Over the last year we've had a lot of innovation in the multi-agent AI space, with folks like
@CamelAIOrg
leading the charge, my work with agent-actors (below),
@yoheinakajima
's BabyAGI,
@pyautogen
, and recently
@joaomdmoura
's CrewAI.
So what comes next?
Most projects using agents have used one agent. Or, if theres been many agents, they typically interact in a sequential manner
Excited to share a new guest blog post from
@cyrusofeden
that pushes the boundary - multiple agents acting in parallel
11
53
205
2
1
9
Replies
I'm thrilled to announce the alpha release of my labor of love — Llegos — a domain specific library for exploring the design space multi-agent systems!
One of our early users called it "more of a PyTorch, less of a Keras".
What's the deal with Llegos?
13
18
133
Existing multi-agent projects all provide a *specific implementations of agent interaction patterns*.
Llegos changes the game — it makes it easier to experiment with different implementations of agent interaction patterns.
1
0
7
Said another way, you could use Llegos to express my designs in CamelAI, agent-actors, AutoGen, CrewAI — but not vice versa.
The best part? Llegos is compatible with all the above.
How??
1
1
3
The centerpiece of Llegos are Actors — which are upgraded Agents that can receive Messages.
Actors can call any Python code they like — this means you can pull in your fav tools (ours are
@LangChainAI
,
@llama_index
,
@OpenRouterAI
@dottxtai
's Outlines,
@lateinteraction
's DSPy)
2
2
9
Llegos strives to do one thing well — being the communication fabric in multi-agent systems.
Llegos lets you go from a diagram like this, to code like that.
1
1
9
There's a lot more power to Llegos than meets the eye at first glance, dive into the examples in the library tests to take a look:
1
0
12
Looking for collaborators, DM's open!
I'm excited to see what incredible systems the community will create with Llegos. Let's build the future together!
1
0
5
And a great big thank you to everyone who's followed along and who I've learned, with special special shouts to
@jeremyphoward
(my first AI teacher), and
@karan4d
and
@max_paperclips
from
@NousResearch
.
1
0
6
And for those wondering what's on the roadmap...
- Refining Developer Experience based on feedback from developing systems (until we get reasonably stable)
- A llegos.development module with asyncio actors for boosting performance
- A production module using
@raydistributed
…
1
0
4
@raydistributed
@notscottmoore
@owocki
@jeffemmett
how might we apply multi-agent AI simulation to what you're working on?
0
0
3
0
0
0