waishnav/devspace

Minimal Coding Agent Harness on MCP for ChatGPT, Claude, Hermes, Grok Bot, OpenClaw

View on GitHub ↗Jump to charts ↓Open shareable report

Summary Information

Updated 58 minutes ago
Added to GitGenius on September 14th, 2026
Created on June 14th, 2026
Open Issues & Pull Requests: 66 (+2)
GitHub issues: Enabled
Number of forks: 540
Total Stargazers: 4,750 (+5)
Total Subscribers: 6 (+0)

Repository Insights (GitGenius)

Median issue/PR response: 18.3 hours
Mean response time: 2.7 days
90th percentile: 7.9 days
Tracked items: 67

Most active contributors

Sign in to see contributor activity.

How this project is maintained

Around half of the issues opened in the past year never receive a reply. 95% of open issues come from outside the core team, so the backlog reflects real-world use rather than internal planning. Only 14% of issues opened in the past year have been closed. Three people close 86% of everything that gets resolved.

Charts & Analytics

Fetching additional details & charts...

Issue Activity (beta)

Open issues: 21
New in 7 days: 7
Closed in 7 days: 4
Avg open age: 20 days
Stale 30+ days: 3
Stale 90+ days: 0

Recent activity

Opened in 7 days: 3
Closed in 7 days: 4
Comments in 7 days: 0
Events in 7 days: 0

Top labels

  • bug (3)
  • good first issue (2)
  • help wanted (2)
  • Discussion and Experimentation (1)
  • enhancement (1)

Detailed Description

DevSpace is a self-hosted MCP server that brings Codex-style coding workflows to ChatGPT and other AI agents.

The tool solves the problem of giving AI assistants secure access to your local codebase and development environment without uploading files to third-party services. It works by running as an MCP server on your machine, exposing a controlled endpoint through a reverse proxy tunnel you manage, and requiring password approval for each client connection. This lets ChatGPT or other coding agents read, edit, search, and execute code in your real projects using only tools and files on your own system.

DevSpace suits developers who want to use ChatGPT as a coding assistant while keeping their source code local and private. It works for both direct ChatGPT integration and as a backend for coding agents that delegate work through it. The setup process distinguishes between where you invoke DevSpace from and which agents it may use as subagents, allowing flexible configurations for different workflows. For ChatGPT users, you specify which local project folders are accessible and provide a public HTTPS URL from a tunnel service of your choice. For coding-agent-only setups, it operates against the current Git project or directory without requiring tunnel configuration.

The project maintains active CI automation and publishes to npm. Development activity shows consistent attention to protocol compatibility, including automatic support for both current and older MCP protocol versions through stateless handling at a single endpoint, with no manual configuration required.