OlympHill
Mini LLM Flow logo

Mini LLM FlowMinimalističko 100-člani sustav za LLM za gradnju samoadaptivnih agent radnog tokova

4.8 (6)
Daniel NikulshynRecenzirao Daniel Nikulshyn·Ažurirano srpanj 2026.

Pregled

Mini LLM Flow je lagan open-source okvir koji reducira orkestraciju LLM na oko 100 redaka koda. On nuduje esencijalne gradivne blokove za lančanu upotribu pokazatelja, upravljanje stanjem, i gradnju protokola agenta bez nadogradnje većih okvira. Projekt temelji se na ideji da minimalna apstrakcija je lakša za samima LLM-ovima da shvaćaju, proširuju i generiraju kôd za. To ga čini pogodnim za eksperimente s autonomnim agentskim programima, gdje modeli razmišljaju o i menjaju svoju logiku rada. Programeri mogu ga koristiti kao učionicu, temelj za prilagođene sustave-agente ili jako smanjenu alternativu u odnosu na težijske biblioteke za koordinaciju.

Ključne značajke

  • Približno 100 linija osnove koda
  • Lančanje upita i kontrola strujanja
  • Podrška za radnje stil agenta
  • Dizajniran za samoadaptivne LLM
  • Minimalna ovisnost o kodima
  • Otvoren i lako forkabilan

Cijene

Model
Free
Ocjena
4.8 / 5 (6)

Slučajevi uporabe

Uči temelje radnog toka agenata

Izučaj skompakćirani ~100-člani koda da bi razumio kako funkcioniraju lančanje upita, stanja i uređivanje agenata bez odlazanja kroz veliki framework.

Gradnja personaliziranih lakih sistema agenata

Forkaj minimalnu osnovu kao osnovu za personalizirane radnje workflow-a, izbjegavajući teške ovisnosti i vezivanje iz velikih orkestracija knjižnica.

Eksperimenti s samoadaptivnim agenata

Koristite minimalnu abstrakciju kako bi LLM-ovi mogli pročitati, razumjeti i generirati modificirne uređivanje same radnje koda izvornice LLM-a više pouzdano.

Brzo prototipiranje LLM pipeline-a

Upotrijebite izbačene primitivne da biste spinuli prompt-lančane i kontrolu strujanja za dokaze provedba koji će vam pomoći prije nego što budete zavezani u težem paketu.

Prednosti i nedostaci

Prednosti

  • Ekstremno malo i čitljivo kodašnje baze
  • Lako za razumevanje i proširenje LLM-om
  • Ni teših ovisnosti ni zavezivanja
  • Dobar obrazovni izvor za dizajniranje agenata

Nedostaci

  • Ograničena ugrađena funkcionalnost u odnosu na veće frameworks
  • Zahtijevano više ručno podešavanja za složenije slučajeve uporabe
  • Manja zajednica i ekosustav

Rekord bitaka

U 1 bitki u Panteonu.

1
1.
0
2.
0
3.

Last battle

Recenzije

4.8

Prosjek iz 6 ocjena.

5
5
4
1
3
0
2
0
1
0

Prijavi se za ostavljanje recenzije.

Daniel Schmidt

Daniel Schmidt

Apr 29, 2026

Years in this space

I've evaluated a lot of these over the years. What stands out here is minimal dependencies — handled better than most — and no heavy dependencies or lock-in. Limited built-in features compared to larger frameworks is my one real gripe. Worth the time if this is your use case.

Leila Hassan

Leila Hassan

Jan 30, 2026

Years in this space

I've evaluated a lot of these over the years. What stands out here is open and easily forkable — handled better than most — and extremely small and readable codebase. Worth the time if this is your use case.

SG

Sanjay Gupta

Jan 8, 2026

Years in this space

I've evaluated a lot of these over the years. What stands out here is prompt chaining and flow control — handled better than most — and extremely small and readable codebase. Smaller community and ecosystem is my one real gripe. Worth the time if this is your use case.

GE

Gunnar Eriksson

Nov 18, 2025

Years in this space

I've evaluated a lot of these over the years. What stands out here is designed for LLM self-programming — handled better than most — and extremely small and readable codebase. Worth the time if this is your use case.

LP

Linda Petersen

Nov 13, 2025

Solid for our team

We rolled this out across the team last quarter and extremely small and readable codebase. Support for agent-style workflows fits neatly into how we already work, and prompt chaining and flow control removed a step we used to do by hand. but it has held up under daily use.

Yuki Mori

Yuki Mori

Oct 14, 2025

Skeptical, then convinced

I went in skeptical — most tools in this space overpromise. It actually delivers on minimal dependencies, and no heavy dependencies or lock-in caught me off guard. still, I'd recommend giving it a real trial.

Pitanja

What are the limitations?

Cons include limited built-in features compared to larger frameworks and requiring more manual setup for complex use cases.

Asked by Victor Nguyen · Sep 25, 2025

What are the pros of using Mini LLM Flow?

Pros include an extremely small and readable codebase, ease of use for LLMs to understand and extend, and no heavy dependencies or lock-in.

Asked by Hosanna Marte · Sep 4, 2025

What are the key features?

Key features include prompt chaining, flow control, support for agent-style workflows, and minimal dependencies.

Asked by Camille Laurent · Aug 7, 2025

What is Mini LLM Flow?

Mini LLM Flow is a lightweight open-source framework for building self-programming agent workflows, with a core codebase of around 100 lines.

Asked by George Papadakis · Jun 28, 2025

Postavi pitanje

Alternative za Okvirji za agenčki AI