Back to browse
GitHub Repository

LLM framework for long running agents

7 starsPython

acorn – LLM framework for long running agents

by onel·Feb 24, 2026·5 points·0 comments

AI Analysis

MidShip ItSlick

Yet another LLM orchestration layer over LiteLLM + Pydantic when DSPy and LangChain dominate.

Strengths
  • Structured I/O with Pydantic schema validation reduces parse errors
  • Step callbacks and streaming support give fine-grained loop control
  • Provider fallback and prompt caching reduce cost/latency at runtime
Weaknesses
  • Feature parity with LangChain/LangGraph/DSPy without clear differentiation
  • Early project (2 stars, 2 issues)—no production validation or examples beyond HuggingFace Spaces demo
Target Audience

Python developers building multi-step AI agents

Similar To

LangChain · LangGraph · DSPy

Post Description

Hi HN,

This is Andrei from askmanu and I'm super happy to share a new framework I've been working on: acorn.

It takes all the best parts of DSPy, langchaing, instructor, etc and wraps it in a beautiful and easy to use API. Very easy to define model I/O, branches, define callbacks for every step, etc

See the getting started docs here: https://github.com/askmanu/acorn/blob/main/docs/getting-star...

Try out the different demos here: https://huggingface.co/spaces/askmanu/acorn

Similar Projects

AI/ML●●Solid

Mnesis – Lossless context management Python library

Engine-managed memory beats model self-summarization on OOLONG benchmarks.

Big BrainWizardry
damatar
102mo ago
Developer Tools●●●Banger

ToolGuard – Pytest for AI agent tool calls

Layer 2 execution testing without LLMs when eval frameworks only test intelligence.

Ship ItSolve My ProblemBig Brain
Heer_J
102mo ago
Security●●●Banger

GuardLLM, hardened tool calls for LLM apps

Lifecycle-aware security pipeline, not point tools—shared context from ingress through output.

Big BrainSolve My ProblemWizardry
mhcoen
104mo ago