Open Issues Need Help
View All on GitHub Build a Harbor-compliant task manifest for the toy tasks about 1 month ago
help wanted
muraliikrishnant/AgentDyno muraliikrishnant/AgentDyno Inference-aware coding-agent harness lab: measures task success vs. inference cost (TTFT/ITL/throughput) across harness architectures on Nebius Token Factory + NVIDIA Nemotron
Open project →
0
Inference-aware coding-agent harness lab: measures task success vs. inference cost (TTFT/ITL/throughput) across harness architectures on Nebius Token Factory + NVIDIA Nemotron
Python
#agentic-ai#coding-agents#llm-evaluation#nebius#nvidia-nemotron
Add --n-concurrent flag for TTFT-under-load experiments about 1 month ago
help wanted good first issue
muraliikrishnant/AgentDyno muraliikrishnant/AgentDyno Inference-aware coding-agent harness lab: measures task success vs. inference cost (TTFT/ITL/throughput) across harness architectures on Nebius Token Factory + NVIDIA Nemotron
Open project →
0
Inference-aware coding-agent harness lab: measures task success vs. inference cost (TTFT/ITL/throughput) across harness architectures on Nebius Token Factory + NVIDIA Nemotron
Python
#agentic-ai#coding-agents#llm-evaluation#nebius#nvidia-nemotron
Add a pytest test suite about 1 month ago
help wanted good first issue
muraliikrishnant/AgentDyno muraliikrishnant/AgentDyno Inference-aware coding-agent harness lab: measures task success vs. inference cost (TTFT/ITL/throughput) across harness architectures on Nebius Token Factory + NVIDIA Nemotron
Open project →
0
Inference-aware coding-agent harness lab: measures task success vs. inference cost (TTFT/ITL/throughput) across harness architectures on Nebius Token Factory + NVIDIA Nemotron
Python
#agentic-ai#coding-agents#llm-evaluation#nebius#nvidia-nemotron
Implement plan-execute orchestration architecture about 1 month ago
help wanted good first issue
muraliikrishnant/AgentDyno muraliikrishnant/AgentDyno Inference-aware coding-agent harness lab: measures task success vs. inference cost (TTFT/ITL/throughput) across harness architectures on Nebius Token Factory + NVIDIA Nemotron
Open project →
0
Inference-aware coding-agent harness lab: measures task success vs. inference cost (TTFT/ITL/throughput) across harness architectures on Nebius Token Factory + NVIDIA Nemotron
Python
#agentic-ai#coding-agents#llm-evaluation#nebius#nvidia-nemotron