sdageltc/agent-durability-bench - 5 Help Wanted Issues

Open Issues Need Help

adapter: Add Google GenAI / Vertex AI Agent Benchmark Adapter 25 days ago

enhancement help wanted

DCP-1.0: Deterministic crash-resilience and SIGKILL fault-injection benchmark for autonomous coding agents

Python

#agentic-ai#ai-agents#benchmark#benchmarks#crash-recovery#crash-resilience#durability#evals#evaluation#fault-injection#fault-tolerance#leaderboard#pregel#python#sigkill

adapter: Add OpenAI Swarm Multi-Agent Benchmark Adapter to DCP-2.0 Suite 25 days ago

enhancement help wanted good first issue

sdageltc/agent-durability-bench

DCP-1.0: Deterministic crash-resilience and SIGKILL fault-injection benchmark for autonomous coding agents

Python

#agentic-ai#ai-agents#benchmark#benchmarks#crash-recovery#crash-resilience#durability#evals#evaluation#fault-injection#fault-tolerance#leaderboard#pregel#python#sigkill

adapter: Add Microsoft AutoGen 0.4 (python-agent-chat) Benchmark Adapter 25 days ago

help wanted good first issue

sdageltc/agent-durability-bench

DCP-1.0: Deterministic crash-resilience and SIGKILL fault-injection benchmark for autonomous coding agents

Python

#agentic-ai#ai-agents#benchmark#benchmarks#crash-recovery#crash-resilience#durability#evals#evaluation#fault-injection#fault-tolerance#leaderboard#pregel#python#sigkill

adapter: Add Hugging Face Smolagents Reference Adapter to DCP-2.0 Benchmark Suite 25 days ago

enhancement help wanted

sdageltc/agent-durability-bench

DCP-1.0: Deterministic crash-resilience and SIGKILL fault-injection benchmark for autonomous coding agents

Python

#agentic-ai#ai-agents#benchmark#benchmarks#crash-recovery#crash-resilience#durability#evals#evaluation#fault-injection#fault-tolerance#leaderboard#pregel#python#sigkill

[Adapter Request] Add Smolagents / OpenHands Framework Adapter for DCP-1.0 29 days ago

help wanted good first issue

sdageltc/agent-durability-bench

DCP-1.0: Deterministic crash-resilience and SIGKILL fault-injection benchmark for autonomous coding agents

Python

#agentic-ai#ai-agents#benchmark#benchmarks#crash-recovery#crash-resilience#durability#evals#evaluation#fault-injection#fault-tolerance#leaderboard#pregel#python#sigkill