Self-hosted alternatives to Runner
200 self-hosted apps like Runner, closest match first.
Top picks
- C
Codeg
LaunchCodeg is a multi-agent coding workspace. It aggregates sessions from several coding agents, including Claude Code, Codex, OpenCode, Pi and Grok Build, so you can run the agents you use together in one place and keep work moving on each scre
FreeOpen sourceSelf-hosted
- O

OpenAgentd
LaunchOpenAgentd is an open-source desktop app that runs a coding agent on your own machine. You give it a task in a real repository, and it works through the steps while you watch. Each file read, patch, shell command and todo appears as it happ
FreeOpen sourceSelf-hosted
- O
ORG-2
LaunchOpen-source workspace that runs 20+ AI coding agents and records every session as a replayable trajectory. Replay any session, review as a team, and trace every line back to the decision behind it.
FreeOpen sourceSelf-hosted
- R
Refact AI
LaunchAI Agent for Coding - Refact.ai adapts to your workflow, automating coding, debugging, and testing with full context awareness. An open-source alternative to Cursor and Copilot, Refact.ai can be deployed on-premise.
FreeOpen sourceSelf-hosted
- 4
49-IDE
LaunchOpen-source 2D IDE for managing AI agents in native CLIs, terminal, gits, beads issues, and files across multiple projects and machines. Self-host on a single machine via localhost OR host on a cluster via Tailscale OR connect to app.49agen
FreeOpen sourceSelf-hosted
- M
Moyai
LaunchMoyai is a self-hosted AI workspace for coding and connected-service tasks. You chat with an agent, steer its work, answer its questions, inspect the computer it works on, and keep the files and history that result. The agent is built with
FreeOpen sourceSelf-hosted
More like Runner
About Runner
Runner
Coding Agent
Runner is a coding agent for professional software developers, built as a standalone editor rather than a fork of VS Code. It is designed around specs: you and the agent write a spec together and you approve it before any code is written. Once a task has been specced out, Runner writes the code and verifies the changes autonomously, and you approve the result at the end, following a plan, code and review flow. The site says Runner uses frontier models with a large amount of context about your codebase, and that it does not cut token usage or switch to cheaper models to hit a price. It also has features to help you understand code faster, because the bottleneck becomes reading what the agent produced. The site links a two-minute demo, a user guide, a spec-driven development introduction and a Discord community. Releases are published on GitHub.
- Category
- Developer Tools
- Website
- runnercode.com


