PawanOsman/OpenCursor

Open-source Cursor-like AI coding agent for VS Code - agentic chat, multi-provider LLMs (OpenAI, Ollama, llama.cpp), semantic search, and MCP support

What it solves

OpenCursor provides a centralized AI coding agent directly within VS Code, allowing developers to automate file edits, terminal commands, and code exploration while maintaining full control over the changes being applied to their workspace.

How it works

The extension integrates into the VS Code sidebar, where you can connect various AI models—ranging from hosted services like OpenAI and Anthropic to local models running via Ollama or llama.cpp. You interact with the agent through a chat interface, providing context by mentioning files, folders, or terminal output. The agent can then perform tasks, and you review its proposed changes hunk-by-hunk before choosing to accept or undo them.

Who it’s for

It is designed for developers who want an AI-powered coding assistant that supports flexible model selection, works with both cloud-based and local infrastructure, and provides granular control over agent permissions and code modifications.

Highlights

  • Flexible Model Support: Connect to major API providers, use custom endpoints, or run models entirely offline with local inference.
  • Workspace Awareness: Chat with the agent about specific files, Git context, documentation, and terminal output.
  • Controlled Execution: Review all file edits and tool actions before they are applied to your project.
  • Advanced Modes: Switch between different operational modes like Agent, Plan, or Project to suit your current workflow.
  • Local Indexing: Create a searchable local index of your codebase and documentation for more accurate, context-aware responses.

Related

  • Project
    openchamber/openchamber

    OpenChamber is an open‑source, cross‑platform workspace that lets developers run AI coding agents, set automated goals, compare multiple model runs, review changes with guided walkthroughs, and ship code—all from desktop, web, VS Code, or mobile.

  • Project
    GoDiao/dreamcoder

    DreamCoder is a local desktop workspace for managing AI coding agents, offering a visual interface for session tracking, multi-provider model configuration, and cross-device access.

  • Project
    openteams-lab/openteams

    A local-first AI desktop app that provides a shared workspace for multiple coding agents to collaborate, plan, and execute tasks without interfering with each other.

  • Project
    bradAGI/awesome-cli-coding-agents

    A curated directory of over 150 terminal-based AI coding agents that can autonomously read, edit, and execute code in your local development environment.

  • Project
    ggml-org/llama.vscode

    A VS Code extension that streams local LLM completions, offers a multi‑turn coding agent, and manages models/environments via llama.cpp, with support for Telegram, dynamic tools, and Hugging Face model download.