VS Code Extensions for Local AI Coding

Cline is an AI coding agent for developers who want help understanding a codebase, making changes and running project tasks. It works in VS Code, JetBrains IDEs and the terminal, with a standalone desktop app for macOS, Windows and Linux.

Free Claude Code lets developers use coding agents with local models or a choice of cloud providers. It connects existing clients to a shared model catalog rather than requiring a separate coding workflow.

llama.vscode is a coding assistant for developers who want AI suggestions, chat, and an agent inside VS Code. It lets you use models on your own hardware or connect to external providers.

Context Mode is a local MCP plugin for developers whose AI coding agents fill their context windows with logs, file reads and search results. It stores large tool outputs on your machine so the agent can retrieve relevant passages as needed.

Continue is a coding agent for developers working in a terminal, VS Code or JetBrains. Its Ollama integration can run models on your computer; Standard OpenAI and Anthropic service connections use cloud models. The repository is read-only and no longer actively maintained.

Pathrule gives AI coding agents project knowledge that stays attached to the relevant workspace and file paths. Memories, rules and skills can follow a repository across agents and sessions, so developers can retain decisions and constraints without pasting the same instructions into each conversation.

Link gives AI agents persistent memory so you don't have to repeat preferences, project decisions and context in every session. Multiple agents can read the same local Markdown files, which you can inspect in an editor or Obsidian.

Kolega Code is a local-first AI coding assistant for developers working in the terminal or an editor. Its Gigacode engine lets a model write a Python workflow to coordinate sub-agents for repository reviews, migrations and tasks with independent workstreams. You can inspect and rerun those workflows, including parallel work and separate verification steps.

Paritok is a self-hosted gateway for developers whose coding agents send large file reads, tool output and conversation histories to an LLM. It reduces that input before the request reaches the upstream model.

Kilo Code is an AI coding assistant for developers who want an agent to edit, explain, and debug a codebase in their editor or terminal. You can choose local models, connect a provider with your own API keys, or use Kilo's hosted model access.

CodeGPT is an AI coding assistant for developers who want help writing, refactoring and debugging code inside their editor. It supports VS Code, JetBrains and Visual Studio, with a choice of local or cloud models.

Qwen Code is an AI coding assistant for developers who want an agent to review code, fix bugs and carry out work in a project. You can use it in a terminal, editor, desktop app or browser.

SpecStory saves AI coding conversations so developers can recover decisions, find past solutions, and carry context into another task. Its CLI and editor extensions keep session history locally across projects and coding tools.

Kibitz helps developers follow several Claude Code or Codex sessions and direct work from one place. It turns agent activity into readable commentary, reducing the need to switch between terminal tabs to see what each session is doing.

Agent Flow helps developers inspect how Claude Code and Codex carry out tasks. It turns local agent activity into a visual record for tracing failures, repeated work and slow tool calls.

OpenChamber is a workspace for developers who want to run AI coding agents on their own computer or server and review the results. It uses OpenCode to run agents and keeps projects and sessions accessible across devices.

Claude Task Master helps developers turn product requirements into tasks they can work through with a coding assistant. It keeps task planning and progress tracking inside the editor or terminal where development happens.

MASFactory is a Python framework for developers building workflows in which several AI agents collaborate. It combines natural-language design, code authoring and visual editing so teams can define the work and inspect how agents carry it out.

marimo is a Python notebook for data analysis, machine learning, and interactive experiments. It keeps results consistent as code changes, reducing the manual reruns and hidden state that can make notebooks hard to trust.

RocketRide is an AI pipeline builder and runtime for developers creating document processing, search, and agent workflows. Its visual editor sits in VS Code, alongside the application code that uses those workflows.

Prompty is a prompt format and developer toolkit for building AI applications. It keeps prompt text, model settings, inputs and tool definitions in a portable Markdown file that developers can share across editors and language runtimes.

Claude Code Agent Monitor gives developers one place to follow coding agents and inspect their work across Claude Code, Cursor and Codex. It keeps conversations and activity available for review after a session ends.

Claw Orchestrator gives developers one interface for multiple coding agents and checks their results independently. You define acceptance criteria, and the runtime executes the checks and keeps the evidence on disk.

DarkMoon runs autonomous penetration tests for security teams, DevSecOps engineers and red teamers. It discovers a target's technology stack, assigns specialist AI agents and tests vulnerabilities across connected systems.

Twinny is an AI coding assistant for developers who want completion and help with their repository inside VS Code, using models on their own hardware or a chosen server.

Prompt flow is a Python toolkit for developers who want to run and evaluate LLM application workflows in their own development environment. Its chatbot examples call OpenAI or Azure OpenAI remotely using API credentials. Workflow execution and evaluation can run locally, while those model requests leave the machine.

Weft is a language and framework for developers who want to run AI workflow orchestration on their own machine. Its runtime requires Docker, and its graph editor works in VS Code and compatible forks. Self-hosting the workflow doesn't make its model calls local: the included WhatsApp support bot uses OpenRouter for inference.

Inspect AI is a Python framework for researchers and developers evaluating language models and AI agents. It measures coding, reasoning, knowledge, behavior and multimodal understanding, including tasks where agents must take actions to succeed.

Azure MCP Server gives AI assistants access to Azure services so developers can inspect and manage cloud resources through natural language requests. It brings Azure tools into the editor or agent they're already using.

Claude Context adds repository search to AI coding assistants so they can retrieve relevant code without loading whole directories into their context. It's for developers working with large codebases that an assistant needs to understand.

ECA is an AI coding assistant for developers who want to use their chosen models across different editors. It brings coding help into the editor while keeping the same settings across supported clients.

Vidurai is a local AI memory service for developers who want their AI assistant to understand recent work without repeatedly explaining it. It tracks file changes, terminal activity and errors, then prepares a focused summary for an assistant. The background service and its stored development history stay on your machine.

Wingman-AI is a self-hosted AI agent platform for developers and teams handling coding, research, operations or support tasks that need ongoing context. It coordinates agents with distinct roles and retains their sessions across clients.

SolidGPT is an AI search assistant for developers, available as a VS Code extension or a self-hosted server with a browser interface. The application can run on your machine or server, but its AI processing uses OpenAI's cloud API. It needs an API key and an internet connection, so hosting it yourself doesn't make model inference local.