Gleam doesn't compile to Erlang source anymore
Gleam v1.19.0 was released with a rewritten Erlang code generator by Giacomo Cavalieri that outputs Erlang abstract forms instead of Erlang source code, letting the compiler load generated code direct…
Gleam v1.19.0 was released with a rewritten Erlang code generator by Giacomo Cavalieri that outputs Erlang abstract forms instead of Erlang source code, letting the compiler load generated code direct…
Deepfates released Imp, a full port of the DSPy language-model programming framework to the Elixir/BEAM ecosystem, letting developers declare typed model calls, agent loops and retrieval that run unde…
Legion, an open-source Elixir library, was released as a runtime that lets AI agents write sandboxed Lua or Elixir code inside an application to compose registered tools and take actions such as findi…
A developer warns that LLM memory systems in production fail silently because retrieval quality degrades while dashboards remain green. The analysis cites benchmarks showing leading systems score 92.5…
Underjord, an Elixir and Nerves consultancy, reports that the Nerves IoT framework is seeing 'sneaky growth' among AI agents and edge AI startups, with one Swedish company running 10,000 to 20,000 Ner…
The BEAM benchmark, developed by the team behind Suprflo, evaluates AI agent memory over long, multi-session histories with changing facts, ranging from 100K to 10 million tokens. It measures distinct…
Faisal Iitian released MindCache, a Python SDK with an MCP server for long-term memory in LLMs, reporting a 64% average rubric pass rate on his BEAM evaluation versus about 53% for Mem0. The system us…
A developer's RE-call memory system, which never calls an LLM, scores lower on temporal reasoning (0.408 vs. 0.567) than Mem0 on the BEAM benchmark, but avoids any LLM cost and keeps data in Postgres.…
A developer replaced the standard text-based editing approach in coding agents with direct Elixir execution, enabling AST-aware refactoring. By giving the model full Elixir execution to edit files, th…
Will Cromwell argues that Elixir and the Phoenix framework are the optimal tech stack for building AI-integrated applications, citing their ability to handle massive concurrency with minimal infrastru…
A developer built an AI agent system to autonomously curate and manage the gaming portal minigames.world, replacing manual game selection, categorization, and publishing. The architecture uses Erlang …
Elixir and the Phoenix framework eliminate the need for separate services like Redis, Kubernetes, and Python sidecars by providing built-in concurrency, fault tolerance, real-time capabilities, and ML…
Researchers introduced Eywa, a provenance-grounded long-term memory architecture for AI agents that stores immutable source evidence before deriving facts, achieving 90.19% judge accuracy on the LoCoM…
BeamWeaver, a new Elixir library, has been released to provide LangChain and LangGraph-style AI agents and durable LLM workflows natively on the BEAM. The library offers agents, graph workflows, strea…
The article describes the development of Hex Diff, an open-source tool for comparing Hex package versions. It explains how the project uses LiveView for a responsive search interface, reads package da…
This article provides an introductory overview of using ETS (Erlang Term Storage) in Elixir and Erlang, focusing on basic patterns for table management and practical usage. It explains how ETS offers …