{"data":{"node":{"slug":"ethz-spylab-agentdojo","name":"agentdojo","tagline":"A Dynamic Environment to Evaluate Prompt Injection Attacks and Defenses for LLM Agents","github_url":"https://github.com/ethz-spylab/agentdojo","owner":"ethz-spylab","repo":"agentdojo","owner_avatar_url":"https://avatars.githubusercontent.com/u/106388551?v=4","primary_language":"Python","stars":893,"forks":235,"topics":["benchmark","large-language-models","prompt-injection","security"],"archived":false,"github_pushed_at":"2026-06-02T10:01:31+00:00","maintenance_label":"Slowing","stars_delta_30d":91,"url":"https://www.graphcanon.com/tools/ethz-spylab-agentdojo","markdown_url":"https://www.graphcanon.com/tools/ethz-spylab-agentdojo.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/ethz-spylab-agentdojo","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=ethz-spylab-agentdojo"},"categories":[{"slug":"ai-agents","name":"AI Agents","url":"https://www.graphcanon.com/categories/ai-agents","markdown_url":"https://www.graphcanon.com/categories/ai-agents.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/ai-agents"},{"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":"benchmark","name":"benchmark"},{"slug":"large-language-models","name":"large-language-models"},{"slug":"prompt-injection","name":"prompt-injection"},{"slug":"security","name":"security"}],"edges":[],"neighbours":[{"slug":"microsoft-ai-agents-for-beginners","name":"ai-agents-for-beginners","tagline":"12 Lessons to Get Started Building AI Agents","github_url":"https://github.com/microsoft/ai-agents-for-beginners","owner":"microsoft","repo":"ai-agents-for-beginners","owner_avatar_url":"https://avatars.githubusercontent.com/u/6154722?v=4","primary_language":"Jupyter Notebook","stars":75177,"forks":24772,"topics":["agentic-ai","agentic-framework","agentic-rag","ai-agents","ai-agents-framework","autogen","foundry","foundry-local","generative-ai","microsoft-foundry","semantic-kernel"],"archived":false,"github_pushed_at":"2026-09-19T06:16:49+00:00","maintenance_label":"Active","url":"https://www.graphcanon.com/tools/microsoft-ai-agents-for-beginners","markdown_url":"https://www.graphcanon.com/tools/microsoft-ai-agents-for-beginners.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/microsoft-ai-agents-for-beginners","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=microsoft-ai-agents-for-beginners","shared_categories":["ai-agents"]},{"slug":"nirdiamant-agents-towards-production","name":"agents-towards-production","tagline":"End-to-end, code-first tutorials for building production-grade GenAI agents","github_url":"https://github.com/NirDiamant/agents-towards-production","owner":"NirDiamant","repo":"agents-towards-production","owner_avatar_url":"https://avatars.githubusercontent.com/u/28316913?v=4","primary_language":"Jupyter Notebook","stars":21298,"forks":2824,"topics":["agent","agent-framework","agentic-ai","agents","ai-agents","deployment","genai","generative-ai","langgraph","llm","llms","mcp","mlops","multi-agent-systems","observability","production","python","rag","tutorials"],"archived":false,"github_pushed_at":"2026-08-15T00:52:10+00:00","maintenance_label":"Steady","url":"https://www.graphcanon.com/tools/nirdiamant-agents-towards-production","markdown_url":"https://www.graphcanon.com/tools/nirdiamant-agents-towards-production.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/nirdiamant-agents-towards-production","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=nirdiamant-agents-towards-production","shared_categories":["ai-agents"]},{"slug":"raga-ai-hub-ragaai-catalyst","name":"RagaAI-Catalyst","tagline":"Python SDK for AI agent observability and evaluation","github_url":"https://github.com/raga-ai-hub/RagaAI-Catalyst","owner":"raga-ai-hub","repo":"RagaAI-Catalyst","owner_avatar_url":"https://avatars.githubusercontent.com/u/161833182?v=4","primary_language":"Python","stars":16162,"forks":3567,"topics":["agentic-ai","agentic-ai-development","agentneo","agents","ai-agent-monitoring","ai-application-debugging","ai-evaluation-tools","ai-performance-optimization","ai-tool-interaction-monitoring","llm-testing","llm-tracing","llmops"],"archived":false,"github_pushed_at":"2026-02-11T14:43:33+00:00","maintenance_label":"Slowing","url":"https://www.graphcanon.com/tools/raga-ai-hub-ragaai-catalyst","markdown_url":"https://www.graphcanon.com/tools/raga-ai-hub-ragaai-catalyst.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/raga-ai-hub-ragaai-catalyst","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=raga-ai-hub-ragaai-catalyst","shared_categories":["evaluation-observability","ai-agents"]},{"slug":"woooodyy-llm-agent-paper-list","name":"LLM-Agent-Paper-List","tagline":"Must-read papers for LLM-based agents.","github_url":"https://github.com/WooooDyy/LLM-Agent-Paper-List","owner":"WooooDyy","repo":"LLM-Agent-Paper-List","owner_avatar_url":"https://avatars.githubusercontent.com/u/48242229?v=4","primary_language":null,"stars":8222,"forks":499,"topics":["agent","large-language-models","llm","nlp","survey"],"archived":false,"github_pushed_at":"2025-09-12T03:08:58+00:00","maintenance_label":"Dormant","url":"https://www.graphcanon.com/tools/woooodyy-llm-agent-paper-list","markdown_url":"https://www.graphcanon.com/tools/woooodyy-llm-agent-paper-list.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/woooodyy-llm-agent-paper-list","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=woooodyy-llm-agent-paper-list","shared_categories":["evaluation-observability","ai-agents"]},{"slug":"superagent-ai-superagent","name":"superagent","tagline":"Superagent SDK","github_url":"https://github.com/superagent-ai/superagent","owner":"superagent-ai","repo":"superagent","owner_avatar_url":"https://avatars.githubusercontent.com/u/152537519?v=4","primary_language":"TypeScript","stars":6752,"forks":964,"topics":["ai","anthropic","guardrails","llm","openai","prompt-injection","security"],"archived":false,"github_pushed_at":"2026-08-25T09:45:01+00:00","maintenance_label":"Steady","url":"https://www.graphcanon.com/tools/superagent-ai-superagent","markdown_url":"https://www.graphcanon.com/tools/superagent-ai-superagent.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/superagent-ai-superagent","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=superagent-ai-superagent","shared_categories":["evaluation-observability"]},{"slug":"tencent-ai-infra-guard","name":"AI-Infra-Guard","tagline":"A full-stack AI Red Teaming platform securing AI ecosystems","github_url":"https://github.com/Tencent/AI-Infra-Guard","owner":"Tencent","repo":"AI-Infra-Guard","owner_avatar_url":"https://avatars.githubusercontent.com/u/18461506?v=4","primary_language":"Python","stars":6471,"forks":599,"topics":["agent","agent-security","agentic-ai","ai-infra","ai-red-teaming","ai-safety","ai-security","llm","llm-evaluation","llm-jailbreak","llm-security","mcp-scan","openclaw-security","prompt-injection","prompt-security","scanner","security","security-tools","skill-scanner","vulnerability"],"archived":false,"github_pushed_at":"2026-09-20T02:29:17+00:00","maintenance_label":"Active","url":"https://www.graphcanon.com/tools/tencent-ai-infra-guard","markdown_url":"https://www.graphcanon.com/tools/tencent-ai-infra-guard.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/tencent-ai-infra-guard","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=tencent-ai-infra-guard","shared_categories":["evaluation-observability"]},{"slug":"meta-llama-purplellama","name":"PurpleLlama","tagline":"Set of tools to assess and improve LLM security","github_url":"https://github.com/meta-llama/PurpleLlama","owner":"meta-llama","repo":"PurpleLlama","owner_avatar_url":"https://avatars.githubusercontent.com/u/153379578?v=4","primary_language":"Python","stars":4420,"forks":777,"topics":[],"archived":false,"github_pushed_at":"2026-09-29T23:08:52+00:00","maintenance_label":"Active","url":"https://www.graphcanon.com/tools/meta-llama-purplellama","markdown_url":"https://www.graphcanon.com/tools/meta-llama-purplellama.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/meta-llama-purplellama","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=meta-llama-purplellama","shared_categories":["evaluation-observability"]},{"slug":"future-agi-future-agi","name":"future-agi","tagline":"Open-source, end-to-end platform for evaluating, observing, and improving LLM and AI agent applications","github_url":"https://github.com/future-agi/future-agi","owner":"future-agi","repo":"future-agi","owner_avatar_url":"https://avatars.githubusercontent.com/u/147392366?v=4","primary_language":"Python","stars":2032,"forks":627,"topics":["ai-agents","ai-evals","ai-gateway","ai-optimization","ai-simulations","evaluation-framework","guardrails","hallucination-detection","llm","llm-evaluation","llm-observability","llmops","model-evaluation","observability","opentelemetry","rag","rag-evaluation","simulation","telemetry","tracing"],"archived":false,"github_pushed_at":"2026-09-18T08:15:25+00:00","maintenance_label":"Active","url":"https://www.graphcanon.com/tools/future-agi-future-agi","markdown_url":"https://www.graphcanon.com/tools/future-agi-future-agi.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/future-agi-future-agi","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=future-agi-future-agi","shared_categories":["evaluation-observability","ai-agents"]},{"slug":"corca-ai-awesome-llm-security","name":"awesome-llm-security","tagline":"A curation of tools, documents and projects about LLM Security","github_url":"https://github.com/corca-ai/awesome-llm-security","owner":"corca-ai","repo":"awesome-llm-security","owner_avatar_url":"https://avatars.githubusercontent.com/u/72978860?v=4","primary_language":null,"stars":1710,"forks":398,"topics":["awesome","awesome-list","llm","security"],"archived":false,"github_pushed_at":"2025-08-20T01:27:47+00:00","maintenance_label":"Dormant","url":"https://www.graphcanon.com/tools/corca-ai-awesome-llm-security","markdown_url":"https://www.graphcanon.com/tools/corca-ai-awesome-llm-security.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/corca-ai-awesome-llm-security","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=corca-ai-awesome-llm-security","shared_categories":["evaluation-observability"]},{"slug":"tiger-ai-lab-clawbench","name":"ClawBench","tagline":"Open-source benchmark for browser AI agents on daily tasks","github_url":"https://github.com/TIGER-AI-Lab/ClawBench","owner":"TIGER-AI-Lab","repo":"ClawBench","owner_avatar_url":"https://avatars.githubusercontent.com/u/144196744?v=4","primary_language":"Python","stars":796,"forks":58,"topics":["agent-evaluation","agentic-ai","ai-agent-benchmark","ai-agents","benchmark","browser-agent","browser-automation","browser-use","chrome-agent","chrome-extension","computer-use","dataset","evaluation","everyday-tasks","llm","llm-evaluation","online-tasks","real-world-benchmark","web-agent","web-agents"],"archived":false,"github_pushed_at":"2026-09-20T05:45:35+00:00","maintenance_label":"Active","url":"https://www.graphcanon.com/tools/tiger-ai-lab-clawbench","markdown_url":"https://www.graphcanon.com/tools/tiger-ai-lab-clawbench.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/tiger-ai-lab-clawbench","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=tiger-ai-lab-clawbench","shared_categories":["evaluation-observability","ai-agents"]},{"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":550,"forks":91,"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":"Slowing","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","ai-agents"]},{"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":503,"forks":81,"topics":["llm","llm-security","llms","prompt-injection","prompt-injection-tool","security-and-privacy"],"archived":false,"github_pushed_at":"2026-09-27T14:35:14+00:00","maintenance_label":"Active","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"]}]}}