RL observability for LLM agents: behavior maps, native trainer metrics, rollout investigations, and Python/SQL analysis.
Root cause analysis for AI agents. Detects agent loops, retry storms, and optimization opportunities in LangSmith, Langfuse, Arize Phoenix, and OpenTelemetry traces.
Prompt and response tracing for LLM workflows
OKI TRACE: Local LLM observability. See step-by-step, layer-by-layer what your AI thinks. Logit Lens & Attention for HuggingFace models.
Forkline is a replay-first tracing and diffing library for agentic AI workflows that lets you deterministically reproduce, fork, and compare agent runs to find exactly where behavior diverged.
LLM Harness for developing, debugging, and evaluating custom agents, tools, MCP servers, prompts, and memory constructs using Anthropic, OpenAI, or a local model.
Offline debugging for AI agent traces: finds loops, retry storms, and hallucinated tool calls.
Stop guessing why your MLX model outputs garbage. Triage in 30 seconds — no model load required.
To associate your repository with the llm-debugging topic, visit your repo's landing page and select "manage topics."