Multi-agent system for software development

A free, open-source coding agent inside VS Code.

Put Claude Code, Cursor, Codex, Gemini & Antigravity in one room — real-time multi-agent AI collaboration over MCP for distributed dev, code review, PR handoff & frontend↔backend integration. Free, self-hostable, MCP-native.

The design layer for agentic AI — design context, interface checks, and verification for coding agents.

Costrict - strict AI coder for enterprises, quality first, including AI Agent, AI CodeReview, AI Completion.

An open-source AI coding agent that lives in your terminal.

Lightweight coding agent written in Rust, optimized for memory footprint and performance

Claude Code skill for OWASP security best practices (2025-2026). Includes Top 10:2025, ASVS 5.0, Agentic AI security, and 20+ language-specific security quirks.

Collaborative multi-agent AI coding workspace: aggregate sessions from Claude Code, Codex, OpenCode, Pi, Grok Build, etc. Desktop app, self-hosted server, or Docker.

A structured 3-agent AI dev team — Architect, Builder, Reviewer. Built from production use. Token-optimized. Works with Claude Code, VS Code, Cursor, and any AI that supports context files.

The graph based agentic IDE

A Socratic supervision layer for AI coding agents.

Automated quality checks that nudge AI coding agents toward better habits

Turn tracker tickets into autonomous agent sessions

Instant recall for coding agents. Search the history already on your machine. Git blame, but for agent sessions.

AI-powered multi-agent code review. Simulates a customizable team of Engineers performing code review with built-in discourse.

FuXi is a fast, self-contained AI coding agent that lives in your terminal — edit code, run commands, and drive tools, with cost-aware routing across LLM providers.

100% Rust implementation of code graphRAG with blazing fast AST+FastML parsing, surrealDB backend and advanced agentic code analysis tools through MCP for efficient code agent context management

Run Claude Code, Codex & Gemini in parallel on Windows & macOS — git worktree fan-out with atomic hunk adoption, approval gates, reboot-surviving sessions

Tool-agnostic 13-phase AI development pipeline — turns a task description into reviewed, committed code through automated design, adversarial review, security, test, and code-review gates. One bash engine, balanced Opus/Sonnet routing, self-healing commit review.

AI Agent Orchestrator for Claude Code

Agentic development harness for Claude Code — SPEC-driven plan/run/sync, TRUST 5 quality gates, model+effort routing, and Claude×GLM multi-LLM cost control. Single Go binary, 16 languages, zero deps.

A dev environment for AI agents.

Bring Claude Code to Visual Studio 2026: A native diff with accept/reject, a live debugger Claude can drive autonomously, Roslyn code navigation, and Test Explorer integration. The IDE half of Claude Code's integration protocol. Community-built, unofficial.