7 projects
ai-agent-sentry
Crash reporting for AI agents. Catch failures before your users do.
bench-my-llm
Dead-simple LLM benchmarking CLI. Measure TTFT, TPS, latency, cost, and quality for any OpenAI-compatible API.
mcp-server-forge
Scaffold, test, and publish Model Context Protocol (MCP) servers in seconds
llm-shelter
Safety and guardrails toolkit for LLM applications
llm-promptdiff
Git-style diff and version control for LLM prompts
agent-trace-replay
Record, replay, and debug AI agent execution traces
llm-cost-guardian
Real-time cost monitoring and budget enforcement for LLM API calls
