{"data":{"node":{"slug":"last9-gpu-telemetry","name":"gpu-telemetry","tagline":"GPU Observability with Workload Attribution","github_url":"https://github.com/last9/gpu-telemetry","owner":"last9","repo":"gpu-telemetry","owner_avatar_url":"https://avatars.githubusercontent.com/u/53378302?v=4","primary_language":"Python","stars":66,"forks":8,"topics":["ai","amd","dcgm","gpu","gpu-monitoring","gpu-observability","helm","intel-gaudi-base-operator","kubernetes","llm-observability","mlops","nvidia","nvml-monitoring","opentelemetry","slurm","workload-attribution"],"archived":false,"github_pushed_at":"2026-08-02T09:12:57+00:00","maintenance_label":"Steady","stars_delta_30d":9,"url":"https://www.graphcanon.com/tools/last9-gpu-telemetry","markdown_url":"https://www.graphcanon.com/tools/last9-gpu-telemetry.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/last9-gpu-telemetry","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=last9-gpu-telemetry"},"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":"amd","name":"amd"},{"slug":"gpu-monitoring","name":"gpu-monitoring"},{"slug":"intel-gaudi-base-operator","name":"intel-gaudi-base-operator"},{"slug":"kubernetes","name":"kubernetes"},{"slug":"nvidia","name":"nvidia"},{"slug":"opentelemetry","name":"opentelemetry"},{"slug":"slurm","name":"slurm"}],"edges":[],"neighbours":[{"slug":"netdata-netdata","name":"netdata","tagline":"The fastest path to AI-powered full stack observability for lean teams","github_url":"https://github.com/netdata/netdata","owner":"netdata","repo":"netdata","owner_avatar_url":"https://avatars.githubusercontent.com/u/43390781?v=4","primary_language":"Go","stars":80598,"forks":6631,"topics":["ai","alerting","cncf","data-visualization","database","devops","docker","grafana","influxdb","kubernetes","linux","machine-learning","mcp","mongodb","monitoring","mysql","netdata","observability","postgresql","prometheus"],"archived":false,"github_pushed_at":"2026-09-20T00:25:10+00:00","maintenance_label":"Very active","url":"https://www.graphcanon.com/tools/netdata-netdata","markdown_url":"https://www.graphcanon.com/tools/netdata-netdata.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/netdata-netdata","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=netdata-netdata","shared_categories":["evaluation-observability"]},{"slug":"comet-ml-opik","name":"opik","tagline":"Debug, evaluate, and monitor LLM applications, RAG systems, and agentic workflows","github_url":"https://github.com/comet-ml/opik","owner":"comet-ml","repo":"opik","owner_avatar_url":"https://avatars.githubusercontent.com/u/31487821?v=4","primary_language":"Python","stars":22110,"forks":1801,"topics":["evaluation","hacktoberfest","hacktoberfest2025","langchain","llama-index","llm","llm-evaluation","llm-observability","llmops","open-source","openai","playground","prompt-engineering"],"archived":false,"github_pushed_at":"2026-09-18T08:25:51+00:00","maintenance_label":"Very active","url":"https://www.graphcanon.com/tools/comet-ml-opik","markdown_url":"https://www.graphcanon.com/tools/comet-ml-opik.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/comet-ml-opik","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=comet-ml-opik","shared_categories":["evaluation-observability"]},{"slug":"plasma-umass-scalene","name":"scalene","tagline":"High-performance CPU, GPU, and memory profiler for Python with AI-powered optimization","github_url":"https://github.com/plasma-umass/scalene","owner":"plasma-umass","repo":"scalene","owner_avatar_url":"https://avatars.githubusercontent.com/u/1880823?v=4","primary_language":"Python","stars":13496,"forks":437,"topics":["cpu","cpu-profiling","gpu","gpu-programming","memory-allocation","memory-consumption","performance-analysis","performance-cpu","profiler","profiles-memory","profiling","python","python-profilers","scalene"],"archived":false,"github_pushed_at":"2026-08-27T22:44:28+00:00","maintenance_label":"Active","url":"https://www.graphcanon.com/tools/plasma-umass-scalene","markdown_url":"https://www.graphcanon.com/tools/plasma-umass-scalene.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/plasma-umass-scalene","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=plasma-umass-scalene","shared_categories":["evaluation-observability"]},{"slug":"kubeshark-kubeshark","name":"kubeshark","tagline":"eBPF-powered network observability for Kubernetes","github_url":"https://github.com/kubeshark/kubeshark","owner":"kubeshark","repo":"kubeshark","owner_avatar_url":"https://avatars.githubusercontent.com/u/99263827?v=4","primary_language":"Go","stars":12082,"forks":549,"topics":["cloud-native","devops","docker","ebpf","golang","grpc","incident-response","kubernetes","mcp","network-analysis","network-engineering","network-observability","network-security","observability","pcap","rest","root-cause-analysis","sniffer","sre","wireshark"],"archived":false,"github_pushed_at":"2026-09-09T17:05:10+00:00","maintenance_label":"Active","url":"https://www.graphcanon.com/tools/kubeshark-kubeshark","markdown_url":"https://www.graphcanon.com/tools/kubeshark-kubeshark.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/kubeshark-kubeshark","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=kubeshark-kubeshark","shared_categories":["evaluation-observability"]},{"slug":"wandb-wandb","name":"wandb","tagline":"Weights & Biases platform for model training and management","github_url":"https://github.com/wandb/wandb","owner":"wandb","repo":"wandb","owner_avatar_url":"https://avatars.githubusercontent.com/u/26401354?v=4","primary_language":"Python","stars":11249,"forks":893,"topics":["ai","collaboration","data-science","data-versioning","deep-learning","experiment-track","hyperparameter-optimization","hyperparameter-search","hyperparameter-tuning","jax","keras","machine-learning","ml-platform","mlops","model-versioning","pytorch","reinforcement-learning","reproducibility","tensorflow"],"archived":false,"github_pushed_at":"2026-09-02T23:43:29+00:00","maintenance_label":"Active","url":"https://www.graphcanon.com/tools/wandb-wandb","markdown_url":"https://www.graphcanon.com/tools/wandb-wandb.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/wandb-wandb","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=wandb-wandb","shared_categories":["evaluation-observability"]},{"slug":"skypilot-org-skypilot","name":"skypilot","tagline":"Run, manage, and scale AI workloads on any AI infrastructure.","github_url":"https://github.com/skypilot-org/skypilot","owner":"skypilot-org","repo":"skypilot","owner_avatar_url":"https://avatars.githubusercontent.com/u/109387420?v=4","primary_language":"Python","stars":10568,"forks":1220,"topics":["cloud-computing","cloud-management","cost-optimization","deep-learning","distributed-training","gpu","hyperparameter-tuning","job-queue","job-scheduler","llm-serving","llm-training","machine-learning","ml-infrastructure","ml-platform","mlops","multicloud","slurm","spot-instances","tpu"],"archived":false,"github_pushed_at":"2026-09-05T16:25:57+00:00","maintenance_label":"Active","url":"https://www.graphcanon.com/tools/skypilot-org-skypilot","markdown_url":"https://www.graphcanon.com/tools/skypilot-org-skypilot.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/skypilot-org-skypilot","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=skypilot-org-skypilot","shared_categories":[]},{"slug":"agentops-ai-agentops","name":"agentops","tagline":"Python SDK for AI agent monitoring and LLM cost tracking","github_url":"https://github.com/AgentOps-AI/agentops","owner":"AgentOps-AI","repo":"agentops","owner_avatar_url":"https://avatars.githubusercontent.com/u/140554352?v=4","primary_language":"Python","stars":5830,"forks":625,"topics":["agent","agentops","agents-sdk","ai","anthropic","autogen","cost-estimation","crewai","evals","evaluation-metrics","groq","langchain","llm","mistral","ollama","openai","openai-agents"],"archived":false,"github_pushed_at":"2026-06-25T08:25:03+00:00","maintenance_label":"Steady","url":"https://www.graphcanon.com/tools/agentops-ai-agentops","markdown_url":"https://www.graphcanon.com/tools/agentops-ai-agentops.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/agentops-ai-agentops","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=agentops-ai-agentops","shared_categories":["evaluation-observability"]},{"slug":"pydantic-logfire","name":"logfire","tagline":"AI observability platform for production LLM and agent systems","github_url":"https://github.com/pydantic/logfire","owner":"pydantic","repo":"logfire","owner_avatar_url":"https://avatars.githubusercontent.com/u/110818415?v=4","primary_language":"Python","stars":4468,"forks":284,"topics":["agent-observability","ai","ai-observability","ai-tools","evals","fastapi","llm-observability","logging","metrics","observability","openai","opentelemetry","pydantic","pydantic-ai","python","trace"],"archived":false,"github_pushed_at":"2026-09-10T04:40:49+00:00","maintenance_label":"Active","url":"https://www.graphcanon.com/tools/pydantic-logfire","markdown_url":"https://www.graphcanon.com/tools/pydantic-logfire.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/pydantic-logfire","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=pydantic-logfire","shared_categories":["evaluation-observability"]},{"slug":"b4rtaz-distributed-llama","name":"distributed-llama","tagline":"Distributed LLM inference using home devices cluster","github_url":"https://github.com/b4rtaz/distributed-llama","owner":"b4rtaz","repo":"distributed-llama","owner_avatar_url":"https://avatars.githubusercontent.com/u/12797776?v=4","primary_language":"C++","stars":3060,"forks":250,"topics":["distributed-computing","distributed-llm","llama2","llama3","llm","llm-inference","llms","neural-network","open-llm"],"archived":false,"github_pushed_at":"2026-07-05T16:47:20+00:00","maintenance_label":"Steady","url":"https://www.graphcanon.com/tools/b4rtaz-distributed-llama","markdown_url":"https://www.graphcanon.com/tools/b4rtaz-distributed-llama.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/b4rtaz-distributed-llama","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=b4rtaz-distributed-llama","shared_categories":[]},{"slug":"microsoft-pai","name":"pai","tagline":"Resource scheduling and cluster management for AI","github_url":"https://github.com/microsoft/pai","owner":"microsoft","repo":"pai","owner_avatar_url":"https://avatars.githubusercontent.com/u/6154722?v=4","primary_language":"JavaScript","stars":2688,"forks":552,"topics":["ai","artificial-intelligence","chainer","cloud","cluster-management","cluster-manager","gpu","gpu-cluster","gpu-computing","gpu-scheduler","jupyter","kubernetes","machine-learning","model-training","on-premise","pytorch","resource-management","scheduling","tensorflow"],"archived":false,"github_pushed_at":"2026-08-15T00:09:09+00:00","maintenance_label":"Steady","url":"https://www.graphcanon.com/tools/microsoft-pai","markdown_url":"https://www.graphcanon.com/tools/microsoft-pai.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/microsoft-pai","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=microsoft-pai","shared_categories":[]},{"slug":"scale3-labs-langtrace","name":"langtrace","tagline":"Open Telemetry based observability tool for LLM applications","github_url":"https://github.com/Scale3-Labs/langtrace","owner":"Scale3-Labs","repo":"langtrace","owner_avatar_url":"https://avatars.githubusercontent.com/u/110545750?v=4","primary_language":"TypeScript","stars":1232,"forks":127,"topics":["ai","datasets","evaluations","gpt","langchain","llm","llm-framework","llmops","observability","open-source","open-telemetry","openai","prompt-engineering","tracing"],"archived":false,"github_pushed_at":"2025-11-17T15:08:48+00:00","maintenance_label":"Slowing","url":"https://www.graphcanon.com/tools/scale3-labs-langtrace","markdown_url":"https://www.graphcanon.com/tools/scale3-labs-langtrace.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/scale3-labs-langtrace","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=scale3-labs-langtrace","shared_categories":["evaluation-observability"]},{"slug":"arize-ai-openinference","name":"openinference","tagline":"OpenTelemetry Instrumentation for AI Observability","github_url":"https://github.com/Arize-ai/openinference","owner":"Arize-ai","repo":"openinference","owner_avatar_url":"https://avatars.githubusercontent.com/u/59858760?v=4","primary_language":"Python","stars":1225,"forks":318,"topics":["aiops","gemini","hacktoberfest","haystack","langchain","langraph","llamaindex","llmops","llms","mcp","openai","openai-agents","opentelemetry","pydantic-ai","smolagents","telemetry","tracing","vercel","vertex"],"archived":false,"github_pushed_at":"2026-09-19T18:57:52+00:00","maintenance_label":"Very active","url":"https://www.graphcanon.com/tools/arize-ai-openinference","markdown_url":"https://www.graphcanon.com/tools/arize-ai-openinference.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/arize-ai-openinference","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=arize-ai-openinference","shared_categories":["evaluation-observability"]}]}}