Coding with local LLMs: 23 open-source projects (2026)

A local proxy that lets Claude Code, Codex, and other coding agents run on free or alternative model providers from your terminal, IDE, browser, or chat apps.

An open-source coding-agent CLI that runs in the terminal and works with cloud APIs and local model backends like Ollama.

Open-source AI developer workspace that builds full-stack web apps in the browser, letting you pick any supported LLM per prompt.

A local proxy that lets Codex, Claude Code, Claude Desktop and Grok Build run any LLM provider.

Open-source AI coding agent for VS Code that works with your own models, including hosted APIs, accounts, and local Ollama or llama.cpp.

Runs open AI models locally on Apple Silicon Macs via MLX and serves them through an Anthropic-API-compatible server so Claude Code works offline.

A coding agent built on pi, tuned for small local LLMs, with background jobs, plan mode and per-phase model selection.

An open-source coding agent for the terminal that runs on local models via Ollama or any OpenAI-compatible API.

Vim plugin that provides local LLM-powered fill-in-the-middle code completion and instruction-based editing via a llama.cpp server.

A self-hosted local coding agent that adds planning, candidate scoring, sandboxed testing and repair around compact open GGUF models.

A command-line tool that opens coding agents like OpenCode and Claude Code preconfigured to run hosted or local open models.

VS Code extension for local LLM code completion, AI chat, and an agentic coding assistant backed by llama.cpp.

A Neovim plugin that provides as-you-type AI code completion using OpenAI, Gemini, Claude, Ollama, llama.cpp, Codestral and other LLM providers.

A minimalist, terminal-native coding agent written in C that works with local llama.cpp models and many cloud LLM providers.

An IntelliJ IDEA plugin that brings local and cloud LLMs into the IDE for reviewing, testing, and explaining project code, with agent mode and spec-driven workflows.

A local inference server for macOS Apple silicon that serves many AI coding agents at once, with batched decoding and grammar-constrained tool calls.

An Emacs package that brings as-you-type code completion from LLMs such as OpenAI, Claude, Gemini, Ollama and llama.cpp into your editor.

A local-LLM-first agentic coding assistant that runs against vLLM, sglang, ollama or llamacpp backends with a browser UI.

A Vim plugin that adds Copilot-style code completion, chat and AI-assisted editing, backed by a local Ollama server or OpenAI-compatible and Mistral APIs.

Local semantic code search MCP server that gives Claude Code, Codex, Cursor and OpenCode meaning-based lookup over your codebase using Ollama or LM Studio embeddings.

Terminal AI agent that plans and runs tasks using free, local (Ollama, LM Studio) or bring-your-own-key cloud models.

A desktop coding agent (Tauri app plus CLI) that runs on your existing AI subscriptions or local models, with built-in code search and verification checks.

A coding agent that runs a local 27B model on your own GPU, with no API key and no data leaving your machine.