Agents Studio is a self-hosted app for developers who want Claude Code to work on their repositories while they're away. It runs on your machine, with browser and terminal interfaces, and supports macOS and Linux. The software is open source under the MIT license. Claude Code must be installed and signed in; sessions can also use Cursor's signed-in agent.
Work can start on a schedule or in response to GitHub events, such as an opened pull request or a failed CI check. Each session gets its own branch and checkout. The app runs your project's tests, blocks merges when checks fail, and can ask the agent to repair failures within a limit you choose. Scheduled jobs retry genuine failures and pause after repeated unsuccessful runs. Spend controls can hold back unattended work, while rate-limit handling can defer runs or switch agents.
You can review activity across repositories, see costs and answer requests that need your decision. A built-in file editor, shell and app preview let you finish changes in the same interface. A merge queue orders completed branches with their dependencies in mind. The library also manages Claude Code agents, skills, commands, plugins and MCP servers.
Configuration and work remain ordinary files and Git branches on your machine. Local hosting doesn't replace the signed-in AI services used by the agents. Optional Slack integration sends reports and lets your own replies in a direct message start sessions on the local runner. Those sessions leave merging and pushing to your approval. Proposed project rules appear as file diffs that you can accept or decline.
Claim this page and we'll verify you by hand. Agents Studio gets the verified badge, and you can upgrade the listing to be featured on localhosted. Proud to be listed? Put our badge on your site.
Want more people to find Agents Studio?Promote it
Something wrong or outdated on this page?
106Updated 2 weeks ago
macOS · Windows · Linux · Web#Agent Skills#Code execution#Git integration
Albert coordinates Claude Code agents for developers who want to hand off a coding goal across several tasks. Its harness and dashboard run locally on Windows, macOS or Linux, and it requires an installed, signed-in Claude Code account. It assigns work to Haiku, Sonnet or Opus according to the task and continues until the goal is complete or it reaches a requested review checkpoint.
41KUpdated 15 hours agoMIT
macOS · Windows · Linux · Android · Docker · Web#Agent Skills#Code execution#Human approval
4.4KUpdated 1 day agoMIT
macOS · Windows · Linux · Web · JetBrains#Agent Client Protocol#Code execution#Git integration
28.3KUpdated 13 hours agoApache-2.0
macOS · Windows · Linux · Web · VS Code · JetBrains#Code execution#Git integration#MCP
294Updated 3 hours ago
macOS · Windows · Linux · Web#Agent Skills#Batch processing#Code execution
Ringer runs parallel AI coding agents on your machine and checks their output by executing tests or other validation commands. It's for developers who want to delegate implementation while keeping planning and review with a stronger model. The aim is to reduce model spending on routine coding work without relying on workers' claims that they're finished.
195Updated 7 months agoMIT
macOS · Windows · Linux · Web#Agent Skills#Code execution#Guardrails
Codewhale is a coding agent that runs on your computer and works with a model you choose. It's for developers who want help understanding a project, fixing bugs or automating repeated work, with control over the agent's access to files and commands. The open-source project uses the MIT license and is written in Rust.
gptme is a self-hosted AI agent that works directly in your terminal, with access to your files and installed tools. It's for developers who want a coding assistant in their own environment, and people who want an agent for data analysis or other knowledge work. The software is free under the MIT license and doesn't require a gptme account.
Qwen Code is an Apache 2.0 licensed AI coding agent for developers who want help working through a codebase, changing code and checking the result. It runs on macOS, Windows and Linux, with a terminal interface and a desktop app. It builds on Google Gemini CLI and has developed into an agent that can use Qwen models alongside other model providers.
VibeHQ Hub coordinates separate Claude Code, Codex and Gemini CLI agents on your own computer. It's for developers assigning parts of a project to multiple coding assistants who need agreement on interfaces, dependencies and deliverables. The hub runs locally. It's open source under the MIT license, with tested Windows and macOS support; some Linux components remain untested.