Writes code: a census of 143 listings

Not a coding agent, but Ada's own MCP Server lets a connected assistant author the Python behind a Code tool from a plain-language description; the draft stages on a change set until a human promotes it.

Source retrieved 2026-09-09

Their engineers build the agent itself as a bespoke engagement, so you are buying custom software delivery rather than a coding agent that authors code from a prompt.

Source retrieved 2026-09-09

A bundled coder persona implements features from written specs using scoped filesystem and allowlisted shell tools, aimed at real multi-file TypeScript rather than snippets.

Source retrieved 2026-09-09

Ships a CodingTools toolkit whose documented job is editing files and running commands in a scoped project directory.

Natural-language requests at the terminal prompt produce edits to named files, and it will create files that do not exist yet, so new code is authored from a description.

Source retrieved 2026-09-30

Agent Composer generates the agent itself from a natural-language description and exposes the auto-generated code for editing, but it authors agent and workflow logic rather than application source files.

Source retrieved 2026-09-24

The TUI's core loop is instructing agents in plain language to edit and build code across the workspace, with the same harness as the desktop app.

Source retrieved 2026-09-10

Custom application and back-end code is written by Arsum's engineers as part of a scoped build, covering interface, back-end and model integration together.

Source retrieved 2026-10-03

PR Author turns a task description or ticket into a branch, an implementation and an opened pull request.

Source retrieved 2026-09-02

Ships a dedicated coder agent whose system prompt specialises it for writing code and creating artifacts, used inside Magentic-One teams alongside a terminal agent.

Source retrieved 2026-09-19

Their own engineers author the agent from a workflow spec mapped in a discovery stage; this is delivered custom development, not an autonomous code-writing tool the buyer drives.

Source retrieved 2026-09-11

Prompt-to-app is the core product: you describe an idea in chat and Bolt generates a working full-stack JavaScript project.

Source retrieved 2026-09-11

AI generates the code inside Studio Execute Code cards and Actions from a prompt; the artifact is bot logic, never source in your own repository.

Source retrieved 2026-09-02

Generates Stagehand browser-automation scripts from a completed Agent run; not general application code.

The agent calls the same file tools Claude Code uses, so it authors and edits code from a prompt.

Source retrieved 2026-09-02

Takes a plain-language description and writes the change across multiple files, then verifies it.

Source retrieved 2026-09-02

Cline authors new code from a plain-language request, creating and editing files across a project rather than completing lines in one buffer.

Source retrieved 2026-09-12

A cloud Coding Agent clones the repo into a sandbox and implements a typed request, but it is in open beta and each starting point is enabled separately per organisation.

Source retrieved 2026-09-15

Edits files and runs local tooling against the working repository.

Source retrieved 2026-09-02

Only inside its own integration workspace: Crescendo Connect turns a plain-English capability request into generated integration code and a published tool, not into application code in your repository.

Source retrieved 2026-09-12

Conductor turns an approved agent blueprint into prompts, subagents, configs, tools and custom functions from natural language, but only for Cresta AI agents, not general application software.

Source retrieved 2026-09-13

Agents you build can author and run Python when code execution is switched on, but this is a capability of agents inside the framework rather than a product that ships code for you.

Source retrieved 2026-09-13

Authoring features from a description is the primary job; the agent edits files and runs terminal commands itself.

Source retrieved 2026-09-02

Implements entire features from a prompt or a Linear/Jira ticket, running and testing the code it writes.

Source retrieved 2026-09-02

The in-editor agent authors new code and whole projects from a prompt.

Source retrieved 2026-09-03

Agents author React components (Frames) and run code in a sandbox to produce files, but Dust documents no repository-level code authoring or commits.

Source retrieved 2026-09-09

ElevenLabs agents do not author code themselves; the Cursor integration lets an agent launch Cursor background agents that do, and needs a paid Cursor plan.

Source retrieved 2026-09-02

Droid authors and patches code from a natural-language task across app, CLI and cloud surfaces.

Source retrieved 2026-09-02

Inline completion plus generation of whole blocks or functions from a comment or prompt, in VS Code, JetBrains IDEs, Cloud Workstations and Cloud Shell Editor.

Source retrieved 2026-09-02

Genspark Code is pitched as a full autonomous coding agent that turns a plain-language brief into a working application, aimed at people who do not code themselves.

Source retrieved 2026-09-15

Authors code from a prompt in three places: inline completions in editors, agent mode in the IDE, and a cloud agent that writes changes on a branch.

Source retrieved 2026-09-02

Code Writer proposes code changes and opens draft pull requests in GitHub, callable from Glean, agents or Slack.

Source retrieved 2026-09-02

ADK does not write application code for you, but its Visual Builder inside the local web UI generates agent projects from a graphical design with an AI assistant, and the vendor marks that builder experimental and Python-only.

Source retrieved 2026-09-15

goose authors new code from a plain-language prompt using the built-in Developer extension's write and edit tools, on your own machine.

Source retrieved 2026-09-16

Agents generate and execute Python and shell code in a per-conversation cloud sandbox that is on by default, and can ship code as a shareable artifact.

Source retrieved 2026-09-30

The model is handed file-write and shell tools inside the project you open, so it authors and edits code directly; Juggler supplies the loop and tooling while the model comes from whichever provider you connect.

Source retrieved 2026-09-17

Julius authors and executes code from a plain-language request, writing Python or R in a hosted container and SQL against connected warehouses, though it targets analysis and deliverables rather than an application repository.

Source retrieved 2026-09-17

Authoring new code from a natural-language task is the core loop; the vendor states it creates files and writes code itself, then verifies the result rather than only proposing a snippet.

Source retrieved 2026-09-18

Authors and refactors code from a prompt across VS Code, JetBrains and the terminal.

Source retrieved 2026-09-02

The vendor ships dcode, a free open-source terminal coding agent that writes and runs code from a prompt; it is a separate package from the paid LangSmith platform.

Source retrieved 2026-09-18

Langflow Assistant turns a natural-language prompt into whole flows or into Python for a single custom component, scoped to Langflow artifacts rather than an application codebase.

Source retrieved 2026-09-03

Agents edit and create files in your repository, including from GitHub issues and PRs.

Source retrieved 2026-09-02

Code authoring is a separate product line, Lindy Build, which generates full-stack apps from a description; the Slack teammate itself is sold for business work, not for writing software in your repository.

Source retrieved 2026-09-19

Builder turns natural language into workflow code; it does not author application code from a description.

Source retrieved 2026-09-02

Generates full-stack applications from a plain-language description, including backend, database and authentication, with no code written by the buyer.

Source retrieved 2026-09-19

Code mode has the model author a TypeScript function that orchestrates your tools, executed in a sandbox; it is a beta tool-use optimisation, not a code-authoring product.

Source retrieved 2026-09-02

Agents you build can write and run code through CodeAct or a provider-hosted code interpreter, but both are gated: the documented CodeAct connector is in preview and code interpreter depends on the model provider you choose.

Source retrieved 2026-09-19

It generates code only inside its own workflows: blocks execute custom JavaScript or Python, and the editor can auto-generate those snippets. It does not author code in your repository.

Source retrieved 2026-09-20

It writes throwaway Python inside a sandbox to compute answers over plugin data, not application source code, and only a subset of Python is available.

Source retrieved 2026-09-20

Authors and edits code from a plain-language instruction in a project directory, running as an interactive terminal session or a single headless prompt.

Source retrieved 2026-09-20

Authors n8n workflows from a plain-language description; the built-in assistant only gives guidance for the JavaScript or Python you write in a Code node, and it never touches application source.

Source retrieved 2026-09-02

Their engineers author new software to order — MVPs, SaaS platforms and customer portals — rather than shipping a product you install yourself.

Source retrieved 2026-09-26

The SDK is a toolkit for building a code-writing agent rather than a ready-made one: sandbox agents get filesystem editing and an apply_patch tool, but you supply the agent, prompt and model.

Source retrieved 2026-09-20

Built-in file and runtime tools let the agent read, write, patch and execute code in its workspace, so it authors code from a chat instruction rather than only advising.

Source retrieved 2026-09-21

Authors new features from a plain description, with a Plan mode first that proposes an approach before any file is written.

Source retrieved 2026-09-21

Core purpose: the agent authors code from a natural-language task across GUI, CLI and SDK surfaces, including scripted headless runs.

Source retrieved 2026-09-21

Perplexity Computer builds apps and sites from a natural-language prompt, and the Agent API sandbox has the model write the code itself.

Source retrieved 2026-09-02

Wren generates agent configuration and the Python tool functions that call your APIs from a description; it does not author application source code.

Source retrieved 2026-09-02

The framework itself is a Python SDK, but its Harness ships a Coder capability whose file tools let an agent author and edit files in a workspace, so code writing comes from the bundled agent rather than a product you sign into.

Source retrieved 2026-09-21

Not a coding agent, but the built-in Website Builder agent in Chat generates a complete website from a text description; there is no general source-authoring product.

Source retrieved 2026-09-22

Describing an app in chat is the entire entry path; Agent authors the project from that prompt, no prior code needed.

Source retrieved 2026-09-22

SafeNet's own team builds the agent, the integrations and the site; the buyer commissions a scoped build rather than driving a code-writing tool.

Source retrieved 2026-09-04

The Agentforce Vibes coding agent turns a natural-language description into Salesforce code and metadata.

Source retrieved 2026-09-03

Ghostwriter turns a prompt, an SOP or a transcript into a production agent journey with workflows and guardrails; what it authors is agent configuration, not application source code.

Source retrieved 2026-09-03

Generates workflow logic, blocks and schemas from a plain-English description, not application source code.

Source retrieved 2026-09-03

Only inside a workflow node: the Code Node ships an AI assistant that drafts Python or TypeScript that runs in a sandbox, not application source in a repository.

Source retrieved 2026-09-09

Project agents run on a coding harness that reads and writes files and runs commands in a sandbox, so new code is authored from the task brief.

Source retrieved 2026-10-03

Engineering delivery is a stated service: the team writes MetaTrader Expert Advisors and production Python pipelines to a scoped brief, and the website tier is described as landing pages built by AI agents.

Source retrieved 2026-09-12

Autopilot generates and extends agent logic from a prompt inside the canvas, and third-party coding agents can author the same projects, but what it writes is agent configuration on a low-code canvas rather than source code in your repository.

Source retrieved 2026-09-03

The hosted Agents product claims agents write code and maintain it, but the vendor describes no repository workflow, branch or diff output anywhere on the page.

Source retrieved 2026-09-27

The assistant writes code and builds small apps itself, alongside roughly thirty bundled skills; the App Builder skill creates interactive web apps from conversation.

Source retrieved 2026-09-27

The coding agent generates and edits code from natural-language prompts and surfaces the result as inline diffs you accept or reject.

Source retrieved 2026-09-03

It writes and runs Python against your own research data for analysis and charts, but it is a research engine, not a tool that authors application code from a spec.

Source retrieved 2026-09-27

Takes a plain-language task in the terminal and creates source files in the working directory, then runs them to check the result.

Source retrieved 2026-09-21

The Agent Panel authors and edits code from a written task description, with the agent gathering its own context and writing files through edit_file and write_file tools.

Source retrieved 2026-09-29

Generates and modifies code across many files and languages from one prompt, then validates its own output and self-corrects on lint or test failures.

Source retrieved 2026-09-09

The agent authors and modifies files directly through built-in write and edit tools, driven from a prompt in the terminal rather than a chat window that returns snippets.

Source retrieved 2026-09-28

Custom development is the core engagement: they write the application as well as the agent, and say AI assists their own delivery from code generation through deployment.

Source retrieved 2026-09-25