Ember Ex Elixir — AI skill for Claude Code
Elixir port of the Ember framework for building LLM applications.
How to install Ember Ex Elixir
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open jmanhype/ember_ex_elixir and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Ember Ex Elixir does
Elixir port of the Ember framework for building LLM applications.
Alternatives in AI
- AI Engineering Hub — In-depth tutorials on LLMs, RAGs and real-world AI agent applications 37.2k ★
- WeKnora — Open-source LLM knowledge platform: turn raw documents into a queryable RAG, an autonomous reasoning agent, an 26.9k ★
- Opencodex — Universal provider proxy for OpenAI Codex & Claude Code — use any LLM (Claude, Gemini, Grok, DeepSeek, Ollama… 12.3k ★
README
EmberEx
Elixir port of the [Ember framework](https://github.com/pyember/ember) for composing LLM-powered pipelines. Provides an operator abstraction, graph-based execution engine, and JIT optimization layer.
Status
| Metric | Value |
|---|---|
| Version | 0.1.0 |
| Elixir | >= 1.14 |
| Runtime deps | 8 |
| Modules (.ex) | 89 |
| Test files | 12 (11 in test/, 1 in test_scripts/) |
| CI | No test CI workflow. Only a self-improve.yml action (last run passed, Nov 2025). |
| Hex published | No |
What it does
- Operators: Composable units of computation. Includes LLM, Map, Sequence, Branch, Retry, Ensemble, MapReduce, MostCommon, Verifier, and SelectorJudge operators.
- Specifications: Input/output schema contracts using Ecto for validation.
- XCS execution engine: Builds a DAG of operators, schedules them sequentially, in parallel, topologically, or in waves.
- JIT optimization: Caches operator results, detects LLM calls, applies structural/trace/enhanced strategies to reduce redundant API calls.
- Model providers: OpenAI and Anthropic adapters. Configurable via
EmberEx.Config. - MCP integration: Basic MCP client (stdio transport) for tool discovery.
- Metrics: Prometheus exporter for operator execution telemetry.
Project structure
lib/ember_ex/
operators/ # 14 operator modules (LLM, Map, Branch, Retry, etc.)
specifications/ # Schema generator, Ecto-based validation
models/ # Provider adapters (OpenAI, Anthropic), usage tracking
xcs/
graph/ # DAG builder variants (structural, trace, LLM, enhanced)
jit/ # JIT core, cache, profiler, strategy selector
schedulers/ # Sequential, Parallel, Topological, Wave
transforms/ # Mesh transform
context/ # Execution context
mcp/ # MCP stdio client, config loader
metrics/ # Prometheus collector and storage
config/ # Configuration manager
examples/
Related Skills
Andrej Karpathy Skills Hermes
Hermes port of Karpathy-inspired LLM coding guidelines — SKILL.md + examples.
Toon Bend
Byte-for-byte port of the toon CLI (toon_rust: JSON <-> TOON, the token-efficient format for LLM context) to B
Osa Claude Code
Claude Code reimagined in Elixir — an AI coding agent built on the BEAM with best practices from the open-sour
Useful Coding Guides For LLMs
Detailed Next.js best-practice guides designed for humans and LLM coding assistants to collaboratively build r
Fraction
Persistent memory layer for LLM agents and AI applications. Zero API costs, sub-100ms ingestion, fully offline
The AI Engineering Bootcamp
A 10-week intensive bootcamp focused on building production-ready AI agent applications. Learn advanced LLM co
Related Agents
Supabase Inference Explorer
Use proactively for exploring creative, non-obvious applications of Supabase Edge Functions, AI (embeddings an
Spec Agentic AI Solutions Engineer
AI solutions engineer who builds AI agents and AI-driven applications. Use this agent proactively when designi
Langfuse Expert
Expert Langfuse engineer for querying traces, debugging LLM applications, managing prompts, analyzing sessions