Cette page est affichée en anglais. Une traduction française est en cours.
SkillsMay 12, 2026·2 min de lecture

Upsonic — Python Framework for Autonomous Agents

Upsonic offers a Python-first path to autonomous and traditional agents, prebuilt agents, and MCP tools for fast internal pilots.

Agent Toolkit
Agent Toolkit · Community
Prêt pour agents

Installation avec revue préalable

Cet actif nécessite une revue. Le prompt copié demande un dry-run, affiche les écritures, puis continue seulement après confirmation.

Needs Confirmation · 64/100Policy : confirmer
Surface agent
Tout agent MCP/CLI
Type
Skill
Installation
Single
Confiance
Confiance : Established
Point d'entrée
Asset
Commande avec revue préalable
npx -y tokrepo@latest install ffdbd41d-a2de-5554-a18f-1baa6cc7e338 --target codex

Dry-run d'abord, confirmez les écritures, puis lancez cette commande.

Introduction

Upsonic offers a Python-first path to autonomous and traditional agents, prebuilt agents, and MCP tools for fast internal pilots.

  • Best for: Python teams that want a lightweight SDK for autonomous agents with guardrails
  • Works with: Python, Anthropic/OpenAI-style models, workspace sandboxing, MCP tools, E2B sandbox providers
  • Setup time: 10-20 minutes

Practical Notes

  • Quant: the README positions prebuilt autonomous agents as ready-to-run assets, shortening time to first useful run.
  • Quant: path traversal and dangerous shell operations are explicitly blocked to the declared workspace boundary.

Rollout pattern

  • Start with one autonomous task that reads files or logs inside a disposable workspace.
  • Adopt prebuilt agents only after you inspect the prompt, tools, and initial message they package.
  • Add MCP tools and cloud sandboxes as separate steps so you can measure what each capability changes.

Watchouts

Because the framework makes it easy to move fast, teams should still review prebuilt agents and external tools instead of treating them as trusted defaults.

FAQ

Q: Is it only for autonomous agents? A: No. The README shows both AutonomousAgent and traditional Agent flows.

Q: What is the main built-in guardrail? A: Workspace-scoped file and shell operations with path-traversal and dangerous-command blocking.

Q: What is a good first use case? A: Internal log analysis or structured triage in a disposable workspace with one model and no external tools.

🙏

Source et remerciements

Source: https://github.com/Upsonic/Upsonic > License: MIT > GitHub stars: 7,846 · forks: 733

Fil de discussion

Connectez-vous pour rejoindre la discussion.
Aucun commentaire pour l'instant. Soyez le premier à partager votre avis.

Actifs similaires

Scrapy — Fast High-Level Web Crawling Framework for Python

Scrapy is the most battle-tested web scraping framework for Python. It handles concurrency, retries, throttling, cookies, and export pipelines — letting you write spiders that scale from one page to millions with the same code.

Skills
Script Depot

Kedro — Production-Ready ML Pipeline Framework for Python

Kedro is an open-source Python framework by McKinsey QuantumBlack that applies software engineering best practices to data science and ML pipelines. It provides a standardized project structure, data catalog, and pipeline abstraction that makes experimental code production-ready.

Skills
AI Open Source

Tornado — Python Async Web Framework and Networking Library

Tornado is a Python web framework and asynchronous networking library originally developed at FriendFeed (acquired by Facebook). Non-blocking I/O, WebSockets, long polling, and thousands of simultaneous connections. One of the earliest async Python web frameworks.

Skills
AI Open Source

Litestar — High-Performance Python ASGI Web Framework

Litestar is a powerful, flexible, and opinionated ASGI web framework for building modern Python APIs with class-based controllers, dependency injection, and automatic OpenAPI docs.

Skills
Script Depot
◈Accueil🔍Rechercher👤Moi