askmanu/acorn
LLM framework for long running agents
Provides structured I/O through Pydantic models with automatic tool schema generation, multi-turn agentic loops with dynamic tool management, and step callbacks for controlling execution flow. Built on LiteLLM for provider agnosticism, it supports streaming responses with partial structured updates, prompt caching for cost reduction, and branching workflows for parallel agent execution. Includes parse error recovery and automatic model fallback for high availability.
Used by 7 other packages. Available on PyPI.
Stars
7
Forks
—
Language
Python
License
MIT
Category
Last pushed
Feb 25, 2026
Monthly downloads
640
Commits (30d)
0
Dependencies
3
Reverse dependents
7
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/agents/askmanu/acorn"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
InfinitiBit/graphbit
GraphBit is the world’s first enterprise-grade Agentic AI framework, built on a Rust core with a...
autogluon/autogluon-assistant
Multi-Agent System Powered by LLMs for End-to-end Multimodal ML Automation
samholt/L2MAC
🚀 The LLM Automatic Computer Framework: L2MAC
pguso/agents-from-scratch
Build AI agents from first principles using a local LLM - no frameworks, no cloud APIs, no...
wjayesh/mahilo
mahilo: Multi-Agent Human-in-the-Loop Framework is a flexible framework for creating multi-agent...