A deterministic linter for agent runs — reads the execution trace and flags structural bugs (ignored errors, schema violations, loops) with evidence. No LLM judge.

agent agent-evaluation ai-agents function-calling linter llm llmops observability opentelemetry python reliability static-analysis tool-calling traces
6 Open Issues Need Help Last updated: Aug 8, 2026

Open Issues Need Help

View All on GitHub
enhancement help wanted

A deterministic linter for agent runs — reads the execution trace and flags structural bugs (ignored errors, schema violations, loops) with evidence. No LLM judge.

Python
#agent#agent-evaluation#ai-agents#function-calling#linter#llm#llmops#observability#opentelemetry#python#reliability#static-analysis#tool-calling#traces
enhancement help wanted ci

A deterministic linter for agent runs — reads the execution trace and flags structural bugs (ignored errors, schema violations, loops) with evidence. No LLM judge.

Python
#agent#agent-evaluation#ai-agents#function-calling#linter#llm#llmops#observability#opentelemetry#python#reliability#static-analysis#tool-calling#traces
enhancement help wanted

A deterministic linter for agent runs — reads the execution trace and flags structural bugs (ignored errors, schema violations, loops) with evidence. No LLM judge.

Python
#agent#agent-evaluation#ai-agents#function-calling#linter#llm#llmops#observability#opentelemetry#python#reliability#static-analysis#tool-calling#traces
good first issue adapter

A deterministic linter for agent runs — reads the execution trace and flags structural bugs (ignored errors, schema violations, loops) with evidence. No LLM judge.

Python
#agent#agent-evaluation#ai-agents#function-calling#linter#llm#llmops#observability#opentelemetry#python#reliability#static-analysis#tool-calling#traces
good first issue rule

A deterministic linter for agent runs — reads the execution trace and flags structural bugs (ignored errors, schema violations, loops) with evidence. No LLM judge.

Python
#agent#agent-evaluation#ai-agents#function-calling#linter#llm#llmops#observability#opentelemetry#python#reliability#static-analysis#tool-calling#traces

A deterministic linter for agent runs — reads the execution trace and flags structural bugs (ignored errors, schema violations, loops) with evidence. No LLM judge.

Python
#agent#agent-evaluation#ai-agents#function-calling#linter#llm#llmops#observability#opentelemetry#python#reliability#static-analysis#tool-calling#traces