> ## Documentation Index > Fetch the complete documentation index at: https://langchain-5e9cc07a-preview-opensw-1783454697-4d4e2b4.mintlify.site/llms.txt > Use this file to discover all available pages before exploring further. # Interpreters > Run lightweight code inside Deep Agents to compose tools, orchestrate subagents, and transform structured data Interpreters give agents a programmable, **in-memory** workspace inside the agent loop. The agent writes code to complete a task, and the runtime executes it and returns only the relevant results. Intermediate results do not become part of the model context. Where [sandboxes](/oss/javascript/deepagents/sandboxes) are a code-first way for acting on an environment (such as running commands, installing dependencies, and editing files), interpreters are a code-first way for composing tools, preserving state, and deciding what information should return to the model. Interpreters are in [**beta**](/oss/javascript/versioning). APIs and lifecycle behavior may change between releases. Interpreters require `@langchain/quickjs`. ## Why use interpreters? Most agent work alternates between model reasoning and tool calls. A model can fire several tool calls in one turn, but that batch is fixed the moment it is emitted. Nothing can loop, branch on a result, retry a failure, or feed one call's output into the next without another model turn, and every result returns to the model's context. The model also decides how many calls to issue, so asking it to dispatch work across hundreds of items is unreliable, and it tends to cover a sample rather than every item. Interpreters move that orchestration into code so the model reasons about *what* to do, not every intermediate step. Call selected tools from interpreter code, including loops, retries, branching, and parallel batches. Dispatch subagents from code for fan-out, verification, and recursive workflows over large inputs. Keep intermediate values in runtime state without overloading the model context. Sort, group, parse, validate, score, and aggregate structured data without another model turn. ## Choose a pattern Use interpreters for code inside the agent loop: composing tools, preserving state, and controlling what returns to the model. Use [sandboxes](/oss/javascript/deepagents/sandboxes) for code against an environment: shell commands, package installs, tests, filesystem edits, and OS-level execution. | Need | Use | | ------------------------------------------------------------------------------------------------ | ---------------------------------------------------------------------------------- | | One or two simple external calls | Normal tool calling | | Pure in-memory JavaScript: loops, branches, retries, or data transforms (no external tools) | Interpreter | | Many external tool calls orchestrated from code (requires [PTC](#programmatic-tool-calling-ptc)) | Interpreter with [programmatic tool calling (PTC)](#programmatic-tool-calling-ptc) | | Many independent units of work, multiple perspectives, or recursive analysis over large inputs | Interpreter with [dynamic subagents](/oss/javascript/deepagents/dynamic-subagents) | | Shell commands, package installs, tests, or full OS filesystem access | [Sandboxes](/oss/javascript/deepagents/sandboxes) | ## Quickstart Install the QuickJS middleware package, then pass interpreter middleware using the `middleware` argument on `createDeepAgent`. ```bash npm theme={null} npm install deepagents @langchain/quickjs ``` ```bash pnpm theme={null} pnpm add deepagents @langchain/quickjs ``` ```bash yarn theme={null} yarn add deepagents @langchain/quickjs ``` ```ts Google theme={null} import { createDeepAgent } from "deepagents"; import { createCodeInterpreterMiddleware } from "@langchain/quickjs"; const agent = createDeepAgent({ model: "google-genai:gemini-3.5-flash", middleware: [createCodeInterpreterMiddleware()], }); ``` ```ts OpenAI theme={null} import { createDeepAgent } from "deepagents"; import { createCodeInterpreterMiddleware } from "@langchain/quickjs"; const agent = createDeepAgent({ model: "openai:gpt-5.5", middleware: [createCodeInterpreterMiddleware()], }); ``` ```ts Anthropic theme={null} import { createDeepAgent } from "deepagents"; import { createCodeInterpreterMiddleware } from "@langchain/quickjs"; const agent = createDeepAgent({ model: "anthropic:claude-sonnet-4-6", middleware: [createCodeInterpreterMiddleware()], }); ``` ```ts OpenRouter theme={null} import { createDeepAgent } from "deepagents"; import { createCodeInterpreterMiddleware } from "@langchain/quickjs"; const agent = createDeepAgent({ model: "openrouter:openrouter:z-ai/glm-5.2", middleware: [createCodeInterpreterMiddleware()], }); ``` ```ts Fireworks theme={null} import { createDeepAgent } from "deepagents"; import { createCodeInterpreterMiddleware } from "@langchain/quickjs"; const agent = createDeepAgent({ model: "fireworks:accounts/fireworks/models/glm-5p2", middleware: [createCodeInterpreterMiddleware()], }); ``` ```ts Baseten theme={null} import { createDeepAgent } from "deepagents"; import { createCodeInterpreterMiddleware } from "@langchain/quickjs"; const agent = createDeepAgent({ model: "baseten:zai-org/GLM-5.2", middleware: [createCodeInterpreterMiddleware()], }); ``` ```ts Ollama theme={null} import { createDeepAgent } from "deepagents"; import { createCodeInterpreterMiddleware } from "@langchain/quickjs"; const agent = createDeepAgent({ model: "ollama:north-mini-code-1.0", middleware: [createCodeInterpreterMiddleware()], }); ``` ## How interpreters work The middleware adds an `eval` tool to the agent. When useful, the agent writes JavaScript and calls `eval`; you do not call the interpreter directly. The tool runs code in a QuickJS context whose variables can persist between `eval` calls, depending on the persistence `mode`. It captures `console.log`, `console.warn`, and `console.error`, and returns the result of the last expression. The agent can write code like this: ```ts theme={null} const rows = [ { team: "alpha", score: 8 }, { team: "beta", score: 13 }, { team: "alpha", score: 21 }, ]; const totals = rows.reduce((acc, row) => { acc[row.team] = (acc[row.team] ?? 0) + row.score; console.log(`${row.team} score: ${acc[row.team]}`); return acc; }, {}); totals; ``` Code runs against [**QuickJS**](https://github.com/quickjs-ng/quickjs), a lightweight JavaScript runtime. By default, interpreter code has no access to the host filesystem, network, shell, package manager, or clock. It can compute, hold state, and write to `console.log`, `console.warn`, or `console.error`, and nothing more. Two explicit bridges extend that reach: * **Tools**, through [programmatic tool calling (PTC)](#programmatic-tool-calling-ptc). Provide an allowlist of tools as async functions under the `tools` namespace. These can be the agent's own tools or standalone tools you define and pass in. * **Subagents**, through [dynamic subagents](/oss/javascript/deepagents/dynamic-subagents). When the agent has subagents configured, the interpreter exposes a `task()` global for dispatching them from code. Programmatic tool calling is off until you [enable it](#enable-ptc). Subagent dispatch through `task()` is on by default whenever the agent has subagents, and you can turn it off. Nothing else crosses the QuickJS boundary. ## Programmatic tool calling (PTC) Programmatic tool calling (PTC) exposes selected agent tools inside the interpreter under the global `tools` namespace. Instead of asking the model to issue one tool call, wait for the result, and then decide the next call, the agent can write code that calls tools in loops, branches, retries, or parallel batches. This helps when intermediate results are only inputs to the next step: the interpreter filters or aggregates them before anything returns to the model, keeping multi-step workflows token-efficient. It is model-agnostic, implemented by middleware rather than a provider-specific tool-calling API. The middleware exposes each allowlisted tool as an async function under `tools`. The agent calls it with `await`, processes the result in code, and the model sees only the final interpreter output, not every intermediate value. Tool names are converted to camelCase while the input object still follows the tool's schema, so a tool named `web_search` becomes `tools.webSearch(...)`: ```ts theme={null} const result: string = await tools.webSearch({ query: "deepagents interpreters", }); ``` ### Enable PTC Enable PTC with an explicit allowlist: ```ts Google theme={null} import { createDeepAgent } from "deepagents"; import { createCodeInterpreterMiddleware } from "@langchain/quickjs"; const agent = createDeepAgent({ model: "google-genai:gemini-3.5-flash", middleware: [createCodeInterpreterMiddleware({ ptc: ["web_search"] })], }); ``` ```ts OpenAI theme={null} import { createDeepAgent } from "deepagents"; import { createCodeInterpreterMiddleware } from "@langchain/quickjs"; const agent = createDeepAgent({ model: "openai:gpt-5.5", middleware: [createCodeInterpreterMiddleware({ ptc: ["web_search"] })], }); ``` ```ts Anthropic theme={null} import { createDeepAgent } from "deepagents"; import { createCodeInterpreterMiddleware } from "@langchain/quickjs"; const agent = createDeepAgent({ model: "anthropic:claude-sonnet-4-6", middleware: [createCodeInterpreterMiddleware({ ptc: ["web_search"] })], }); ``` ```ts OpenRouter theme={null} import { createDeepAgent } from "deepagents"; import { createCodeInterpreterMiddleware } from "@langchain/quickjs"; const agent = createDeepAgent({ model: "openrouter:openrouter:z-ai/glm-5.2", middleware: [createCodeInterpreterMiddleware({ ptc: ["web_search"] })], }); ``` ```ts Fireworks theme={null} import { createDeepAgent } from "deepagents"; import { createCodeInterpreterMiddleware } from "@langchain/quickjs"; const agent = createDeepAgent({ model: "fireworks:accounts/fireworks/models/glm-5p2", middleware: [createCodeInterpreterMiddleware({ ptc: ["web_search"] })], }); ``` ```ts Baseten theme={null} import { createDeepAgent } from "deepagents"; import { createCodeInterpreterMiddleware } from "@langchain/quickjs"; const agent = createDeepAgent({ model: "baseten:zai-org/GLM-5.2", middleware: [createCodeInterpreterMiddleware({ ptc: ["web_search"] })], }); ``` ```ts Ollama theme={null} import { createDeepAgent } from "deepagents"; import { createCodeInterpreterMiddleware } from "@langchain/quickjs"; const agent = createDeepAgent({ model: "ollama:north-mini-code-1.0", middleware: [createCodeInterpreterMiddleware({ ptc: ["web_search"] })], }); ``` After PTC is enabled, the agent can call the allowlisted tool from interpreter code. This example searches several topics in parallel and combines the results before returning to the model: ```ts theme={null} const topics = ["retrieval", "memory", "evaluation"]; const results = await Promise.all( topics.map((topic) => tools.webSearch({ query: `${topic} best practices 2025` }), ), ); results.join("\n\n"); ``` PTC calls currently execute through the interpreter bridge and do not go through the normal tool calling path. As a result, `interruptOn` approval workflows are not enforced per PTC-invoked tool call. ## Dynamic subagents The following overview below covers when to use dynamic subagents and a minimal `task()` pattern. For configuration, orchestration examples, workflow triggers, and safety notes, see [Dynamic subagents](/oss/javascript/deepagents/dynamic-subagents). Dynamic subagents let the interpreter dispatch configured [subagents](/oss/javascript/deepagents/subagents) from code using the built-in `task()` global. A task that spans many independent units, such as reviewing every file in a directory or triaging a batch of tickets, becomes a loop that fans out work and synthesizes the results. Use dynamic subagents for: * **Fan-out and synthesize**: Run the same kind of work across many items in parallel, then combine the results. * **Verification**: Send findings to independent verifier subagents and keep only confirmed results. * **Recursive workflows**: Keep a working set in interpreter variables, select slices, call subagents, and refine the result. ```ts theme={null} const paths = ["src/auth.ts", "src/routes/api.ts"]; const reviews = await Promise.all( paths.map((path) => task({ description: `Review ${path} for authentication issues`, subagentType: "reviewer", }), ), ); reviews.join("\n\n"); ``` ## Security Interpreters use QuickJS to run untrusted JavaScript with strict default isolation. Treat that as a scoped interpreter runtime, not a full production sandbox backend. Every tool you expose through PTC is an outside capability that interpreter code can use. Treat the PTC allowlist as a permission boundary: expose only the tools the agent needs, and avoid bridging broad tools that can access sensitive systems, spend money, mutate data, or call unrestricted networks unless that behavior is intentional. | Capability | Available by default | How to expose it | | ----------------------------------------------------------- | -------------------- | ------------------------------------------------------------------------------------------------------------------------ | | JavaScript execution | Yes | Add interpreter middleware | | Top-level `await` | Yes | Use promises in interpreter code | | `console.log`, `warn`, `error` capture | Yes | Disable with `captureConsole: false` | | Agent tools | No | Add a PTC allowlist | | Filesystem access | No | Add the [built-in filesystem tools](/oss/javascript/deepagents/overview#virtual-filesystem-access) via the PTC allowlist | | Network access | No | Expose a specific network tool through PTC | | Wall-clock or datetime access | No | Expose an explicit time tool if needed | | Shell commands, package installs, tests, OS-level execution | No | Use a [sandbox backend](/oss/javascript/deepagents/sandboxes) | **How code execution works** Interpreter code runs in a WASM-sandboxed QuickJS runtime via [QuickJS-Emscripten](https://github.com/justjake/quickjs-emscripten), not in the host Node.js process. Treat interpreters as a capability-scoped execution layer: bridge only the tools and subagents the agent needs, and keep the PTC allowlist narrow. ## Configuration `createCodeInterpreterMiddleware` accepts the following options: | Option | Default | Purpose | | -------------------- | -------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | `memoryLimitBytes` | `64 * 1024 * 1024`
(64 MB) | Cap QuickJS heap memory per session. | | `maxStackSizeBytes` | `320 * 1024` | Cap QuickJS stack size per session. | | `executionTimeoutMs` | `5000` | Timeout limit in milliseconds for each `eval` call. Negative values disable the timeout. | | `toolName` | `"eval"` | Name of the interpreter tool exposed to the model. | | `captureConsole` | `true` | Capture `console.log`, `console.warn`, and `console.error` in the tool response. Set to `false` to discard console output. | | `maxResultChars` | `4000` | Truncate result, error, and console output returned to the model to a maximum character count. | | `systemPrompt` | `null` | Custom system prompt for the interpreter tool. Defaults to the built-in prompt when `null`. | | `ptc` | omitted | Allowlist of tool names or `StructuredToolInterface` instances exposed as `tools.*` inside the interpreter. Omit to disable. See [Enable PTC](#enable-ptc). | | `maxPtcCalls` | `256` | Maximum `tools.*` calls allowed per `eval`. Set to `null` only in trusted environments. See [Programmatic tool calling (PTC)](#programmatic-tool-calling-ptc) and [Security](#security). | | `subagents` | `true` | Expose the built-in `task()` global when the agent has subagents. Set to `false` to require dispatch through the normal `task` tool. See [Dynamic subagents](#dynamic-subagents). | ***
[Connect these docs](/use-these-docs) to Claude, VSCode, and more via MCP for real-time answers. [Edit this page on GitHub](https://github.com/langchain-ai/docs/edit/main/src/oss/deepagents/interpreters.mdx) or [file an issue](https://github.com/langchain-ai/docs/issues/new/choose).