LangGraph
Why it matters: Agent observability, evals, and runtime governance
Source last checked: 2026-06-28
Open public sourceBrowse projects categorized as AI Agent Framework in the current public-source research set, with each record's stored research lens and public source.
Why it matters: Agent observability, evals, and runtime governance
Source last checked: 2026-06-28
Open public sourceWhy it matters: Multi-agent monitoring, workflow evals, and governance
Source last checked: 2026-07-22
Open public sourceWhy it matters: Enterprise agent evaluation and operational controls
Source last checked: 2026-06-28
Open public sourceWhy it matters: Production tracing, workflow testing, and model routing
Source last checked: 2026-06-28
Open public sourceWhy it matters: Agent testing, type-safe workflow governance, and observability
Source last checked: 2026-07-22
Open public sourceWhy it matters: Agent tool-governance review, MCP tool discovery controls, and runtime observability planning.
Source last checked: 2026-07-22
Open public sourceWhy it matters: Agent tracing configuration, session reliability review, and sandboxed execution governance.
Source last checked: 2026-07-17
Open public sourceWhy it matters: Memory privacy, stateful-agent monitoring, and sandbox policies
Source last checked: 2026-06-28
Open public sourceWhy it matters: Agent sandboxing, evals, and lightweight deployment guidance
Source last checked: 2026-06-28
Open public sourceWhy it matters: Agent application integration review, model-provider dependency tracking, and observability planning.
Source last checked: 2026-07-22
Open public sourceExperimental research dimension
These records track public evidence that AI agents are being embedded into high-value vertical workflows. The fields are intentionally sparse and remain source-bound.
Why it matters: Healthcare workflow integration, patient-data controls, monitoring of agent escalations, and audit-ready clinical communication records.
Why it matters: Agentic EDA workflow integration review, engineering data governance, design-flow monitoring, and auditability.
Why it matters: Enterprise AI agent governance, identity and permission review, workflow monitoring, data lineage, and audit controls.
Why it matters: Compliance workflow integration, evidence data quality, security questionnaire controls, and audit trail review.
Why it matters: Agent workflow integration, usage governance, spend visibility, model gateway policy, and audit reporting.
Why it matters: Support-stack integration, conversation monitoring, customer data controls, and resolution auditability.
Why it matters: HR and finance data integration, agent permissions, workflow auditability, and operational governance.
Why it matters: Enterprise workflow integration, exception monitoring, process data quality, and audit-ready automation governance.
Explore related research