Skillget

am-agi

agent
Security Audit
Fail
Health Warn
  • No license — Repository has no license file
  • Description — Repository has a description
  • Active repo — Last push 0 days ago
  • Low visibility — Only 5 GitHub stars
Code Fail
  • process.env — Environment variable access in agent/src/adapters/nextjs-loop.ts
  • process.env — Environment variable access in agent/src/adapters/nextjs.ts
  • process.env — Environment variable access in agent/src/board-project-data.test.ts
  • network request — Outbound network request in agent/src/board-project-data.test.ts
  • process.env — Environment variable access in agent/src/claude/invoke.ts
  • exec() — Shell command execution in agent/src/exec.ts
  • process.env — Environment variable access in agent/src/exec.ts
  • process.env — Environment variable access in agent/src/git/commit.e2e.test.ts
  • process.env — Environment variable access in agent/src/git/commit.test.ts
  • process.env — Environment variable access in agent/src/loop/adapter.ts
Permissions Pass
  • Permissions — No dangerous permissions requested
Purpose
This project is an autonomous AI agent system designed to manage and execute software project tasks. It uses a local Kanban board for tracking work and performs git-based execution to automatically push code changes.

Security Assessment
Overall risk: High. The agent is designed to autonomously execute real work on your local machine. The codebase relies heavily on shell command execution (`exec()`), which gives it the potential to run arbitrary system commands. It also makes outbound network requests and reads environment variables, likely to interact with external APIs (like the mentioned Claude integration). While there are no hardcoded secrets in the code, piping a remote install script directly to bash (`curl ... | bash`) is a risky setup method that requires manually reviewing the script beforehand.

Quality Assessment
The project is active, with recent pushes and clear documentation. However, the community footprint is extremely small, with only 5 GitHub stars. The README currently features a prominent warning that the tool does not work at the moment due to a broken integration. Additionally, there is a contradiction in the project quality: the documentation claims an MIT license via a badge, but the repository actually lacks a formal license file, leaving its legal status unclear.

Verdict
Not recommended — it is currently broken, inherently risky due to autonomous shell execution, and lacks the maturity of a formal open-source license.
SUMMARY

AM — autonomous AI agent system. The agent does the work and ships the PR. ⭐ Star to follow along.

README.md

CLAUDE CUT EVERYONE OFF. I AM WORKING ON A NEW INTEGRATION. THIS DOESNT WORK AT THE MOMENT!

🚀 AM — Not just another AI, an AI with a kanban, calendar, and more!

GitHub Repo stars
GitHub forks
GitHub release (latest by date)
Project Maintenance
Top Language
MIT License

If this is useful to you — ⭐ Star the repo. It costs nothing and helps more people find it.

AM - The AI that doesnt just plan, it executes

helloam.bot hero screenshot

AM - The local AI agent with a Kanban board for a brain

AM Board

AM - Perfect for scheduling future content and tasks

AM Calendar

The AM kanban board — every task tracked, every transition gated, future work scheduled, auto de-slop - and long and short term memory with nightly reflection!

Table of Contents

What it actually does

AugmentedMe is a digital worker that doesn't forget you exist between sessions. Not Siri. Not Alexa. Those are stateless magic 8-balls. This is an agent that owns outcomes — short + long-term memory on your own hardware, a Kanban state machine that tracks what's happening and what's blocked, and a git-based execution loop where every action is a traceable commit, not a vibe.

It manages real work: software projects, content, home logistics, research. The parts of your life that need a system but nobody ever built a real one for.

Features

  • 🧠 Persistent memory — short-term context + long-term embeddings, stored locally
  • 📋 Kanban state machine — gated transitions, explicit task status, nothing moves implicitly
  • 🔄 Git-driven loop — every step is an auditable commit; no black boxes
  • 🌍 Cross-platform — Mac, Linux (systemd/OpenRC/runit), and Windows (Task Scheduler)

How you get started

Mac / Linux:

curl -fsSL https://raw.githubusercontent.com/augmentedmike/am-agi/main/install.sh | bash

Windows:

irm https://raw.githubusercontent.com/augmentedmike/am-agi/main/install.ps1 | iex

Both installers clone the repo, install all dependencies, build the board, register background services, and open http://localhost:4220 when ready. Sign in with your Anthropic account in the onboarding flow and create your first card.

Dog-Fooding

You use Claude Code to bootstrap the first few steps:

source ./init.sh
# follow steps/1.md → steps/2.md → steps/3.md

After step 3, AM does the rest. We find bugs before you do because we build the product with the product.

Architecture

Three things. That's it.

1. Memory — Short-term context + long-term embeddings. Stored locally. Traceable. Inspect every vector if you want to.

2. State — Kanban-driven. Every task has an explicit status. Transitions are gated. Nothing implicitly moves.

3. Loop — One-shot iteration per worktree. Commit. Merge. Repeat. If you can't trace the execution, the execution is wrong.

Docs:

Philosophy

Claude Code is the incubator, and after step 3 it becomes just a tool in AM's toolbelt. AM is the intelligence, the persistence, the memory, the "being" — Anthropic or other models are just those random thoughts in your own head. They aren't YOU.

AM is a cognitive architecture, not just random thoughts. A mix of engineering (creating analogs for brain regions) and research.

I got tired of agents that do things I didn't ask for. So I rewrote it.

This is the real system — not a demo, not a toy, not another LangChain wrapper with a readme that promises AGI. Memory lives on your machine. Inference goes out over HTTPS. Every state change is a git commit. You can read all of it in an afternoon.

Acknowledgements

Built on ideas from:

  • Ken Thompson · John McCarthy · Jim Weirich
  • Richard Sutton · Yann LeCun
  • Andrej Karpathy · George Hotz

Contributing

We welcome humans and well-behaved AI agents. See Contributing Guide.

Help wanted:

License

MIT © augmentedmike

中文简介 | Chinese (简体)

AM（AugmentedMe）是一个真正的个人 AI 智能体系统。 不是框架。不是 SaaS。不是 LangChain 包装器。

这是一个真实运行在生产环境中的系统，完全开源，代码可在下午读完。

特性 说明
🧠 持久记忆 短期 + 长期记忆，存储在本地，数据属于你
📋 看板状态机 每个任务有明确状态，转换有门控，执行可追溯
🔄 Git 驱动循环 每一步都是可审计的提交，没有黑盒
🌍 全平台支持 Mac / Linux / Windows 均支持，非 Mac 独占
💰 低成本可选 支持 DeepSeek、Kimi、Qwen 等中国模型——参与贡献

中文用户专区：
🌏 中文本地化讨论 · 🤖 寻求帮助：支持中国模型 · 📌 发帖前请阅读

⭐ 如果觉得有用，请 Star 支持我们！Star 是我们了解有多少人在关注的重要信号。

Reviews (0)

No results found