{"data":{"node":{"slug":"grayswanai-circuit-breakers","name":"circuit-breakers","tagline":"Improving Alignment and Robustness with Circuit Breakers","github_url":"https://github.com/GraySwanAI/circuit-breakers","owner":"GraySwanAI","repo":"circuit-breakers","owner_avatar_url":"https://avatars.githubusercontent.com/u/174157256?v=4","primary_language":"Jupyter Notebook","stars":266,"forks":42,"topics":[],"archived":false,"github_pushed_at":"2024-09-24T18:44:40+00:00","maintenance_label":"Dormant","url":"https://www.graphcanon.com/tools/grayswanai-circuit-breakers","markdown_url":"https://www.graphcanon.com/tools/grayswanai-circuit-breakers.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/grayswanai-circuit-breakers","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=grayswanai-circuit-breakers"},"categories":[{"slug":"evaluation-observability","name":"Evaluation & Observability","url":"https://www.graphcanon.com/categories/evaluation-observability","markdown_url":"https://www.graphcanon.com/categories/evaluation-observability.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/evaluation-observability"}],"tags":[{"slug":"adversarial-attacks","name":"adversarial-attacks"},{"slug":"alignment","name":"alignment"},{"slug":"circuit-breaker","name":"circuit breaker"},{"slug":"robustness","name":"robustness"}],"edges":[],"neighbours":[{"slug":"llm-attacks-llm-attacks","name":"llm-attacks","tagline":"Universal and Transferable Attacks on Aligned Language Models","github_url":"https://github.com/llm-attacks/llm-attacks","owner":"llm-attacks","repo":"llm-attacks","owner_avatar_url":"https://avatars.githubusercontent.com/u/140664770?v=4","primary_language":"Python","stars":4756,"forks":633,"topics":[],"archived":false,"github_pushed_at":"2024-08-02T06:02:18+00:00","maintenance_label":"Dormant","url":"https://www.graphcanon.com/tools/llm-attacks-llm-attacks","markdown_url":"https://www.graphcanon.com/tools/llm-attacks-llm-attacks.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/llm-attacks-llm-attacks","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=llm-attacks-llm-attacks","shared_categories":["evaluation-observability"]},{"slug":"fasterdecoding-medusa","name":"Medusa","tagline":"Framework for accelerating LLM generation using multiple decoding heads","github_url":"https://github.com/FasterDecoding/Medusa","owner":"FasterDecoding","repo":"Medusa","owner_avatar_url":"https://avatars.githubusercontent.com/u/144572371?v=4","primary_language":"Jupyter Notebook","stars":2767,"forks":205,"topics":["llm","llm-inference"],"archived":false,"github_pushed_at":"2024-06-25T12:23:04+00:00","maintenance_label":"Dormant","url":"https://www.graphcanon.com/tools/fasterdecoding-medusa","markdown_url":"https://www.graphcanon.com/tools/fasterdecoding-medusa.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/fasterdecoding-medusa","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=fasterdecoding-medusa","shared_categories":[]},{"slug":"georgian-io-llm-finetuning-toolkit","name":"LLM-Finetuning-Toolkit","tagline":"Toolkit for fine-tuning and testing open-source large language models","github_url":"https://github.com/georgian-io/LLM-Finetuning-Toolkit","owner":"georgian-io","repo":"LLM-Finetuning-Toolkit","owner_avatar_url":"https://avatars.githubusercontent.com/u/10764713?v=4","primary_language":"Python","stars":870,"forks":107,"topics":["ablation-study","classification","falcon","fine-tuning","finetuning","flan-t5","large-language-models","llama2","llm-test","lora","mistral-7b","nlp","nlp-machine-learning","qlora","redpajama","summarization","unit-testing","zephyr"],"archived":false,"github_pushed_at":"2026-05-04T16:33:40+00:00","maintenance_label":"Slowing","url":"https://www.graphcanon.com/tools/georgian-io-llm-finetuning-toolkit","markdown_url":"https://www.graphcanon.com/tools/georgian-io-llm-finetuning-toolkit.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/georgian-io-llm-finetuning-toolkit","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=georgian-io-llm-finetuning-toolkit","shared_categories":[]},{"slug":"robustnlp-cipherchat","name":"CipherChat","tagline":"A framework to assess safety alignment generalization in LLMs for non-natural languages","github_url":"https://github.com/RobustNLP/CipherChat","owner":"RobustNLP","repo":"CipherChat","owner_avatar_url":"https://avatars.githubusercontent.com/u/71020516?v=4","primary_language":"Python","stars":628,"forks":68,"topics":["alignment","chatgpt","gpt-4-0613","jailbreak","large-language-models","llm","security"],"archived":false,"github_pushed_at":"2025-10-09T03:20:12+00:00","maintenance_label":"Slowing","url":"https://www.graphcanon.com/tools/robustnlp-cipherchat","markdown_url":"https://www.graphcanon.com/tools/robustnlp-cipherchat.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/robustnlp-cipherchat","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=robustnlp-cipherchat","shared_categories":["evaluation-observability"]},{"slug":"oxbshw-llm-agents-ecosystem-handbook","name":"LLM-Agents-Ecosystem-Handbook","tagline":"One-stop handbook for building, deploying, and understanding LLM agents","github_url":"https://github.com/oxbshw/LLM-Agents-Ecosystem-Handbook","owner":"oxbshw","repo":"LLM-Agents-Ecosystem-Handbook","owner_avatar_url":"https://avatars.githubusercontent.com/u/212214682?v=4","primary_language":"Python","stars":539,"forks":85,"topics":["ai","ai-agent","ai-agents","fine-tuning","finetuning-llms","freamework","llm","llmops","local-development","mcp-server","memory","rag","rag-chatbot","voice-agent"],"archived":false,"github_pushed_at":"2026-06-30T12:22:57+00:00","maintenance_label":"Steady","url":"https://www.graphcanon.com/tools/oxbshw-llm-agents-ecosystem-handbook","markdown_url":"https://www.graphcanon.com/tools/oxbshw-llm-agents-ecosystem-handbook.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/oxbshw-llm-agents-ecosystem-handbook","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=oxbshw-llm-agents-ecosystem-handbook","shared_categories":["evaluation-observability"]},{"slug":"liu00222-open-prompt-injection","name":"Open-Prompt-Injection","tagline":"Benchmark and toolkit for prompt injection attacks and defenses in LLMs","github_url":"https://github.com/liu00222/Open-Prompt-Injection","owner":"liu00222","repo":"Open-Prompt-Injection","owner_avatar_url":"https://avatars.githubusercontent.com/u/42081599?v=4","primary_language":"Python","stars":470,"forks":74,"topics":["llm","llm-security","llms","prompt-injection","prompt-injection-tool","security-and-privacy"],"archived":false,"github_pushed_at":"2025-10-29T17:11:34+00:00","maintenance_label":"Slowing","url":"https://www.graphcanon.com/tools/liu00222-open-prompt-injection","markdown_url":"https://www.graphcanon.com/tools/liu00222-open-prompt-injection.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/liu00222-open-prompt-injection","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=liu00222-open-prompt-injection","shared_categories":["evaluation-observability"]},{"slug":"llm-tuning-safety-llms-finetuning-safety","name":"LLMs-Finetuning-Safety","tagline":"Demonstrates safety risks in fine-tuning GPT-3.5 Turbo with adversarial examples","github_url":"https://github.com/LLM-Tuning-Safety/LLMs-Finetuning-Safety","owner":"LLM-Tuning-Safety","repo":"LLMs-Finetuning-Safety","owner_avatar_url":"https://avatars.githubusercontent.com/u/146881603?v=4","primary_language":"Python","stars":358,"forks":38,"topics":["alignment","llm","llm-finetuning"],"archived":false,"github_pushed_at":"2024-02-23T21:19:44+00:00","maintenance_label":"Dormant","url":"https://www.graphcanon.com/tools/llm-tuning-safety-llms-finetuning-safety","markdown_url":"https://www.graphcanon.com/tools/llm-tuning-safety-llms-finetuning-safety.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/llm-tuning-safety-llms-finetuning-safety","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=llm-tuning-safety-llms-finetuning-safety","shared_categories":["evaluation-observability"]},{"slug":"libr-ai-do-not-answer","name":"do-not-answer","tagline":"A Dataset for Evaluating Safeguards in LLMs","github_url":"https://github.com/Libr-AI/do-not-answer","owner":"Libr-AI","repo":"do-not-answer","owner_avatar_url":"https://avatars.githubusercontent.com/u/133515165?v=4","primary_language":"Jupyter Notebook","stars":339,"forks":29,"topics":[],"archived":false,"github_pushed_at":"2024-06-07T14:55:51+00:00","maintenance_label":"Dormant","url":"https://www.graphcanon.com/tools/libr-ai-do-not-answer","markdown_url":"https://www.graphcanon.com/tools/libr-ai-do-not-answer.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/libr-ai-do-not-answer","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=libr-ai-do-not-answer","shared_categories":["evaluation-observability"]},{"slug":"giskard-ai-awesome-ai-safety","name":"awesome-ai-safety","tagline":"A curated list of papers and technical articles on AI Quality & Safety","github_url":"https://github.com/Giskard-AI/awesome-ai-safety","owner":"Giskard-AI","repo":"awesome-ai-safety","owner_avatar_url":"https://avatars.githubusercontent.com/u/71782571?v=4","primary_language":null,"stars":220,"forks":39,"topics":["ai","ai-alignment","ai-quality","ai-safety","artificial-intelligence","awesome","awesome-list","computer-vision","ethical-ai","llm","llmops","machine-learning","ml","ml-safety","ml-testing","mlops","model-testing","model-validation","natural-language-processing","robustness"],"archived":false,"github_pushed_at":"2025-04-14T12:42:48+00:00","maintenance_label":"Dormant","url":"https://www.graphcanon.com/tools/giskard-ai-awesome-ai-safety","markdown_url":"https://www.graphcanon.com/tools/giskard-ai-awesome-ai-safety.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/giskard-ai-awesome-ai-safety","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=giskard-ai-awesome-ai-safety","shared_categories":["evaluation-observability"]},{"slug":"dipampaul17-agentguard","name":"AgentGuard","tagline":"Real-time guardrail that monitors token spend and manages LLM/agent loops in real time","github_url":"https://github.com/dipampaul17/AgentGuard","owner":"dipampaul17","repo":"AgentGuard","owner_avatar_url":"https://avatars.githubusercontent.com/u/40596409?v=4","primary_language":"JavaScript","stars":171,"forks":10,"topics":["ai-agents","anthropic","anthropic-claude","cost-monitoring","debugging","guardrails","llm","observability","openai","openai-api","prompt-engineering","token-usage"],"archived":false,"github_pushed_at":"2025-07-31T15:20:56+00:00","maintenance_label":"Dormant","url":"https://www.graphcanon.com/tools/dipampaul17-agentguard","markdown_url":"https://www.graphcanon.com/tools/dipampaul17-agentguard.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/dipampaul17-agentguard","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=dipampaul17-agentguard","shared_categories":["evaluation-observability"]},{"slug":"zenguard-ai-fast-llm-security-guardrails","name":"fast-llm-security-guardrails","tagline":"The fastest Trust Layer for AI Agents","github_url":"https://github.com/ZenGuard-AI/fast-llm-security-guardrails","owner":"ZenGuard-AI","repo":"fast-llm-security-guardrails","owner_avatar_url":"https://avatars.githubusercontent.com/u/163059052?v=4","primary_language":"Python","stars":154,"forks":21,"topics":["agentic-ai","ai-agent","ai-agents","ai-runtime","cx-agent","llm-guard","llm-guardrails","llm-privacy","llm-security","prompt-security","security"],"archived":false,"github_pushed_at":"2026-02-03T18:31:21+00:00","maintenance_label":"Slowing","url":"https://www.graphcanon.com/tools/zenguard-ai-fast-llm-security-guardrails","markdown_url":"https://www.graphcanon.com/tools/zenguard-ai-fast-llm-security-guardrails.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/zenguard-ai-fast-llm-security-guardrails","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=zenguard-ai-fast-llm-security-guardrails","shared_categories":["evaluation-observability"]},{"slug":"atrayee-dev-secure-ai-agent-boundary","name":"secure-ai-agent-boundary","tagline":"Secure AI Engineering Framework 2026: Data-Boundary Security for Frontier Models","github_url":"https://github.com/Atrayee-dev/secure-ai-agent-boundary","owner":"Atrayee-dev","repo":"secure-ai-agent-boundary","owner_avatar_url":"https://avatars.githubusercontent.com/u/191036427?v=4","primary_language":"HTML","stars":151,"forks":0,"topics":["ai-security","claude-opus","coding-agents","data-boundary","government-tech","gpt-5-5","local-llm","mirogate","secure-ai","secure-coding"],"archived":false,"github_pushed_at":"2026-08-13T11:48:08+00:00","maintenance_label":"Active","url":"https://www.graphcanon.com/tools/atrayee-dev-secure-ai-agent-boundary","markdown_url":"https://www.graphcanon.com/tools/atrayee-dev-secure-ai-agent-boundary.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/atrayee-dev-secure-ai-agent-boundary","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=atrayee-dev-secure-ai-agent-boundary","shared_categories":["evaluation-observability"]}]}}