forgegod

Name: forgegod
Author: waitdeadai

waitdeadai April 2, 2026

3 copies 0 downloads

Autonomous coding agent with web research (Recon), adversarial plan debate, 5-tier cognitive memory, multi-model routing (Gemini + DeepSeek + Ollama), 24/7 loops, and $0 local mode. Apache 2.0.

Agent Definition

<p align="center">
  <a href="README.md"><img src="https://img.shields.io/badge/lang-en-blue.svg" alt="English"></a>
  <a href="README.es.md"><img src="https://img.shields.io/badge/lang-es-yellow.svg" alt="Español"></a>
</p>

<p align="center">
  <img src="docs/mascot.png" alt="ForgeGod official mascot" width="120" />
</p>

<p align="center">
  <sub>Official mascot design by <a href="https://www.linkedin.com/in/matt-mesa/">Matias Mesa</a>.</sub>
</p>

<h1 align="center">ForgeGod</h1>

<p align="center">
  <strong>The coding agent that runs 24/7, learns from its mistakes, and costs $0 when you want it to.</strong>
</p>

<p align="center">
  <a href="https://pypi.org/project/forgegod/"><img src="https://img.shields.io/pypi/v/forgegod?color=00e5ff&style=flat-square" alt="PyPI"></a>
  <a href="https://github.com/waitdeadai/forgegod/blob/main/LICENSE"><img src="https://img.shields.io/badge/license-Apache%202.0-00e5ff?style=flat-square" alt="License"></a>
  <a href="https://www.python.org/"><img src="https://img.shields.io/badge/python-3.11+-00e5ff?style=flat-square" alt="Python 3.11+"></a>
  <a href="https://github.com/waitdeadai/forgegod/actions"><img src="https://img.shields.io/github/actions/workflow/status/waitdeadai/forgegod/ci.yml?style=flat-square&color=00e5ff" alt="CI"></a>
  <a href="https://forgegod.com"><img src="https://img.shields.io/badge/site-forgegod.com-00e5ff?style=flat-square" alt="Website"></a>
  <a href="docs/AUDIT_2026-04-07.md"><img src="https://img.shields.io/badge/audit-2026.04.07-00e5ff?style=flat-square" alt="Audit"></a>
</p>

<p align="center">
  <code>23 built-in tools</code> &bull; <code>8 LLM providers</code> &bull; <code>5-tier memory</code> &bull; <code>24/7 autonomous</code> &bull; <code>$0 local mode</code>
</p>

---

ForgeGod orchestrates multiple LLMs (OpenAI, Anthropic, Google DeepSeek, Ollama, OpenRouter, DeepSeek, Kimi via Moonshot, and Z.AI GLM) into a single autonomous coding engine. It routes tasks to the right model, runs 24/7 fr

Comments

More Agents

View all

hybrid-model-workflow

HAL 分层混合模型工作流 — 强模型(Claude)负责理解/拆解/验收，低成本模型(DeepSeek)负责检索/提取/清洗。Hermes Agent skill。

ph4ble

Dynamic-Review-Agent

An LLM agent fine-tuned on DeepSeek for spaced repetition, dynamically integrating knowledge points based on the Ebbinghaus forgetting curve.

1838177

StellarOS-Watch

基于 STM32F103 构建的端到端 AI 智能手表生态。自研“零重定位”原生机器码动态加载引擎与页面栈式 UI 框架；集成生产级 OTA 回滚保护机制与高带宽（921600 baud）串口协议栈。通过 Node.js 中继实现 DeepSeek AI 语义控制及 ASRPRO 语音全双工交互，是一个集成了分布式计算、现代存储管理与 AI Agent 的嵌入式全栈工程。

chenshuang888