@Dmk, the Sagents library is built on the Elixir LangChain library, does not use Oban, and the agents_demo project sets up DB persistence for the agent and the user-side conversation.
brainlid
Dmk
I had missed @typesend’s post originally - but caught it this weekend and watched the demo video. Very impressive. Saw that is was built ontop of LangChain.
My previous comment about not using LangChain in my projects was just that with Elixir rolling your own solution is very simple - making the need for using an external library (for me anyways) somewhat unnecessary.
2
mattei
I’d like to share that I started building a hobby coding agent using Elixir/OTP called Opal:
https://github.com/matteing/opal
It’s nowhere near finished, but it’s currently bootstrapping itself. The core agent loop uses :gen_statem for the state machine, tools are executed in parallel and subagents basically come for free due to OTP primitives. I’ve found Elixir an awesome language to build this in.
It’s a hobby project so please adjust expectations 
I started building this to learn both OTP and how agents work. I’ve been using AI to accelerate my work but keeping a close eye + manually reviewing the agent line by line.
So far, I’ve found using Erlang distribution gives us unprecedented observability into the state of running agents. Being able to iex into any Opal session to dump state, poke around and issue calls: it’s just insane.
Drop a star and let me know any feedback!
3
manast
I think BullMQ would be quite useful, particularly the “flows” features, if you want to breakdown a task in sub-agents: Flows & Parent-Child Jobs — BullMQ v1.3.3
1
mikehostetler
Did you try Jido at all? I see it listed above - Jido has a sophisticated “ReAct” reasoning loop with tools powered by ReqLLM here - models switch pretty easily:
https://github.com/agentjido/jido_ai/blob/main/lib/jido_ai/agents/examples/weather_agent.ex
4
mikehostetler
Here’s code to walk you through a tutorial on how to build agents of varying sophistication with ReqLLM as well:
1
brainlid
I get what you’re saying. If you only need to make a one-off LLM call, then rolling your own and doing it direct is a great option. Sagents is designed to help when it gets more complex than that. It helps handle the extra complexity of things like HITL (Human in the Loop), sub-agents, uninterruptible sub-agents, introspection, telemetry, managing a different view of the conversation from the user’s perspective vs the agent’s perspective, etc.
1
lukaszsamson
ElixirLS Core Team
If you are working on agents you may want to check out my libs:
- GitHub - lukaszsamson/a2a_ex: Elixir client and server library for the Agent2Agent (A2A) protocol · GitHub - A2A protocol implementation
- GitHub - lukaszsamson/a2ui_lv: A2UI LiveView is a Phoenix LiveView renderer and session engine for the A2UI protocol · GitHub - A2UI protocol client and phoenix liveview renderer library
- Elixir SDK by lukaszsamson · Pull Request #1046 · ag-ui-protocol/ag-ui · GitHub - PR adding AG-UI client and liveview components
2
byu
KristerV
oh, thanks. i did search, but this did not come up.
specifically this links is interesting: GitHub - druyang/awesome-elixir-llm-genai: A list of LLM and GenAI Elixir Resources/Tools · GitHub
1