darrenhinde/openagentscontrol

AI agent framework for plan-first development workflows with approval-based execution. Multi-language support (TypeScript, Python, Go, Rust) with automatic...

View on GitHub ↗Jump to charts ↓Open shareable report

Summary Information

Updated 52 minutes ago
Added to GitGenius on September 14th, 2026
Created on August 14th, 2025
Open Issues & Pull Requests: 67 (+0)
GitHub issues: Enabled
Number of forks: 397
Total Stargazers: 4,850 (+0)
Total Subscribers: 39 (+0)

Repository Insights (GitGenius)

Median issue/PR response: 17.1 hours
Mean response time: 7.2 days
90th percentile: 13.4 days
Tracked items: 107

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. 79% of open issues come from outside the core team, so the backlog reflects real-world use rather than internal planning. Work labelled "documentation" is answered fastest, typically in about 7 hours, while "enhancement" waits about 36 hours. Only 10% of issues opened in the past year have been closed. Three people close 83% of everything that gets resolved.

Charts & Analytics

Fetching additional details & charts...

Issue Activity (beta)

Open issues: 38
New in 7 days: 1
Closed in 7 days: 0
Avg open age: 184 days
Stale 30+ days: 27
Stale 90+ days: 23

Recent activity

Opened in 7 days: 1
Closed in 7 days: 0
Comments in 7 days: 0
Events in 7 days: 1

Top labels

  • bug (32)
  • documentation (32)
  • automated (31)
  • enhancement (11)
  • feature (11)
  • framework (9)
  • idea (5)
  • priority-high (5)

Detailed Description

OpenAgentsControl is an AI agent framework that enforces plan-first development workflows with human approval gates before code execution.

The framework addresses the problem of AI agents generating generic, inconsistent code that requires extensive rework. Most AI coding assistants lack context about a project's specific patterns, architecture, and standards. OpenAgentsControl solves this by loading project-specific coding patterns into agents before generation, enabling them to produce code matching the team's conventions from the start. The approach works through a propose-approve-execute cycle: agents generate a plan for review, await human approval, then execute incrementally with validation. The tool emphasizes token efficiency through minimal viable information design, loading only necessary context when needed.

Developers should consider OpenAgentsControl if they work in teams that need consistent code generation across multiple developers or if they want to reduce rework from AI-generated code. It suits projects where coding standards and architectural patterns are important and should be enforced consistently. The framework supports multiple languages including TypeScript, Python, Go, Rust, and C#, and works with various AI models including Claude, GPT, Gemini, and local models, avoiding vendor lock-in. A distinguishing feature is that agents are editable through markdown files rather than being baked-in plugins, giving teams direct control over agent behavior without compilation or vendor constraints. The tool is built on OpenCode, an open-source AI coding framework, and extends it with specialized agents and team workflows.

Development activity shows consistent engagement with the codebase through regular commits addressing both features and bug fixes. The project maintains active issue tracking and responds to community contributions. Documentation includes a roadmap and community resources, indicating ongoing planning and stakeholder communication. The maintainer actively develops new capabilities while keeping the core framework stable.