Mirror of https://github.com/roostorg/awesome-safety-tools
README: alphabetize and tweak for consistency
+136
-117
+136
-117
README.md
+136
-117
README.md
···
1
1
# awesome-safety-tools
2
+
2
3
A collection of open source tools for online safety
3
4
5
+
Inspired by prior work like [Awesome Redteaming](https://github.com/yeyintminthuhtut/Awesome-Red-Teaming/) and [Awesome Phishing](https://github.com/PhishyAlice/awesome-phishing). This list is not an endorsement, but rather an attempt to organize and map the available technology. ❤️
4
6
5
-
Inspired by prior work like [Awesome Redteaming](https://github.com/yeyintminthuhtut/Awesome-Red-Teaming/) and [Awesome Phishing](https://github.com/PhishyAlice/awesome-phishing). This list is not an endorsement, but rather an attempt to organize and map the available technology ❤️
7
+
Help contribute by opening a pull request to add more resources and tools!
6
8
7
-
Help and contribute by adding a pull request to add more resources and tools!
8
9
10
+
## Hash Matching
9
11
10
-
## Hash Matching
12
+
* [Altitude by Jigsaw](https://github.com/jigsaw-code/altitude)
13
+
* web UI and hash matching for violent extremism and terrorism content
11
14
* [Hasher Matcher Action (HMA) by Meta](https://github.com/facebook/ThreatExchange/tree/main/hasher-matcher-actioner)
12
15
* hashing algorithm, matching function, and ability to hook into actions
16
+
* [Hasher-Matcher-Actioner (CLIP demo)](https://github.com/juanmrad/HMA-CLIP-demo)
17
+
* HMA extension for CLIP as reference for adding other format extensions
18
+
* [Lattice Extract by Adobe](https://github.com/adobe/lattice_extract)
19
+
* grid and lattice detection to guard against FP in hash matching
20
+
* [MediaModeration (Wiki Extension)](https://github.com/wikimedia/mediawiki-extensions-MediaModeration?tab=readme-ov-file)
21
+
* CSAM hash matching for Wikimedia
13
22
* [PDQ by Meta](https://github.com/facebook/ThreatExchange/tree/main/pdq)
14
23
* perceptual hash algorithm for images
15
-
* [TMK by Meta](https://github.com/facebook/ThreatExchange/tree/main/tmk)
16
-
* visual similarity match for videos
17
-
* [VPDQ by Meta](https://github.com/facebook/ThreatExchange/tree/main/vpdq)
18
-
* visual similarity match for videos using PDQ algorithm
19
-
* [Hasher-Matcher-Actioner (CLIP demo)](https://github.com/juanmrad/HMA-CLIP-demo)
20
-
* HMA extension for CLIP as reference for adding other format extensins
21
24
* [Perception by Thorn](https://github.com/thorn-oss/perception)
22
25
* provides a common wrapper around existing, popular perceptual hashes (such as those implemented by ImageHash)
23
-
* [Altitude by Jigsaw](https://github.com/jigsaw-code/altitude)
24
-
* web UI and hash matching for violent extremism and terrorism content
25
-
* [Lattice Extract by Adobe](https://github.com/adobe/lattice_extract)
26
-
* grid and lattice detection to guard against FP in hash matching
27
26
* [RocketChat CSAM](https://github.com/prostasia/rocketchatcsam)
28
27
* CSAM hash matching for RocketChat
29
-
* [MediaModeration (Wiki Extension)](https://github.com/wikimedia/mediawiki-extensions-MediaModeration?tab=readme-ov-file)
30
-
* CSAM hash matching for Wikimedia
28
+
* [TMK by Meta](https://github.com/facebook/ThreatExchange/tree/main/tmk)
29
+
* visual similarity match for videos
30
+
* [VPDQ by Meta](https://github.com/facebook/ThreatExchange/tree/main/vpdq)
31
+
* visual similarity match for videos using PDQ algorithm
32
+
31
33
32
34
## Classification
35
+
33
36
* [CoPE by Zentropi](https://huggingface.co/zentropi-ai/cope-a-9b)
34
37
* small language model trained for accurate, fast, steerable content classification based on developer-defined content policies
38
+
* [Detoxify by Unitary AI](https://github.com/unitaryai/detoxify)
39
+
* detects and mitigates generalized toxic language (including hate speech, harassment, bullying) in text
40
+
* [gpt-oss-safeguard by OpenAI](https://github.com/openai/gpt-oss-safeguard)
41
+
* open-weight reasoning model to classify text content based on provided safety policies
42
+
* [NSFW Keras Model](https://github.com/GantMan/nsfw_model)
43
+
* convoluted neural network (CNN) based explicit image ML model
44
+
* [NSFW Filtering](https://github.com/nsfw-filter/nsfw-filter)
45
+
* browser extension to block explicit images from online platforms; user facing
35
46
* [OSmod by Jigsaw](https://github.com/conversationai/conversationai-moderator)
36
47
* toolkit of machine learning (ML) tools, models, and APIs that platforms can use to moderate content
37
48
* [Perspective API by Jigsaw](https://github.com/conversationai/perspectiveapi)
38
49
* machine learning-powered tool that helps platforms detect and assess the toxicity of online conversations
39
-
* [Roblox Voice Safety Classifier](https://github.com/Roblox/voice-safety-classifier)
40
-
* machine learning model that detects and moderates harmful content in real-time voice chat on Roblox. Focuses on spoken language detection.
41
-
* [Detoxify by Unitary AI](https://github.com/unitaryai/detoxify)
42
-
* detects and mitigates generalized toxic language (including hate speech, harassment, bullying) in text
43
-
* [Toxic Prompt RoBERTa by Intel](https://huggingface.co/Intel/toxic-prompt-roberta)
44
-
* a BERT-based model for detecting toxic content in prompts to language models
45
-
* [NSFW Filtering](https://github.com/nsfw-filter/nsfw-filter)
46
-
* browser extension to block explicit images from online platforms. User facing.
47
-
* [NSFW Keras Model](https://github.com/GantMan/nsfw_model)
48
-
* convoluted neural network (CNN) based explicit image ML model
49
50
* [Private Detector by Bumble](https://github.com/bumble-tech/private-detector)
50
-
* a pretrained model for detecting lewd images
51
+
* pretrained model for detecting lewd images
52
+
* [Roblox Voice Safety Classifier](https://github.com/Roblox/voice-safety-classifier)
53
+
* machine learning model that detects and moderates harmful content in real-time voice chat on Roblox; focuses on spoken language detection
51
54
* [Sentinel by Roblox](https://github.com/Roblox/Sentinel/tree/main)
52
-
* a Python library designed specifically for realtime detection of extremely rare classes of text by using contrastive learning principles
53
-
* [gpt-oss-safeguard by OpenAI](https://github.com/openai/gpt-oss-safeguard)
54
-
* open-weight reasoning model to classify text content based on provided safety policies
55
+
* Python library designed specifically for realtime detection of extremely rare classes of text by using contrastive learning principles
56
+
* [Toxic Prompt RoBERTa by Intel](https://huggingface.co/Intel/toxic-prompt-roberta)
57
+
* BERT-based model for detecting toxic content in prompts to language models
58
+
55
59
56
60
## AI-powered Guardrails
61
+
62
+
* [Guardrails AI](https://github.com/guardrails-ai/guardrails)
63
+
* Python framework that helps build safe AI applications checking input/output for predefined risks
64
+
* [Kanana Safeguard By Kakao](https://huggingface.co/kakaocorp/kanana-safeguard-8b)
65
+
* harmful content detection model based on Kanana 8B
57
66
* [Llama Guard by Meta](https://github.com/meta-llama/PurpleLlama/tree/main/Llama-Guard3)
58
67
* AI-powered content moderation model to detect harm in text-based interactions
59
68
* [Llama Prompt Guard 2 by Meta](https://github.com/meta-llama/PurpleLlama/blob/main/Llama-Prompt-Guard-2/86M/MODEL_CARD.md)
60
-
* Detects prompt injection and jailbreaking attacks in LLM inputs.
69
+
* Detects prompt injection and jailbreaking attacks in LLM inputs
61
70
* [Purple Llama by Meta](https://github.com/meta-llama/PurpleLlama/tree/main/Llama-Guard3)
62
71
* set of tools to assess and improve LLM security. Includes Llama Guard, CyberSec Eval, and Code Shield
72
+
* [RoGuard](https://github.com/Roblox/RoGuard-1.0)
73
+
* LLM that helps safeguard unlimited text generation on Roblox
63
74
* [ShieldGemma by Google DeepMind](https://www.kaggle.com/code/fernandosr85/shieldgemma-web-content-safety-analyzer?scriptVersionId=198456916)
64
75
* AI safety toolkit by Google DeepMind designed to help detect and mitigate harmful or unsafe outputs in LLM applications
65
-
* [Guardrails AI](https://github.com/guardrails-ai/guardrails)
66
-
* a Python framework that helps build safe AI applications checking input/output for predefined risks
67
-
* [RoGuard](https://github.com/Roblox/RoGuard-1.0)
68
-
* a LLM that helps safeguard unlimited text generation on Roblox
69
-
* [Kanana Safeguard By Kakao](https://huggingface.co/kakaocorp/kanana-safeguard-8b)
70
-
* A harmful content detection model based on Kanana 8B
76
+
71
77
72
78
## Privacy Protection
79
+
73
80
* [Fawkes Facial De-Recognition Cloaking](https://github.com/Shawn-Shan/fawkes)
74
81
* Code and binaries to confuse AIs when trying to match identity to photos, such as [Clearview](https://www.theverge.com/23919134/kashmir-hill-your-face-belongs-to-us-clearview-ai-facial-recognition-privacy-decoder)
75
82
* Many other great tools at github.com/Shawn-Shan, MIT researcher
76
83
* [Presidio by Microsoft](https://github.com/microsoft/presidio)
77
84
* toolset for detecting Personal Identifiable Information (PII) and other sensitive data in images and text
85
+
78
86
79
87
## Core Infrastructure
80
-
* [Mjolnir by Matrix](https://github.com/matrix-org/mjolnir)
81
-
* moderation bot for the Matrix protocol that automatically enforces content policies
88
+
82
89
* [AbuseIO](https://github.com/AbuseIO/AbuseIO)
83
90
* abuse management platform designed to help organizations handle and track abuse complaints related to online content, infrastructure, or services
84
-
* [Open Truss by Github](https://github.com/open-truss/open-truss)
85
-
* framework designed to help users create internal tools without needing to write code
86
91
* [Access by Discord](https://github.com/discord/access)
87
-
* a centralized portal for managing access to internal systems within any organization
92
+
* centralized portal for managing access to internal systems within any organization
93
+
* [Mjolnir by Matrix](https://github.com/matrix-org/mjolnir)
94
+
* moderation bot for the Matrix protocol that automatically enforces content policies
95
+
* [Open Truss by GitHub](https://github.com/open-truss/open-truss)
96
+
* framework designed to help users create internal tools without needing to write code
88
97
98
+
89
99
## Redteaming Tools
90
100
101
+
* [Aymara](https://github.com/aymara-ai/aymara-sdk-python)
102
+
* Automated eval tools for AI safety, accuracy, and jailbreak vulnerability
103
+
* [Counterfit by Microsoft](https://github.com/Azure/counterfit/)
104
+
* Automation tool for assessing AI model security and robustness
105
+
* [Garak by NVIDIA](https://github.com/NVIDIA/garak)
106
+
* Framework for adversarial testing and model evaluation
107
+
* [LLM Canary](https://github.com/LLM-Canary/LLM-Canary)
108
+
* AI benchmarking tool that evaluates models for security vulnerabilities and adversarial robustness
109
+
* [Prompt Fuzzer](https://github.com/prompt-security/ps-fuzz)
110
+
* Tool for testing prompt injection vulnerabilities in AI systems
111
+
* [Promptfoo](https://github.com/promptfoo/promptfoo)
112
+
* Automated LLM evaluations, report generations, several ready-to-use attack strategies
91
113
* [PyRIT Documentation](https://azure.github.io/PyRIT/)
92
-
* Microsoft’s Python-based tool for AI red teaming and security testing.
93
-
* [AI Benchmarking Tool](https://github.com/LLM-Canary/LLM-Canary)
94
-
* Evaluates AI models for security vulnerabilities and adversarial robustness.
95
-
* [Prompt Fuzzer Red Teaming Tool](https://github.com/prompt-security/ps-fuzz)
96
-
* Tool for testing prompt injection vulnerabilities in AI systems.
97
-
* [Open Source Red Teaming Tool – Nvidia](https://github.com/NVIDIA/garak)
98
-
* Framework for adversarial testing and model evaluation.
99
-
* [Tool that Enables Models to Chat with One Another](https://github.com/socketteer?tab=repositories)
100
-
* Allows AI models to interact, helping test conversational weaknesses.
101
-
* [Microsoft AI Tool – Counterfit](https://github.com/Azure/counterfit/)
102
-
* Automation tool for assessing AI model security and robustness.
103
-
* [Automated AI Alignment Evals - Aymara](https://github.com/aymara-ai/aymara-sdk-python)
104
-
* Automated eval tools for AI safety, accuracy, and jailbreak vulnerability.
105
-
* [LLM Evals & red teaming Promptfoo](https://github.com/promptfoo/promptfoo)
106
-
* Automated evaluations, report generations, several ready-to-use attack strategies.
114
+
* Microsoft’s Python-based tool for AI red teaming and security testing
115
+
* [Socketteer](https://github.com/socketteer?tab=repositories)
116
+
* Allows AI models to interact, helping test conversational weaknesses
117
+
107
118
108
119
## Clustering
120
+
121
+
* [scikit-learn](https://github.com/scikit-learn/scikit-learn)
122
+
* python library including clustering through various algorithms, such as K-Means, DBSCAN, and hierarchical clustering
109
123
* [SpamAssassin by Apache](https://spamassassin.apache.org)
110
124
* anti-spam platform that uses a variety of techniques, including text analysis, Bayesian filtering, and DNS blocklists, to classify and block unsolicited email
111
-
* [scikit-learn](https://github.com/scikit-learn/scikit-learn)
112
-
* python library including clustering through various algorithms, such as K-Means, DBSCAN, and hierarchical clustering
113
125
114
126
115
127
## Rules Engines
128
+
129
+
* [Druid by Apache](https://github.com/apache/druid)
130
+
* high performance real-time analytics database
131
+
* [Marble](https://github.com/checkmarble/marble)
132
+
* real-time fraud detection and compliance engine tailored for fintech companies and financial institutions
116
133
* [Osprey by ROOST](https://github.com/roostorg/osprey)
117
-
* a high-performance rules engine for real-time event processing at scale, designed for Trust & Safety and anti-abuse work
134
+
* high-performance rules engine for real-time event processing at scale, designed for Trust & Safety and anti-abuse work
118
135
* [RulesEngine by Microsoft](https://microsoft.github.io/RulesEngine/)
119
-
* a library for abstracting business logic, rules, and policies from a system via JSON for .NET language families
120
-
* [Marble](https://github.com/checkmarble/marble)
121
-
* a real-time fraud detection and compliance engine tailored for fintech companies and financial institutions
136
+
* library for abstracting business logic, rules, and policies from a system via JSON for .NET language families
122
137
* [Wikimedia Smite Spam](https://github.com/wikimedia/mediawiki-extensions-SmiteSpam)
123
-
* an extension for MediaWiki that helps identify and manage spam content on a wiki
124
-
* [Druid by Apache](https://github.com/apache/druid)
125
-
* a high performance real-time analytics database
138
+
* extension for MediaWiki that helps identify and manage spam content on a wiki
126
139
127
140
128
141
## Review
129
-
* [RabbitMQ](https://github.com/rabbitmq)
130
-
* a message broker that enables applications to communicate with each other by sending messages through queues
142
+
131
143
* [BullMQ](https://github.com/taskforcesh/bullmq)
132
144
* message queue and batch processing for NodeJS and Python based on Redis
133
-
* [Owlculus](https://github.com/be0vlk/owlculus)
134
-
* an OSINT (Open-Source Intelligence) toolkit and case management platform
135
145
* [NCMEC Reporting by ello](https://github.com/ello/ncmec_reporting)
136
-
* a Ruby client library for reporting incidents to the National Center for Missing & Exploited Children (NCMEC) CyberTipline
146
+
* Ruby client library for reporting incidents to the National Center for Missing & Exploited Children (NCMEC) CyberTipline
147
+
* [Owlculus](https://github.com/be0vlk/owlculus)
148
+
* OSINT (Open-Source Intelligence) toolkit and case management platform
149
+
* [RabbitMQ](https://github.com/rabbitmq)
150
+
* message broker that enables applications to communicate with each other by sending messages through queues
137
151
138
152
139
153
## Investigation
154
+
155
+
* [CIB MangoTree](https://github.com/CIB-Mango-Tree/CIB-Mango-Tree-Website)
156
+
* collection of tools to aid researchers in coordinated inauthentic behavior (CIB) analysis
157
+
* [Crossover](https://crossover.social/)
158
+
* open-source project that builds dashboards for monitoring and analyzing the recommendation algorithms of social networks, with a focus on disinformation and election monitoring
159
+
* [DAU Dashboard by Tattle](https://github.com/tattle-made/dau-dashboard)
160
+
* Deepfake Analysis Unit(DAU) is a collaborative space for analyzing deepfakes
161
+
* [Feluda by Tattle](https://github.com/tattle-made/feluda)
162
+
* configurable engine for analysing multi-lingual and multi-modal content
163
+
* [Interference by Digital Forensics Research Lab](https://github.com/DFRLab/interference2024)
164
+
* interactive, open-source database that tracks allegations of foreign interference or foreign malign influence relevant to the 2024 U.S. presidential election
165
+
* [OpenMeasures](https://gitlab.com/openmeasures)
166
+
* open source platform for investigating internet trends
140
167
* [ThreatExchange by Meta](https://github.com/facebook/ThreatExchange )
141
-
* a platform that enables organizations to share information about threats, such as malware, phishing attacks, and online safety harms in a structured and privacy-compliant manner
168
+
* platform that enables organizations to share information about threats, such as malware, phishing attacks, and online safety harms in a structured and privacy-compliant manner
142
169
* [ThreatExchange Client via PHP](https://github.com/certly/threatexchange)
143
-
* a PHP client for ThreatExchange
170
+
* PHP client for ThreatExchange
144
171
* [ThreatExchange via Python](https://github.com/facebook/ThreatExchange/tree/main/python-threatexchange)
145
-
* a Python library for ThreatExchange
146
-
* [Feluda by Tattle](https://github.com/tattle-made/feluda)
147
-
* A configurable engine for analysing multi-lingual and multi-modal content
148
-
* [DAU Dashboard by Tattle](https://github.com/tattle-made/dau-dashboard)
149
-
* Deepfake Analysis Unit(DAU) is a collaborative space for analyzing deepfakes
150
-
* [CIB MangoTree](https://github.com/CIB-Mango-Tree/CIB-Mango-Tree-Website)
151
-
* A collection of tools to aid researchers in coordinated inauthentic behavior (CIB) analysis
152
-
* [Interference by Digital Forensics Research Lab](https://github.com/DFRLab/interference2024)
153
-
* an interactive, open-source database that tracks allegations of foreign interference or foreign malign influence relevant to the 2024 U.S. presidential election
154
-
* [Crossover](https://crossover.social/)
155
-
* An open-source project that builds dashboards for monitoring and analyzing the recommendation algorithms of social networks, with a focus on disinformation and election monitoring.
172
+
* Python library for ThreatExchange
156
173
* [TikTok Observatory](https://github.com/aiforensics/tkobservatory)
157
-
* An open-source project maintained by [AI Forensics](https://aiforensics.org/) that allows researchers to monitor the promotion and demotion of content by the TikTok reccomendation algorithm.
158
-
* [OpenMeasures](https://gitlab.com/openmeasures)
159
-
* an open source platform for investigating internet trends
174
+
* open-source project maintained by [AI Forensics](https://aiforensics.org/) that allows researchers to monitor the promotion and demotion of content by the TikTok reccomendation algorithm
160
175
161
176
162
177
## Datasets
178
+
163
179
* [Aegis Content Safety by NVIDIA](https://huggingface.co/datasets/nvidia/Aegis-AI-Content-Safety-Dataset-2.0)
164
-
* a dataset created by NVIDIA to aid in content moderation and toxicity detection
165
-
* [Toxicity by Jigsaw](https://huggingface.co/datasets/google/jigsaw_toxicity_pred)
166
-
* a large number of Wikipedia comments which have been labeled by human raters for toxic behavior
180
+
* dataset created by NVIDIA to aid in content moderation and toxicity detection
167
181
* [Toxic Chat by LMSYS](https://huggingface.co/datasets/lmsys/toxic-chat)
168
-
* a dataset of toxic conversations collected from interactions with Vicuna
182
+
* dataset of toxic conversations collected from interactions with Vicuna
183
+
* [Toxicity by Jigsaw](https://huggingface.co/datasets/google/jigsaw_toxicity_pred)
184
+
* large number of Wikipedia comments which have been labeled by human raters for toxic behavior
169
185
* [Uli Dataset by Tattle](https://github.com/tattle-made/uli_dataset)
170
-
* A dataset of gendered abuse, created for Uli ML redaction.
186
+
* dataset of gendered abuse, created for Uli ML redaction.
171
187
* [VTC by Unitary AI](https://github.com/unitaryai/VTC)
172
-
* an implementation of video-text retrieval with comments including a dataset, method of identifying relevant auxiliary information that adds context to videos, and quantification of the value comment-modality bring to video.
188
+
* implementation of video-text retrieval with comments including a dataset, method of identifying relevant auxiliary information that adds context to videos, and quantification of the value comment-modality bring to video
173
189
174
190
175
191
## Red Teaming Datasets
176
-
* [Red Team Resistance Leaderboard](https://huggingface.co/spaces/HaizeLabs/red-teaming-resistance-benchmark)
177
-
* rankings of AI models based on resistance to adversarial attacks.
178
-
* [JailbreakHub by WalledAI](https://huggingface.co/datasets/walledai/JailbreakHub)
179
-
* a collection of jailbreak prompts and corresponding model responses
180
-
* [SidFeel Jailbreak Dataset](https://github.com/sidfeels/PromptsDB)
181
-
* a collection of prompts used for jailbreaking AI models.
192
+
193
+
* [AI Alignment Dataset by Anthropic](https://atlas.nomic.ai/map/anthropic_rlhf)
194
+
* data used for reinforcement learning with human feedback (RLHF) to align AI models.
195
+
* [DEFCOM Red Teaming Dataset](https://github.com/humane-intelligence/ai_village_defcon_grt_data)
196
+
* dataset from DEF CON’s AI red teaming event.
182
197
* [HackAPrompt Jailbreak Dataset](https://huggingface.co/datasets/hackaprompt/hackaprompt-dataset/viewer/default/train?p=1&row=137)
183
-
* a dataset for testing AI vulnerability to prompt-based jailbreaking.
198
+
* dataset for testing AI vulnerability to prompt-based jailbreaking
184
199
* [HiroKachi Jailbreak Dataset](https://sizu.me/love)
185
-
* adataset focused on adversarial AI prompt attacks.
200
+
* dataset focused on adversarial AI prompt attacks
201
+
* [Jailbreak Prompt Generator AI Model](https://huggingface.co/tsq2000/Jailbreak-generator)
202
+
* AI model that generates jailbreak-style prompts
203
+
* [JailbreakHub by WalledAI](https://huggingface.co/datasets/walledai/JailbreakHub)
204
+
* collection of jailbreak prompts and corresponding model responses
205
+
* [Red Team Resistance Leaderboard](https://huggingface.co/spaces/HaizeLabs/red-teaming-resistance-benchmark)
206
+
* rankings of AI models based on resistance to adversarial attacks
186
207
* [Rentry Jailbreak Datasets](https://rentry.org/gpt0721)
187
-
* collection of datasets related to jailbreak attempts on AI models.
188
-
* [DEFCOM Red Teaming Dataset](https://github.com/humane-intelligence/ai_village_defcon_grt_data)
189
-
* dataset from DEF CON’s AI red teaming event.
190
-
* [Anthropic’s AI Alignment Dataset](https://atlas.nomic.ai/map/anthropic_rlhf)
191
-
* data used for reinforcement learning with human feedback (RLHF) to align AI models.
192
-
* [Jailbreak Prompt Generator AI Model](https://huggingface.co/tsq2000/Jailbreak-generator)
193
-
* AI model that generates jailbreak-style prompts.
208
+
* collection of datasets related to jailbreak attempts on AI models
209
+
* [SidFeel Jailbreak Dataset](https://github.com/sidfeels/PromptsDB)
210
+
* collection of prompts used for jailbreaking AI models
194
211
212
+
195
213
## Decentralized Platforms
214
+
215
+
* [Automod by Bluesky](https://github.com/bluesky-social/indigo/tree/main/automod)
216
+
* tool for automating content moderation processes for the Bluesky social network and other apps on the AT Protocol
196
217
* [FediCheck](https://connect.iftas.org/library/iftas-documentation/fedicheck/)
197
218
* domain moderation tool to assist ActivityPub service providers, such as Mastodon servers, now open-sourced.
198
219
* [Fediverse Spam Filtering](https://github.com/MarcT0K/Fediverse-Spam-Filtering/ )
199
-
* a spam filter for Fediverse social media platforms. For now, the current version is only a proof of concept.
220
+
* spam filter for Fediverse social media platforms. For now, the current version is only a proof of concept.
200
221
* [FIRES](https://github.com/fedimod/fires)
201
222
* reference server + protocol for the exchange of moderation adivsories and recommendations
202
223
* [Ozone by Bluesky](https://github.com/bluesky-social/ozone)
203
224
* labeling tool designed for Bluesky. Includes moderation features to action on abuse flags, policy enforcement tools, and investigation features
204
-
* [Automod by Bluesky](https://github.com/bluesky-social/indigo/tree/main/automod)
205
-
* a tool for automating content moderation processes for the Bluesky social network and other apps on the AT Protocol
225
+
206
226
207
227
## User Safety Tools
208
-
* [Uli by Tattle](https://github.com/tattle-made/Uli)
209
-
* Software and Resources for Mitigating Online Gender Based Violence in India
228
+
210
229
* [Frankly by Applied Social Media Lab](https://github.com/berkmancenter/frankly/)
211
-
* an online deliberations platform that allows anyone to host video-enabled conversations about any topic
230
+
* online deliberations platform that allows anyone to host video-enabled conversations about any topic
212
231
* [PolicyKit by UW Social Futures Lab](https://github.com/policykit/policykit)
213
-
* a toolkit for building governance in your online community
232
+
* toolkit for building governance in your online community
214
233
* [SquadBox by UW Social Futures Lab](https://github.com/amyxzhang/squadbox)
215
-
* a tool to help people who are being harassed online by having their friends (or “squad”) moderate their messages
216
-
217
-
234
+
* tool to help people who are being harassed online by having their friends (or “squad”) moderate their messages
235
+
* [Uli by Tattle](https://github.com/tattle-made/Uli)
236
+
* Software and Resources for Mitigating Online Gender Based Violence in India
218
237