Open Issues Need Help
View All on GitHub Independent benchmark reproduction about 1 month ago
help wanted research benchmark
Jostophe-021/mcp-cross-model-delegation Jostophe-021/mcp-cross-model-delegation Open, reproducible framework for measuring, comparing, routing and verifying bounded work across heterogeneous LLMs via MCP.
Open project →
0
Open, reproducible framework for measuring, comparing, routing and verifying bounded work across heterogeneous LLMs via MCP.
Python
#ai-security#anthropic#gemini#llm-benchmark#llm-evaluation#llm-orchestration#llm-routing#mcp#model-context-protocol#model-routing#multi-llm#prompt-injection#python#research
Extend the public prompt-injection benchmark about 1 month ago
good first issue research benchmark security
Jostophe-021/mcp-cross-model-delegation Jostophe-021/mcp-cross-model-delegation Open, reproducible framework for measuring, comparing, routing and verifying bounded work across heterogeneous LLMs via MCP.
Open project →
0
Open, reproducible framework for measuring, comparing, routing and verifying bounded work across heterogeneous LLMs via MCP.
Python
#ai-security#anthropic#gemini#llm-benchmark#llm-evaluation#llm-orchestration#llm-routing#mcp#model-context-protocol#model-routing#multi-llm#prompt-injection#python#research
Add an optional local or OpenAI-compatible provider about 1 month ago
help wanted provider
Jostophe-021/mcp-cross-model-delegation Jostophe-021/mcp-cross-model-delegation Open, reproducible framework for measuring, comparing, routing and verifying bounded work across heterogeneous LLMs via MCP.
Open project →
0
Open, reproducible framework for measuring, comparing, routing and verifying bounded work across heterogeneous LLMs via MCP.
Python
#ai-security#anthropic#gemini#llm-benchmark#llm-evaluation#llm-orchestration#llm-routing#mcp#model-context-protocol#model-routing#multi-llm#prompt-injection#python#research