a win.
• The best proof is same-page, same-session, same-tokenizer comparisons.

Same Chrome session, measured with tiktoken cl100k_base. Run ./bench/token_benchmark.sh to reproduce.

kuri saves 16% tokens per workflow cycle — compounding across multi-step tasks.

Action responses are flat JSON (🔥) instead of nested CDP, which adds up:
click = 9 tokens, back = 5 tokens, scroll = 5 tokens.

Why lightpanda scores low: Lightpanda can’t execute JS-heavy SPAs. Google Flights renders via client-side fetch() — lightpanda returns a 507-token empty nav shell with zero flight data. The low token count is a failed render, not efficiency.

Measured on Apple M3 Pro, macOS 15.3. kuri built with -Doptimize=ReleaseFast. agent-browser v0.20.0.

                        agent-browser        kuri             delta
                        (v0.20)              (v0.2)
─────────────────────────────────────────────────────────────────────
CLI binary              6.0 MB               464 KB           13× smaller
Cold start (--version)  3.4 ms               3.0 ms           ~same
Install (npm)           33 MB                3.3 MB (3 bins)  10× smaller
Commands                140+                 40+ endpoints    different focus
Standalone fetcher      ❌                    ✅ kuri-fetch     no Chrome needed
Terminal browser        ❌                    ✅ kuri-browse    interactive REPL
JS engine (no Chrome)   ❌                    ✅ QuickJS        SSR-style DOM
HTTP API server         ❌ (CLI only)         ✅ kuri           thread-per-conn

agent-browser exposes a broader browser-control surface. Kuri is intentionally narrower: a lightweight HTTP API and CLI stack optimized for agent integration, token economy, and deployment simplicity.

Every browser automation tool drags in Playwright (~300 MB), a Node.js runtime, and a cascade of npm dependencies. Your AI agent just wants to read a page, click a button, and move on.
Kuri is a single Zig binary. Four modes, zero runtime:

kuri           →  CDP server (Chrome automation, a11y snapshots, HAR)
kuri-fetch     →  standalone fetcher (no Chrome, QuickJS for JS, ~2 MB)
kuri-browse    →  interactive terminal browser (navigate, follow links, search)
kuri-agent     →  agentic CLI (scriptable Chrome automation + security testing)

curl -fsSL https://raw.githubusercontent.com/justrach/kuri/main/install.sh | sh

Detects your platform, downloads the right binary, installs to ~/.local/bin.
macOS binaries are notarized — no Gatekeeper prompt.

bun install -g kuri-agent
# or: npm install -g kuri-agent

Downloads the correct native binary for your platform at install time.

Download the tarball for your platform from GitHub Releases and unpack it to your $PATH.

Requires Zig ≥ 0.15.0.

git clone https://github.com/justrach/kuri.git
cd kuri
zig build -Doptimize=ReleaseFast
# Binaries in zig-out/bin/: kuri  kuri-agent  kuri-fetch  kuri-browse

Requirements: Zig ≥ 0.15.1 · Chrome/Chromium (for CDP mode)

git clone https://github.com/justrach/kuri.git
cd kuri

zig build              # build everything
zig build test         # run 230+ tests

# CDP mode — launches Chrome automatically
./zig-out/bin/kuri

# Standalone mode — no Chrome needed
./zig-out/bin/kuri-fetch https://example.com

# Interactive browser — browse from your terminal
./zig-out/bin/kuri-browse https://example.com

# start the server; if CDP_URL is unset, kuri launches managed Chrome for you
./zig-out/bin/kuri

# discover tabs from that managed browser
curl -s http://127.0.0.1:8080/discover

# inspect the discovered tab list
curl -s http://127.0.0.1:8080/tabs

If you already have Chrome running with remote debugging, set CDP_URL to either the WebSocket or HTTP endpoint:

CDP_URL=ws://127.0.0.1:9222/devtools/browser/... ./zig-out/bin/kuri
# or
CDP_URL=http://127.0.0.1:9222 ./zig-out/bin/kuri

# 1. Discover Chrome tabs
curl -s http://localhost:8080/discover
# → {"discovered":1,"total_tabs":1}

# 2. Get tab ID
curl -s http://localhost:8080/tabs
# → [{"id":"ABC123","url":"chrome://newtab/","title":"New Tab"}]

# 3. Navigate
curl -s "http://localhost:8080/navigate?tab_id=ABC123&url=https://vercel.com"

# 4. Get accessibility snapshot (token-optimized for LLMs)
curl -s "http://localhost:8080/snapshot?tab_id=ABC123&filter=interactive"
# → [{"ref":"e0","role":"link","name":"VercelLogotype"},
#    {"ref":"e1","role":"button","name":"Ask AI"}, ...]

All endpoints return JSON. Optional auth via KURI_SECRET env var.

On macOS, auth profile secrets are stored in the user Keychain. On other platforms, Kuri falls back to .kuri/auth-profiles/.

url and expression query params are percent-decoded by the server, so encoded values like https%3A%2F%2Fexample.com are accepted.

Kuri applies anti-detection patches automatically on startup — no manual config needed.

• Page.addScriptToEvaluateOnNewDocument — stealth patches run before any page JS
• navigator.webdriver = false — hides automation flag at Chromium level (--disable-blink-features=AutomationControlled)
• WebGL/Canvas/AudioContext spoofing — defeats fingerprint-based detection
• UA rotation — 5 realistic Chrome/Safari/Firefox user agents
• chrome.csi/chrome.loadTimes — stubs for Akamai-specific checks

Navigate auto-detects blocks and returns structured fallback:

curl -s "http://localhost:8080/navigate?tab_id=ABC&url=https://protected-site.com"
# If blocked:
# {"blocked":true,"blocker":"akamai","ref_code":"0.7d...",
#  "fallback":{"suggestions":["Open URL directly in browser","Use KURI_PROXY"]}}
# If ok: normal CDP response

Detects: Akamai, Cloudflare, PerimeterX, DataDome, generic captcha.

KURI_PROXY=socks5://user:pass@residential-proxy:1080 ./zig-out/bin/kuri
KURI_PROXY=http://proxy:8080 ./zig-out/bin/kuri

Standalone HTTP fetcher — no Chrome, no Playwright, no npm. Ships as a ~2 MB binary with built-in QuickJS for JS execution.

zig build fetch    # build + run

# Default: convert to Markdown
kuri-fetch https://example.com

# Extract links
kuri-fetch -d links https://news.ycombinator.com

# Structured JSON output
kuri-fetch --json https://example.com

# Execute inline scripts via QuickJS
kuri-fetch --js https://example.com

# Write to file, quiet mode
kuri-fetch -o page.md -q https://example.com

# Pipe-friendly: content → stdout, status → stderr
kuri-fetch -d text https://example.com | wc -w

• 5 output modes — markdown, html, links, text, json
• QuickJS JS engine — --js executes inline
  Like Us

  Follow Us

  Subscribe Us

  Follow Us