Appendix A: Tool & Framework Directory

This appendix provides a curated list of tools and resources for building agent infrastructure. The landscape changes rapidly - tools listed here may have been superseded by the time you read this. The categories and evaluation criteria are more durable than the specific tools.

When evaluating tools, consider five criteria. Maturity: Is it production-ready or experimental? Check the GitHub stars, the release cadence, and whether anyone is using it in production. Standards compliance: Does it support MCP, OpenTelemetry, and other standards? Non-standard tools create lock-in. Community: Is there an active community? Can you get help when you’re stuck? Maintenance: Is it actively maintained? Check the last commit date and the issue response time. License: Is the license compatible with your use case? Some tools are open-source for development but require a commercial license for production.

Agent frameworks

Choosing an agent framework is one of the most consequential early decisions in agent adoption. The framework determines your development velocity, your operational capabilities, and your migration cost if you need to switch later.

For teams starting out: Use the simplest framework that meets your needs. If you’re building a single-agent system for coding tasks, you may not need a framework at all - the model provider’s SDK (Anthropic’s Python SDK, OpenAI’s Python SDK) plus a simple loop is sufficient. Adding a framework adds complexity, and complexity you don’t need is complexity that slows you down.

For teams building multi-agent systems: LangGraph or CrewAI provide the orchestration primitives you need - agent definitions, tool routing, state management, and handoff protocols. LangGraph is more flexible (graph-based, supports arbitrary workflows). CrewAI is more opinionated (role-based, supports team-of-agents patterns). Choose based on whether you want flexibility or convention.

For teams building production infrastructure: Consider whether you need a framework or a platform. A framework gives you building blocks - you assemble them into a system. A platform gives you a complete system - you configure it for your use case. Frameworks are more flexible but require more engineering investment. Platforms are less flexible but get you to production faster.

ToolTypeLanguageLicenseBest For
LangChainFrameworkPython/JSMITComplex chains and workflows
LangGraphOrchestrationPython/JSMITGraph-based agent workflows
CrewAIFrameworkPythonMITRole-based multi-agent teams
AutoGenFrameworkPythonMITMulti-agent conversations
OpenAI Agents SDKSDKPythonMITOpenAI-native agent building
GooseAgentRust/PythonApache 2.0MCP-native production agent
MastraFrameworkTypeScriptMITTypeScript-first agent building

Coding agents

ToolTypePricingBest For
OnaAutonomousUsage-basedProduction-grade fully autonomous engineering with full environment access, secure sandboxed execution, multi-repo migrations at scale, enterprise (VPC)
Claude CodeCLI + IDEUsage-basedDeep codebase reasoning
OpenAI CodexCloudUsage-basedParallel task execution
CursorIDE$20/monthReal-time code generation
WindsurfIDEFree/$15/monthMulti-file cascade editing
GitHub CopilotIDE + CLI$10-39/monthWorkspace-aware completion
DevinAutonomousUsage-basedEnd-to-end task completion

Context engineering

ToolPurposeLanguageLicense
DistillContext deduplication and compressionPythonMIT
AnythingLLMLocal RAG and document managementJavaScriptMIT
ChromaVector database for embeddingsPythonApache 2.0
WeaviateVector databaseGoBSD-3
QdrantVector databaseRustApache 2.0
skills.shOpen agent skills ecosystem (reusable SKILL.md files)TypeScriptMIT

Authorization & security

ToolPurposeLanguageLicense
OpenFGAZanzibar-style authorizationGoApache 2.0
sandbox-runtimeAgent sandboxingPythonMIT
BubblewrapUnprivileged sandboxingCLGPL
gVisorApplication kernel for containersGoApache 2.0

Observability

ToolPurposeLanguageLicense
OpenTelemetryDistributed tracing and metricsMultiApache 2.0
LangfuseLLM observability platformTypeScriptMIT
LangSmithLangChain observabilityPythonCommercial
Arize PhoenixML observabilityPythonApache 2.0

MCP ecosystem

ToolPurposeLanguage
MCP SDK (TypeScript)Build MCP servers/clientsTypeScript
MCP SDK (Python)Build MCP servers/clientsPython
MCP ServersReference MCP server implementationsMulti
MCP InspectorDebug and test MCP serversTypeScript

Local inference

ToolPurposeBest For
OllamaLocal model runnerEasy setup, many models
llama.cppOptimized local inferencePerformance-critical
vLLMHigh-throughput servingProduction serving
LocalAIOpenAI-compatible local APIDrop-in replacement