LangGraph template for a simple ReAct agent, with MCP tools support and robust test suites.
-
Updated
Sep 28, 2025 - Python
#
agentevals
Here are 10 public repositories matching this topic...
agentevals is a framework-agnostic evaluations solution based on OpenTelemetry traces
-
Updated
Oct 19, 2026 - Python
Evaluation kit for testing stateful agents
-
Updated
Aug 27, 2026 - Python
🤖 Build intelligent agents with the Letta Code SDK, enabling persistent memory and learning for enhanced multi-turn conversations.
python chrome-extension r ai shiny memory exploratory-data-analysis language-model agents ai-agents vscode-snippets wabot lord-botz letta-agents agentevals
-
Updated
Oct 13, 2026 - TypeScript
Offline LLM evaluation suite on LangSmith: RAG and tool-using agent evals, end-state checks, prompt-injection guard, judge calibration and multi-model comparison (LangGraph, openevals, agentevals, AWS Bedrock)
python pytest ai-agents rag langchain prompt-injection langsmith aws-bedrock llm-evaluation langgraph llm-as-a-judge agent-evaluation openevals agentevals
-
Updated
Oct 13, 2026 - Python
Adversarial customer-support RAG agent with guardrails, DeepEval evals and Langfuse tracing, tested on a trap-seeded knowledge base
-
Updated
Oct 10, 2026 - Python
Walk-forward / out-of-sample validation for agent evals — detect eval-set overfitting the way quants detect backtest overfitting. Zero dependencies.
python evaluation backtesting ai-agents overfitting mlops out-of-sample llm llmops walk-forward agent-evaluation agentevals
-
Updated
Jul 15, 2026 - Python
Evaluate a LangGraph agent with the LangSmith SDK, 100% offline: evaluate() with correctness, trajectory matching, a local LLM-as-judge critic, pairwise A/B and a CI regression gate.
python regression-testing observability ai-agents llm prompt-engineering generative-ai langchain llmops evals ollama langsmith trajectory-evaluation llm-evaluation langgraph llm-as-judge agentic-ai agent-evaluation openevals agentevals
-
Updated
Oct 25, 2026 - Python
Is TypeSafe AI's Jev calibrated? Reliability diagram, ECE and saturation split on 240 hand-labelled agent tool calls.
-
Updated
Oct 10, 2026 - Python
Add this topic to your repo
To associate your repository with the agentevals topic, visit your repo's landing page and select "manage topics."