Define evaluations and framework configurations for AI agent applications using simple TOML files.
AgentCI Client Config provides a TOML-based configuration format for:
- Evaluations: Test cases for AI agents and tools with support for accuracy, performance, consistency, and safety testing
- Framework Configurations: Patterns for discovering agents and tools in popular AI frameworks
Create evaluation configs in .agentci/evals/:
# .agentci/evals/test_accuracy.toml
[eval]
description = "Test that the agent responds with correct information"
type = "accuracy"
[eval.targets]
agents = ["my_agent"]
[[eval.cases]]
prompt = "What is the capital of France?"
expected.exact = "Paris"Create framework configs in .agentci/frameworks/:
# .agentci/frameworks/my_framework.toml
[framework]
name = "my-framework"
dependencies = ["my-framework"]
[[agents]]
path = "my_framework.Agent"
args.model = "llm"
args.prompt = "system_prompt"
execution.method = "run"
execution.args.prompt = "user_input"Evaluation TOML files define test cases for agents and tools:
- Evaluation Types: accuracy, performance, consistency, safety, llm, custom
- String Matching: exact, contains, regex, semantic similarity
- Schema Validation: Validate structured JSON outputs
- Tool Calls: Verify correct tool usage
- Multiple Iterations: Run tests multiple times for consistency
Framework TOML files define agent and tool discovery patterns:
- Built-in Frameworks: LangChain, LlamaIndex, Pydantic AI, OpenAI Agents, Google ADK, Agno
- Custom Frameworks: Define your own patterns
- Agent Discovery: Map framework parameters to standard fields
- Tool Discovery: Configure tool types (decorator, function, class, constructor)
- Execution Config: Define how to run agents and tools
your-project/
├── .agentci/
│ ├── evals/ # Evaluation configurations
│ │ ├── accuracy.toml
│ │ ├── performance.toml
│ │ └── safety.toml
│ └── frameworks/ # Framework configurations (optional)
│ └── custom.toml
├── src/
└── tests/
- Evaluation Schema Guide - Complete TOML schema for evaluations
- Framework Schema Guide - Complete TOML schema for frameworks
- Python API - Programmatic usage (optional)