> ## Documentation Index > Fetch the complete documentation index at: https://docs.usebench.ai/llms.txt > Use this file to discover all available pages before exploring further. # Supported frameworks > What Bench can recognize in source code, what it can evaluate, and where real app tests are still needed. ## Copy this into your coding agent Paste into Cursor, Codex, Claude Code, or another coding agent in your project. ```text theme={null} Check this app against https://docs.usebench.ai/guides/framework-support. Identify its framework, language, agent entry points, prompts and tool definitions. Explain what Bench can discover from this code and what needs an real app test. Suggest the Bench client for this language and wrappers around the entry point and tools. Do not describe package detection as proof that the whole app has been tested. ``` ## Recognition is not execution Bench's static recognition catalog covers **19 framework and SDK families**. It looks for dependencies, imports, supported declarations and model calls without executing repository code. An installed package is evidence of a dependency, not proof that an agent exists or is running. | Family | Current recognition | | ------------------- | ------------------------------------------------------------------------------------------------------------------------------------------ | | Mastra | JS/TS Agent declarations, direct createWorkflow calls and selected prompt/model/tool references | | Vercel AI SDK | Model calls and JS/TS ToolLoopAgent declarations | | OpenAI Agents SDK | Python and JS/TS Agent declarations, with supported same-file handoff references | | OpenAI model SDK | Imports, dependencies and supported model-call shapes, including Azure client constructors | | Anthropic model SDK | Imports, dependencies and supported model-call shapes | | Claude Agent SDK | Imports and dependencies; no dedicated full agent/subagent reconstruction | | LangGraph | StateGraph declarations, with selected literal Python graph edges | | LangChain | Python create\_agent and JS/TS createAgent declarations, plus supported model wrappers | | Deep Agents | Python create\_deep\_agent and JS/TS createDeepAgent declarations, including awaited factories, with explicit prompt/model/tool references | | CrewAI | Selected Python Agent and Crew declarations with literal membership | | Microsoft AutoGen | Selected Python AssistantAgent and team declarations | | LlamaIndex | Selected Python FunctionAgent, ReActAgent and AgentWorkflow declarations; JS package/import evidence | | Pydantic AI | Selected Python Agent declarations | | Google ADK | Selected Python agents and sequential/parallel/loop declarations; JS package/import evidence | | Google Gen AI SDK | Imports, dependencies and supported model calls | | Mistral SDK | Imports, dependencies and supported model calls | | DSPy | Selected Python Predict, ChainOfThought and ReAct declarations | | Pipecat | Python package/import evidence and selected module-level Pipeline declarations | | LiveKit Agents | Package/import evidence and selected Python Agent and AgentSession declarations | The Python extractor also recognizes selected Cohere, Groq and LiteLLM call patterns. These are additional call-site patterns, not three more complete agent-runtime integrations. ## Language coverage ### Deep Agents Bench recognizes module-level `create_deep_agent(...)` in Python and `await createDeepAgent({...})` in TypeScript, including import aliases. It records explicit prompts, models and named tool references. Built-in tools, middleware, dynamic subagents and file effects need recorded execution evidence; the scan does not reconstruct or run them automatically. Wrap the awaited agent invocation and tool handlers with `bench.trace` in the [JavaScript](/sdk/quickstart) or [Python](/sdk/python) client. See the framework's [Python](https://docs.langchain.com/oss/python/deepagents/overview) and [TypeScript](https://docs.langchain.com/oss/javascript/deepagents/overview) examples. ### Other languages Tracing clients are available for JavaScript/TypeScript, Python, Go and Rust. They use explicit wrappers. More automatic framework adapters are coming soon. Tracing support and source-code discovery are separate capabilities. The deepest extraction is in Python and JavaScript/TypeScript, including JSX/TSX. It can resolve selected imports, model clients, prompts, tools and functions. Java, Kotlin, Go, C#, Rust, Ruby, PHP and Swift have narrower extraction of explicit prompt constructs. These entries need review; they are not full parsers for those languages' agent runtimes. Prompt/configuration files offer another entry point. ## Workflows, agents and tools Known same-file relationships can group declared agents into a multi-agent candidate. Ordinary workflow nodes are not automatically separate agents. Two agents are not grouped merely because they share a repository. Tool discovery is based on declarations and references, not a fixed catalog of named SaaS tools. For supported patterns Bench retains available tool names, descriptions, parameters and source locations. A custom weather, search or order tool can therefore be visible without a provider-specific connector. There is **no claim that every discovered tool can be executed by Bench**. The prompt runner exposes supported tool declarations to a model and continues the conversation with fixed simulated responses. It does not run that tool's code, call a production database, or prove a downstream action succeeded. Some parameter types are simplified, so complete schema fidelity is not guaranteed. ## What can be benched today? The main execution unit is an extracted prompt and configured model, with supported case inputs and tool declarations. Eligibility depends on a resolvable prompt, supported model route, credentials, replayable inputs and available allowance. Recognizing a framework does not guarantee all its models, custom transports or runtime behavior can be evaluated. Bench can test observable response behavior, format, supported tool-call decisions and criteria grounded in supplied evidence. It can compare prompt/model candidates on the same test suite and report measured score and estimated model-cost changes. Whole-application tool execution, orchestration retries, permissions, side effects, real-time voice behavior and arbitrary multi-agent handoffs require additional runtime adapters and controlled execution. Static topology is not proof of those behaviors. A successful example test does not establish support for every application. ## Known scan limits * Dynamic prompt values, runtime-only tools and remote prompt stores may need SDK evidence or explicit inputs. * Cross-file agent relationships, function-local factories, subclasses and chained workflow construction can be incomplete. * Notebooks and fenced documentation examples are not equivalent to application source files. * Recognition traversal is bounded to 5,000 visited files, 2 MB per file and 20 MB total. Tests are excluded by default; hidden paths and symlinks are excluded. * Scanned structure is a proposal with source evidence, not a runtime certification. If discovery misses a system, upload its prompt or declare it through the SDK. Review the resulting system boundary before treating it as complete coverage. Next: [how Bench works](/guides/how-bench-works), [context](/guides/context), [evaluations](/guides/evaluations) and [SDK setup](/sdk/quickstart).