Show HN: BeamWeaver – LangChain/DeepAgents-style agents and workflows for Elixir (github.com)
We build agents in Elixir. We kept running into the same issue and found there is no observability for agentic systems.
We decided to take the best aspects of LangChain, LangGraph, and DeepAgents and put them into Elixir.
BeamWeaver comes with an OTP-native design and: - agents and tool calling - graph workflows - checkpoints and resumable execution - memory stores - retries, fallbacks, interrupts, and human review - typed streaming events - provider adapters for OpenAI, Anthropic, Google Gemini, xAI, and Moonshot/Kimi - fake/replay models for deterministic tests
We're also building observability on top of it through WeaveScope, which we'll release very soon.
BeamWeaver gives Elixir teams the tools needed to build advanced agentic systems without pushing the hard parts into Python services.
1 comment
[ 3.1 ms ] story [ 12.8 ms ] threadWith agent systems, logs get bad pretty quickly. You want to know what is alive, what spawned what, what it's waiting on, what retried, what died, etc.
Since this is Elixir, are you planning to show the actual BEAM process/supervision structure in WeaveScope, or mostly the higher-level workflow graph?
Feels like both are useful. The graph shows what you meant to run, the process tree shows what is actually running.