Results for “code-completion”

Morph

API that instantly merges AI-generated code edits into your actual files, so coding agents can make changes without rewriting whole files.

Zencoder

AI coding agent that treats a feature or bug fix as a full workflow — planning, coding, testing and review — instead of just answering chat questions.

Clark

Clark is a coding agent you can run either in the cloud, on tasks that don't need your local setup, or directly on your own machine when it does — instead of forcing every task into one mode.

AskCodi

An AI coding helper that lives in your editor and, in its newer 'AI CTO' mode, runs a small team of coding agents for you inside a Mac app — like having a junior dev team you manage instead of code you write line by line.

Ascii

Sends out multiple AI coding agents to work on your repositories at once — like hiring a small team of junior developers who each take a ticket, write the code, run the tests, and hand back a pull request for you to review.

Desktop Commander

An MCP server that lets Claude (or another AI client) actually reach into your computer — read and edit files, run terminal commands, search your codebase — instead of just talking about what you should do.

Graphify

A tool that maps your codebase into a graph of how everything connects, so AI coding assistants like Claude Code or Cursor can actually understand your project's structure instead of guessing from scattered file snippets.

Juggler

A visual, point-and-click alternative to running AI coding agents in a terminal — you can see the whole conversation as a browsable tree, inspect exactly what tool calls happened, and branch off to try a different approach without losing your place.

Orca

A free tool that lets you run several AI coding assistants on the same problem at once, each working in its own isolated copy of your code, so you can compare their different solutions and pick (or merge) the best one.

Typeahead

An autocomplete tool that finishes your sentences in any Mac app — email, code editor, chat — without ever sending what you type to the internet.

Pluck

A browser extension that lets you click on any button, card, or layout you like on a website and instantly turn it into ready-to-use code or a Figma file, instead of manually rebuilding it from scratch.

Dirac

An open-source AI coding agent built to cut API costs 50-80% versus other agents by curating context instead of dumping entire files into every prompt.

Kolega Code

A free, open-source command-line assistant that writes and edits code for you like Claude Code or GitHub Copilot's CLI mode, but lets you plug in whichever AI model you already pay for — Anthropic, OpenAI, Google, Groq, or a model running locally on your

Continue

Continue is the open-source engine you can drop into VS Code or JetBrains to get AI code suggestions and edits without being locked into one company's black-box coding assistant — you choose which AI model powers it.

Nanocoder

Nanocoder is a free terminal coding agent built by a volunteer community rather than a company — no paid tiers, no telemetry, and you choose whether it runs on your own local model or a cloud provider.

OpenCode

OpenCode was a free, open-source terminal coding agent that let you plug in any AI model instead of being locked to one vendor — it's now archived, with its team continuing development under a new name, Crush.

Nibware

A library of over 1,250 ready-made SwiftUI building blocks you can copy straight into your iOS app, each one shown as an actual screenshot so you know exactly what you're getting before you paste the code.

Fine

An AI teammate that takes a plain-English task or a Jira ticket and turns it into a working pull request, without you setting up a dev environment first.

CodeParrot

A VS Code plugin that turns a Figma design or a screenshot into frontend code that actually looks like the rest of your codebase, instead of a fresh throwaway component.

Potpie

An open-source tool that builds AI agents which actually understand how your codebase fits together — not just individual files — so they can debug, plan features, and answer questions grounded in the real structure of your code.