tagged with llm
Displaying 1-9 of 9 total results

lefinepro

lefinepro/ocawe

Workflow automation as simple as taking notes

  • 11
  • 0
  • 2
  • 1
  • 8
  • about 21 hours ago
mamantoha

mamantoha/toon-crystal

Crystal implementation of the Token-Oriented Object Notation(TOON) serialization format

  • 10
  • 0
  • 0
  • 0
  • 0
  • 3 days ago
wevote-project

wevote-project/crystal-text-splitter

Intelligent text chunking for RAG (Retrieval-Augmented Generation) and LLM applications in Crystal.

  • 7
  • 0
  • 0
  • 0
  • 1
  • 6 months ago
xthezealot

xthezealot/aixtract

Flatten directories into AI-ready files with encoded path context 🗂️🤖

  • 1
  • 0
  • 0
  • 0
  • 0
  • over 1 year ago
AgentC-Consulting

AgentC-Consulting/knowledge-packs

Fine-tune a small local model on your docs and prove it actually learned: versioned knowledge packs (curated sources + generated training JSONL + contamination-guarded held-out eval + JSON manifest), the packsmith Crystal CLI, MLX LoRA recipes for Apple Silicon, and measured before/after eval reports. Amber framework pack + eval harness included.

  • 1
  • 0
  • 0
  • 0
  • 1
  • 4 days ago
Cxmrykk

Cxmrykk/Palm-CLI Archived

CLI for PaLM API (Text Generation)

  • 0
  • 0
  • 0
  • 0
  • 0
  • almost 3 years ago
AgentC-Consulting

AgentC-Consulting/crystal-llm-structured-json

Get typed, schema-checked JSON from an LLM in Crystal, every time: structured outputs with llamero — OpenAI/Anthropic/Groq/OpenRouter with automatic failover, or local MLX inference on Apple Silicon. No Python, no llama.cpp, no GGUF.

  • 0
  • 0
  • 0
  • 0
  • 1
  • 29 days ago
AgentC-Consulting

AgentC-Consulting/crystal-amber-recipes

Crystal & Amber recipes (2026): 15 copy-paste answers — JSON::Serializable, LLM structured output, Amber v2 routing and CRUD, Postgres, ECR templates, and import maps without Node.js.

  • 0
  • 0
  • 0
  • 0
  • 0
  • 29 days ago
jbox-web

jbox-web/ssherlock

Read-only SSH fleet audit collector in Crystal — one static binary, preset-based command catalogues (Linux, Proxmox, VMware ESXi), and one structured JSON envelope per host, shaped for an LLM to reason over.

  • 0
  • 0
  • 0
  • 0
  • 6
  • 11 days ago