Local, headless pull-request system for agent-to-agent code review workflows
AI agent code quality guardrails — ESLint, Prettier, and Stylelint unified config
Sandboxed agent runtime for Roomy. Spawns and manages Docker containers that execute agent code in isolation.
Local microVM sandboxes for agent code
Stateful MCP server for the kensai multi-agent code review pipeline
Embeddable AI coding agent built on @cuylabs/agent-core
Review AI agent code changes before commit
Agent code templates for the AgentLaunch platform
Mikey Pro Ruff configuration - AI agent code quality guardrails for Python
Configurable audit tool and linter for AI-generated code
Turn a function into an `http.Agent` instance
Policy enforcement and rollback for AI agent code edits
Scan TypeScript AI agent code for unguarded tool calls. Reports every function with side effects and shows which ones have no checks.
Curated agents, skills, and commands for the OpenCode AI coding CLI — autonomous orchestrator, multi-agent code review, model fallback, and in-session asset creation tools.
Automated security auditing for AI agent code - quarantine-first scanning for pip, npm, git repos, and MCP servers
Core review engine for GHAGGA — AI-powered multi-agent code reviewer
An HTTP(s) proxy `http.Agent` implementation for HTTP
Ai tool for Agent Code Execution
Maps proxy protocols to `http.Agent` implementations
An HTTP(s) proxy `http.Agent` implementation for HTTPS
ESLint plugin that guards AI-agent-written TypeScript against common sloppy patterns: async/Promise/.then chains, bare catches, unsafe casts, raw SQL, manual enum casts, mocks in integration tests, and hardcoded secrets.
Pi package that automatically queues a read-only code review after agent code changes.
GitHub Copilot Coding Agent preToolUse hook — scans every tool call through Interven before execution. Allow/deny enforcement with no agent code change.
A SOCKS proxy `http.Agent` implementation for HTTP and HTTPS
An AI-powered coding agent for the terminal, written in pure Rust
DEPRECATED: This crate has been renamed to agent-code. Install with: cargo install agent-code
DEPRECATED: This crate has been renamed to agent-code. Install with: cargo install agent-code
Agent engine library: LLM providers, tools, query loop, memory
claw CLI agent (cargo-binstall ready) — built from ultraworkers/claw-code
A CLI for keeping focus across agent-driven context switches
Codex agent plugin for the ao-rs orchestrator
OpenAI Codex agent provider for CIAB
Miyabi CodeGen Agent - AI-driven code generation with LLM integration
Codex provider for Nucel agent-sdk — subprocess wrapper for OpenAI codex CLI
A light weight agent that leverages the Carmen gem to derive a state code given the name of a country and region.
AgentHarness provides a unified interface for CLI-based AI coding agents like Claude Code, Cursor, Gemini CLI, and others. It offers full orchestration with provider switching, circuit breakers, health monitoring, flexible configuration, dynamic provider registration, and token usage tracking.
A minimal coding agent supporting Ollama, Anthropic, OpenAI, and VertexAI.
Production-grade coding agent with tool execution, middleware pipeline, context compaction, session persistence, and multi-provider LLM support.
Interactive command-line interface for the Brute coding agent. Supports single-prompt, interactive, piped, and session modes.
ClaudeAgent is a Ruby SDK for building autonomous AI agents that interact with Claude Code CLI. It provides both simple one-shot queries and interactive bidirectional sessions with support for tool use, hooks, permissions, and in-process MCP servers.
CodeAct provides Think-Code-Observe agents that synthesize and execute Ruby code dynamically. Ship DSPy.rb workflows that write custom Ruby code while tracking execution history, observations, and safety signals.
Lightweight gem, tested in large Rails codebases (20k+ Ruby files). Allows AI assistants to evaluate and verify rails/ruby code changes securely at lighting-speed access without the need to restart server or run bundler.
Genie CLI is a command-line tool that brings Test Driven Development (TDD) principles to life by integrating with a large language model (LLM) through the ruby_llm library. It provides an interactive session to write tests, implement code, and manage your codebase.
An AI-powered CLI coding assistant specialized for Ruby and Rails, featuring a 16-layer agentic architecture, local SQLite persistence, and Claude OAuth.
Aircana generates distributable Claude Code plugins with specialized agents backed by Confluence and web knowledge sources. Includes manifest-based knowledge tracking, ERB template generation, and team collaboration features.
Rack app exposing the Brute agent over HTTP with JSON and SSE streaming endpoints. Deploy with Falcon.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.