techaro.lol
Weighs the soul of incoming HTTP requests to stop AI crawlers
1## Anubis has the ability to let you import snippets of configuration into the main
2## configuration file. This allows you to break up your config into smaller parts
3## that get logically assembled into one big file.
4##
5## Of note, a bot rule can either have inline bot configuration or import a
6## bot config snippet. You cannot do both in a single bot rule.
7##
8## Import paths can either be prefixed with (data) to import from the common/shared
9## rules in the data folder in the Anubis source tree or will point to absolute/relative
10## paths in your filesystem. If you don't have access to the Anubis source tree, check
11## /usr/share/docs/anubis/data or in the tarball you extracted Anubis from.
12
13bots:
14 # Pathological bots to deny
15 - # This correlates to data/bots/deny-pathological.yaml in the source tree
16 # https://github.com/TecharoHQ/anubis/blob/main/data/bots/deny-pathological.yaml
17 import: (data)/bots/_deny-pathological.yaml
18 - import: (data)/bots/aggressive-brazilian-scrapers.yaml
19
20 # Aggressively block AI/LLM related bots/agents by default
21 - import: (data)/meta/ai-block-aggressive.yaml
22
23 # Consider replacing the aggressive AI policy with more selective policies:
24 # - import: (data)/meta/ai-block-moderate.yaml
25 # - import: (data)/meta/ai-block-permissive.yaml
26
27 # Search engine crawlers to allow, defaults to:
28 # - Google (so they don't try to bypass Anubis)
29 # - Apple
30 # - Bing
31 # - DuckDuckGo
32 # - Qwant
33 # - The Internet Archive
34 # - Kagi
35 # - Marginalia
36 # - Mojeek
37 - import: (data)/crawlers/_allow-good.yaml
38 # Challenge Firefox AI previews
39 - import: (data)/clients/x-firefox-ai.yaml
40
41 # Allow common "keeping the internet working" routes (well-known, favicon, robots.txt)
42 - import: (data)/common/keep-internet-working.yaml
43
44 # # Punish any bot with "bot" in the user-agent string
45 # # This is known to have a high false-positive rate, use at your own risk
46 # - name: generic-bot-catchall
47 # user_agent_regex: (?i:bot|crawler)
48 # action: CHALLENGE
49 # challenge:
50 # difficulty: 16 # impossible
51 # report_as: 4 # lie to the operator
52 # algorithm: slow # intentionally waste CPU cycles and time
53
54 # Requires a subscription to Thoth to use, see
55 # https://anubis.techaro.lol/docs/admin/thoth#geoip-based-filtering
56 - name: countries-with-aggressive-scrapers
57 action: WEIGH
58 geoip:
59 countries:
60 - BR
61 - CN
62 weight:
63 adjust: 10
64
65 # Requires a subscription to Thoth to use, see
66 # https://anubis.techaro.lol/docs/admin/thoth#asn-based-filtering
67 - name: aggressive-asns-without-functional-abuse-contact
68 action: WEIGH
69 asns:
70 match:
71 - 13335 # Cloudflare
72 - 136907 # Huawei Cloud
73 - 45102 # Alibaba Cloud
74 weight:
75 adjust: 10
76
77 ## System load based checks.
78 # If the system is under high load, add weight.
79 - name: high-load-average
80 action: WEIGH
81 expression: load_1m >= 10.0 # make sure to end the load comparison in a .0
82 weight:
83 adjust: 20
84
85 ## If your backend service is running on the same operating system as Anubis,
86 ## you can uncomment this rule to make the challenge easier when the system is
87 ## under low load.
88 ##
89 ## If it is not, remove weight.
90 # - name: low-load-average
91 # action: WEIGH
92 # expression: load_15m <= 4.0 # make sure to end the load comparison in a .0
93 # weight:
94 # adjust: -10
95
96 # Generic catchall rule
97 - name: generic-browser
98 user_agent_regex: >-
99 Mozilla|Opera
100 action: WEIGH
101 weight:
102 adjust: 10
103
104dnsbl: false
105
106# #
107# impressum:
108# # Displayed at the bottom of every page rendered by Anubis.
109# footer: >-
110# This website is hosted by Zombocom. If you have any complaints or notes
111# about the service, please contact
112# <a href="mailto:contact@domainhere.example">contact@domainhere.example</a>
113# and we will assist you as soon as possible.
114
115# # The imprint page that will be linked to at the footer of every Anubis page.
116# page:
117# # The HTML <title> of the page
118# title: Imprint and Privacy Policy
119# # The HTML contents of the page. The exact contents of this page can
120# # and will vary by locale. Please consult with a lawyer if you are not
121# # sure what to put here
122# body: >-
123# <p>Last updated: June 2025</p>
124
125# <h2>Information that is gathered from visitors</h2>
126
127# <p>In common with other websites, log files are stored on the web server saving details such as the visitor's IP address, browser type, referring page and time of visit.</p>
128
129# <p>Cookies may be used to remember visitor preferences when interacting with the website.</p>
130
131# <p>Where registration is required, the visitor's email and a username will be stored on the server.</p>
132
133# <!-- ... -->
134
135# Open Graph passthrough configuration, see here for more information:
136# https://anubis.techaro.lol/docs/admin/configuration/open-graph/
137openGraph:
138 # Enables Open Graph passthrough
139 enabled: false
140 # Enables the use of the HTTP host in the cache key, this enables
141 # caching metadata for multiple http hosts at once.
142 considerHost: false
143 # How long cached OpenGraph metadata should last in memory
144 ttl: 24h
145 # # If set, return these opengraph values instead of looking them up with
146 # # the target service.
147 # #
148 # # Correlates to properties in https://ogp.me/
149 # override:
150 # # og:title is required, it is the title of the website
151 # "og:title": "Techaro Anubis"
152 # "og:description": >-
153 # Anubis is a Web AI Firewall Utility that helps you fight the bots
154 # away so that you can maintain uptime at work!
155 # "description": >-
156 # Anubis is a Web AI Firewall Utility that helps you fight the bots
157 # away so that you can maintain uptime at work!
158
159# By default, send HTTP 200 back to clients that either get issued a challenge
160# or a denial. This seems weird, but this is load-bearing due to the fact that
161# the most aggressive scraper bots seem to really, really, want an HTTP 200 and
162# will stop sending requests once they get it.
163status_codes:
164 CHALLENGE: 200
165 DENY: 200
166
167# Anubis can store temporary data in one of a few backends. See the storage
168# backends section of the docs for more information:
169#
170# https://anubis.techaro.lol/docs/admin/policies#storage-backends
171store:
172 backend: memory
173 parameters: {}
174
175# The weight thresholds for when to trigger individual challenges. Any
176# CHALLENGE will take precedence over this.
177#
178# A threshold has four configuration options:
179#
180# - name: the name that is reported down the stack and used for metrics
181# - expression: A CEL expression with the request weight in the variable
182# weight
183# - action: the Anubis action to apply, similar to in a bot policy
184# - challenge: which challenge to send to the user, similar to in a bot policy
185#
186# See https://anubis.techaro.lol/docs/admin/configuration/thresholds for more
187# information.
188thresholds:
189 # By default Anubis ships with the following thresholds:
190 - name: minimal-suspicion # This client is likely fine, its soul is lighter than a feather
191 expression: weight <= 0 # a feather weighs zero units
192 action: ALLOW # Allow the traffic through
193 # For clients that had some weight reduced through custom rules, give them a
194 # lightweight challenge.
195 - name: mild-suspicion
196 expression:
197 all:
198 - weight > 0
199 - weight < 10
200 action: CHALLENGE
201 challenge:
202 # https://anubis.techaro.lol/docs/admin/configuration/challenges/metarefresh
203 algorithm: metarefresh
204 difficulty: 1
205 report_as: 1
206 # For clients that are browser-like but have either gained points from custom rules or
207 # report as a standard browser.
208 - name: moderate-suspicion
209 expression:
210 all:
211 - weight >= 10
212 - weight < 20
213 action: CHALLENGE
214 challenge:
215 # https://anubis.techaro.lol/docs/admin/configuration/challenges/proof-of-work
216 algorithm: fast
217 difficulty: 2 # two leading zeros, very fast for most clients
218 report_as: 2
219 # For clients that are browser like and have gained many points from custom rules
220 - name: extreme-suspicion
221 expression: weight >= 20
222 action: CHALLENGE
223 challenge:
224 # https://anubis.techaro.lol/docs/admin/configuration/challenges/proof-of-work
225 algorithm: fast
226 difficulty: 4
227 report_as: 4