Autoloom – tinyloom을 기반으로 구축된 자율 AI 에이전트
hackernews
|
|
📦 오픈소스
#tinyloom
#tui
#격리 환경
#경량화
#자율 ai 에이전트
원문 출처: hackernews · Genesis Park에서 요약 및 분석
요약
Autoloom은 tinyloom 기반의 초경량 자율 AI 에이전트로, 핵심 라이브러리는 약 900줄로 구성되어 있으며 셸 명령 실행과 파일 편집 기능을 제공합니다. 사용자는 cron을 통해 작업을 관리하고 웹훅 서버를 활용할 수 있으며, PyPI 또는 소스를 통해 설치할 수 있습니다. 다만, 루트 기기에서 실행 시 시스템 손상 위험이 있어 반드시 컨테이너나 마이크로VM 같은 격리된 환경에서만 실행해야 합니다.
본문
Join Discord -- Website: thresher.sh Autoloom is a tiny self-learning autonomous agent wrapper built on top of tinyloom . The core runtime is only about ~225 lines of code. The entire core library is ~900 lines of code and the entire plugins and all is about ~1500 lines of code. It keeps its state in ~/.autoloom , uses plain files for sessions/tasks/memories, manages heartbeat runs with cron, and ships a minimal Textual TUI plus a small webhook server. Autoloom inherits tinyloom's ability to run shell commands and edit files. It is not a sandbox by itself. If you want isolation, run it inside a container or microVM. See the sandbox docs below. If you run it on your root machine you risk destroying it, do not run it outside an isolated environment. You have been warned! End user (after the first PyPI release): uv tool install autoloom # or pip install autoloom autoloom setup Developer (from source): git clone cd autoloom uv sync --extra dev End-user examples in this README use autoloom directly. Developers should prefix with uv run (e.g. uv run autoloom setup ). autoloom setup autoloom autoloom "review pending work and update tasks" autoloom heartbeat run autoloom webhook serve Update your heartbeat: tinyloom "update my heartbeat.md with ... " Create a new scheduled task: tinyloom "create a new cron job with and launch yourself on that cron job for a task of " Autoloom stores its data in: ~/.autoloom/SOUL.md ~/.autoloom/heartbeat.md ~/.autoloom/tasks/ ~/.autoloom/skills/ ~/.autoloom/knowledgegraph/memories/ ~/.autoloom/sessions/ autoloom opens the TUIautoloom "..." runs a persisted headless session and streams JSONL eventsautoloom setup walks an interactive setup that configures agent identity, model provider/credentials/tuning, safety limits, compaction, heartbeat schedule, plugins, and webhook — the API key is written to~/.autoloom/.env , neverconfig.yaml autoloom heartbeat run executes one heartbeat sessionautoloom cron install|show|remove manages the heartbeat cron blockautoloom webhook serve runs the local-first webhook server - Getting Started - State and Heartbeats - Self-Learning - Plugins - Webhooks - Design Decisions - Docker Sandbox Guide - Podman Sandbox Guide - microsandbox Guide - Kata Containers Guide - Docker Sandbox microVM Guide uv run ruff check uv run pytest I have a autoloom that is running ever 10 minutes in a vps. It's goal is to research popular trends and identify plugins for tinyloom or autoloom and then plan, implement, and test them. it... just... works... It's ran for 24 hours and it's built 15 plugins... all passing tests... Now a lot of them are throw away... but this is with one line of "direction". After starting up, the TUI detected that git was missing, so it automatically installed it before proceeding to clone repositories. Within two heartbeat cycles, it cloned the repo, began planning plugins, and started building its own knowledge graph. The system self learns, self directs, and has full autonomy.
Genesis Park 편집팀이 AI를 활용하여 작성한 분석입니다. 원문은 출처 링크를 통해 확인할 수 있습니다.
공유