local-first Tag
Local-First AI Coding Tools - Private, On-Device Development
Explore AI coding tools that run locally on your machine or self-hosted, keeping your code private and your data under your control.
local-first Tag
Local-First AI Coding Tools - Private, On-Device Development
Local-first AI tools run entirely on-device or self-hosted, so your code never leaves your machine. Ideal for regulated industries and privacy-conscious teams.
Local-first tools are the right choice when your codebase contains sensitive IP, regulated data, or when you need to work offline.
Related resources
local-first Tools (21)
openworker
Andrew Ng's open-source desktop agent that hands back finished work instead of chat. It runs on your machine, connects to the tools you already use, and checks in before anything consequential. The August 2026 release added three security coworkers: one drives semgrep and secret scans and triages findings by reachability rather than severity, one checks Terraform against the live cloud read-only and opens infrastructure pull requests, and one audits dependencies. Bring your own API key, or run a local model through Ollama and nothing leaves the machine.
vibekeys
A six-key mechanical keypad with a rotary knob that maps Accept, Retry, YOLO, Escape and Voice to physical buttons for Claude Code, Cursor, Codex, Gemini CLI and Copilot. The Max model adds a status screen and remote control over Wi-Fi.
vibe80
Apache-2.0 web workspace that orchestrates Codex and Claude Code over your Git repositories in sandboxed parallel worktrees, with a PTY web terminal and a mobile companion app that picks up a session by QR code.
orca
Open-source Agent Development Environment for running a fleet of AI coding agents at once. Every task gets its own git worktree, its own agent terminal, and its own browser tab, so you can fan one prompt across several agents, compare the diffs, and merge the winner. It drives roughly 30 CLI agents you already pay for, including Claude Code, Codex, OpenCode, Cursor and Copilot, and ships on macOS, Windows, Linux, iOS and Android.
conductor
macOS app for running Claude Code, Codex, Cursor, and OpenCode side by side, each in its own isolated workspace, without wrangling git worktrees by hand. You bring your own agent subscriptions and keys. The paid Conductor Cloud tier moves those workspaces into Vercel sandboxes so agents keep running after you shut the laptop, and adds shared multiplayer workspaces plus an API.
vibekit (superagent)
Looking for the mobile AI app builder at vibekit.bot? That is a different product: see VibeKit at /tools/vibekit-bot. This page covers superagent-ai/vibekit, the open-source sandbox. MIT-licensed CLI wrapper and SDK from Superagent (YC) that runs Claude Code, Gemini CLI, Codex, Grok CLI, and OpenCode inside an isolated sandbox, redacting secrets from completions and logging every file change, shell command, and outbound call. Install with npm and prefix your usual command: `vibekit claude`. The local path uses Docker and needs no cloud account; the `@vibe-kit/sdk` package embeds the same sandboxing in your own app across E2B, Dagger, Daytona, Northflank, Cloudflare, Modal, and Fly.io. Development has been quiet since November 2025: no commits to the default branch since 2025-11-10, no npm publish since 2025-10-14, and Superagent's recent work has shifted to its grok-cli and gateway projects. The code is MIT and still installs, so treat it as forkable rather than actively supported. Naming history, and there are three collisions worth knowing. First: in July 2025 the team shipped an open-source v0 clone called vibe0, built on VibeKit. That name has been retired and the project is now just VibeKit, with the template surviving in the repo as templates/v0-clone. Second: VibeKit at vibekit.bot is an unrelated mobile-first AI app builder by Brian Boisjoli, still actively shipping, and its own about page states it is not affiliated with this project. Third: Vibe Scan at vibe0.com.au is a security scanner from a Perth consultancy that happens to share the vibe0 name.
vibe kanban
Open-source kanban board for orchestrating AI coding agents. Plan tasks as issues, run Claude Code, Codex, or Gemini CLI in isolated git worktrees, review diffs inline, and open pull requests from one local UI. The company behind it (bloop) shut down in April 2026, but the project lives on as community-maintained open source and local workspaces keep working.
parallel code
Free, open-source desktop app that dispatches AI coding agents in parallel, each in its own git worktree. It runs the real CLI agents you already trust (Claude Code, Codex, Gemini) side by side, then lets you review the diffs, merge the wins, and toss the rest.
openclaw
Free, open-source personal AI assistant by Peter Steinberger that runs on your machine and performs real tasks autonomously. Talk to it from WhatsApp, Telegram, iMessage, Discord, Slack, or Signal. One-liner install, persistent local memory, ClawHub skills marketplace, sandbox or full system access, and support for Claude, OpenAI, DeepSeek, Qwen, or local LLMs via Ollama. 247K GitHub stars by March 2026; Steinberger joined OpenAI on February 14, 2026 with a non-profit foundation taking project stewardship.
hermes agent
Self-hosted autonomous agent from Nous Research with a built-in learning loop. Creates skills from experience, persists memory across sessions, and runs 24/7 on your own hardware with sandboxed terminals and messaging-app gateways.
hermes webui
Lightweight dark-themed browser interface for Hermes Agent with full parity to the CLI. Three-panel layout with sessions sidebar, chat, and workspace file browser. Community project that runs against any existing Hermes install.
deerflow
Open-source SuperAgent harness from ByteDance that orchestrates sub-agents, long-term memory, extensible skills, and Docker-based sandboxes to execute complex, long-horizon tasks like deep research, coding, and content creation.
claude code cli
Anthropic's official terminal-based agentic coding tool that deeply understands your local codebase, autonomously edits files, runs terminal commands, handles git workflows, and iterates via natural language prompts. Now with Channels (Telegram/Discord remote messaging), Remote Control, Dispatch, and /loop scheduling for persistent autonomous agents. Designed for professional developers who live in the terminal.
void
Free, open-source VS Code fork with built-in AI coding features, inline completions, chat, and multi-file edits. All model calls can go directly to your chosen provider or a local model, keeping your code private.
pieces
AI-powered snippet manager and productivity tool. Saves, organizes, and explains code snippets. Works offline and integrates with your workflow.
vibesdk
Open-source AI "vibe coding" platform built on Cloudflare. Generate full-stack apps from prompts, sandboxed in WebContainers, and deploy instantly to Workers. The self-hosted alternative to Bolt.new.
intellicode
Microsoft's AI-assisted development tool for Visual Studio and VS Code. Provides whole-line completions and API usage examples based on thousands of open-source projects.
qwen3-coder
Alibaba's powerful open-source model (Unsloth optimized). Capable of handling huge monorepos with massive context windows. Run it locally or on private cloud.
refact.ai
AI coding assistant specialized in refactoring and technical debt reduction. Can run on local or remote models, emphasizing privacy and code quality.
goose
Open-source AI agent that runs locally for improved privacy and control.
wispr flow
AI dictation app that turns speech into polished text in any text field, with auto-edits and voice commands.
Related Articles
Vibe Kanban Review 2026: Open Source Now, Company Gone
Vibe Kanban review after the April 2026 shutdown: what still works locally, what cloud features are gone, and whether the open-source project is worth installing.
DeerFlow Review 2026: Is ByteDance's Open-Source SuperAgent Worth Self-Hosting?
Honest DeerFlow 2.0 review covering architecture, Docker sandbox execution, pricing (free), CrewAI comparison, local Ollama setup, and who should actually self-host this SuperAgent framework.
OpenClaw Guide 2026: Install, Configure, and Run a Self-Hosted AI Agent
OpenClaw setup guide for v2026.3.23: prerequisites, one-liner install, model and messaging app configuration, cost breakdown, and troubleshooting for common 2026 issues.
OpenClaw on a VPS: The Self-Hosting Guide for Non-DevOps People 2026
Step-by-step guide to self-hosting OpenClaw on a VPS. Covers Hetzner, Oracle Cloud, DigitalOcean, and Linode with Ubuntu 22.04 setup commands, security hardening, and HTTPS configuration.
OpenClaw Beginner's Guide 2026: Set Up Your Own 24/7 AI Agent from Scratch
Step-by-step OpenClaw setup guide for beginners. Deploy on a VPS, connect Telegram, add Google Workspace, configure security and model routing – no code required.
How Much Does OpenClaw Actually Cost? The Real Pricing Breakdown (2026)
Real OpenClaw costs broken down: VPS hosting, API tokens by model, routing strategies, and total monthly spend from $6 to $200 by use case.