Havuz

Zero-modification Human-in-the-Loop adapter for OpenOPC's agentic DAG runtime.

Markdown-first orchestration for 71 specialists across Codex, Claude, Gemini, and Grok. Chrono coordinates scoped tasks in isolated git work

Build for agents — from the AI Gateway to the entire application stack.

Run DeepSeek as a real sub-agent inside Claude Code / Codex CLI — with its own 7-tool agent loop, workspace-scoped file access, and bounded

El objetivo de Polaris es tener el mejor sistema agéntico para trabajar con mi diagnóstico.

Open-source dynamic multi-agent workflows for AI coding agents - the script-as-orchestrator engine behind Claude Code dynamic workflows & ul

Loop engineering for software development. Turn any repository into a self-organizing AI engineering team — 8 specialists, contract-driven,

🤖 LLM Engineering Roadmap — Complete Developer Guide

Local-first workspace for Claude Code and OpenAI Codex agents. Durable sessions, projects, scheduling, goals, and native MCP/tool/skill inte

Model router for AI coding agents: routes routine work to cheaper models with routing rules, 8 subagents, hooks and a CLI runner

🏛️ Autonomous Multi-Agent CLI Orchestrator — Bring Claude Code, OpenAI Codex, Cursor Agent, xAI Grok & Google Antigravity into one terminal

Adaptive Human-Agent Teaming (HAT) & Smart Company (SmC) Infrastructure This repository implements a Human-Model-Free adaptive agent archite

🚀 Multi-agent orchestration for Qwen Code CLI. 24 specialized AI agents and 82+ skills working as a professional dev department. Built for A

Discontinued. Succeeded by OpenCognit Desktop — every coding agent in one window → opencognitos.github.io

The orchestration layer under your coding agent. Turns work into a typed graph, runs one model per node, and takes the verdict from outside

Prove an AI-written fix actually fixes the bug. mini-ork certify reproduces the bug against your repo's own code, attacks the patch with gen

Open-source AI agent that reasons by blending many AI models, does real work on its own, and keeps learning — safe, self-hostable, and fully

Beastmode: MofA (Mixture of Agents) orchestration framework for Hermes/OpenClaw/Codex with MemroOS-style context continuity.

Claude doesn't do its own stunts. Plan with Claude, execute with a near-free model, review with Claude — a delegation harness for Claude Cod

Open-source Fugu: the open-source LLM orchestration brain.

Development workflows for Codex that keep technical rigor and edge-case handling from becoming product overengineering.

Claude Code skill + subagent for setting up guardrailed agentic loops (loop engineering): headless, evaluator-optimizer, meta/prompt-refinem

Local-first AI workflow orchestration for chaining models, agents, tools, and scripts into repeatable workflows.

Declare the outcome, skip the logic. The developer-first infrastructure engine for structured, multi-turn AI conversations with built-in saf

Claude as subagents in Codex — scoped workers, resumable sessions, git-ignored logs.

A self-hosted Slack/Telegram agent that extends itself by writing and deploying its own code at runtime.

Control plane plugin for Hermes Agent — pool many free/cheap model providers + local AI CLIs, switch brains from Telegram in one command (ev

A control loop that turns Codex subagents into a continuously refilled engineering team—with isolated workers, independent model review, hea

Production LLM call layer for AI agents and tools: keep OpenAI/Anthropic/AI SDK/LiteLLM, hot-swap models with MDA presets, and add cache, re

Production-grade Go SDK for building AI agents with long-term memory, knowledge retrieval, and voice — runnable as a library, a daemon, or a

AINL helps turn AI from "a smart conversation" into "a structured worker." It is designed for teams building AI workflows that need multipl

Local task queue & scheduler that squeezes Claude's 5-hour usage windows dry — and now any Anthropic-compatible subscription (Kimi Code, GLM

The open-source governance layer for AI agents: write the rules declaratively, Bernstein enforces them and produces the verifiable, replayab