> your AI agent picks dependencies from memory; give it dated facts — try starlog.dev ↗ vet your agent's deps ↗ vibe-coding is fine. vibe-importing isn’t. — try starlog.dev ↗ vibe-importing isn’t fine ↗ your agent has never seen your private packages — try starlog.dev ↗ facts for private packages ↗ a linter for the dependencies your AI agent picks — try starlog.dev ↗ a linter for agent deps ↗

All articles

LLM Engineering

How LLM applications get built and shipped: inference and serving, structured output, token formats, evaluation, and the libraries powering production language-model systems.

149 articles

LLM Engineering

CircuitStream: A Lightweight LLM Proxy for Teams Sharing Rate Limits

★ 5 Python May 10, 2026
LLM Engineering

Building a Slack Doppelgänger: Fine-Tuning LLMs on Your Message History with Modal

★ 6 May 10, 2026
LLM Engineering

Inside the Foundation Model Transparency Index: How Stanford Scores AI Giants on Disclosure

★ 87 May 10, 2026
LLM Engineering

SimplyRetrieve: Building Privacy-First RAG Systems That Treat LLMs as Context Interpreters, Not Oracles

★ 218 Python May 10, 2026
LLM Engineering

Deconstructing Sparse Matrix Performance: A Case Study in Rust Optimization

★ 48 Jupyter Notebook May 10, 2026
LLM Engineering

LLM-CLI: A Crystal-Fast Command Generator That Learns What You Mean

★ 14 Crystal May 10, 2026
LLM Engineering

Instructor: How Pydantic Models Turned LLM JSON into Type-Safe Python Objects

★ 12.9k Python May 10, 2026
LLM Engineering

Inside Microsoft's LMOps: Research Prototypes That Reveal How LLMs Actually Work

★ 4.4k Python May 10, 2026
LLM Engineering

Paxml: Google's JAX Framework for Training Models at Trillion-Parameter Scale

★ 550 Python May 10, 2026
LLM Engineering

BishopFox/llm-testing-findings: The Missing Standard for Documenting AI Security Vulnerabilities

★ 74 HTML May 10, 2026
LLM Engineering

LitGPT: The Zero-Abstraction Framework for Production LLM Training

★ 13.3k Python May 10, 2026
LLM Engineering

getML: The C++ Engine That Makes Feature Engineering on Relational Data 1000x Faster

★ 241 C++ May 10, 2026
LLM Engineering

Weaponizing Machine Learning Models: How Pickle Deserialization Turns TensorFlow into a Trojan Horse

★ 43 Python May 10, 2026
LLM Engineering

Inside GCG: The Gradient-Based Attack That Broke LLM Alignment

★ 4.7k Python May 10, 2026
LLM Engineering

AutoRedTeam: Training Language Models to Attack Other Language Models

★ 15 Python May 10, 2026
LLM Engineering

MiniHF: Building Domain-Specific Language Models Through Constitutional AI and Tree Search

★ 185 Python May 10, 2026
LLM Engineering

Zep: Why Temporal Knowledge Graphs Beat Vector Databases for AI Agent Memory

★ 4.5k Python May 10, 2026
LLM Engineering

Red-Teaming LLMs with Systematic Prompt Perturbation: Inside Fiddler Auditor

★ 191 Python May 10, 2026
LLM Engineering

How Large Language Models Are Learning to Think in Graphs: A Research Taxonomy

★ 989 May 10, 2026
LLM Engineering

Running Mixtral-8x7B on Consumer Hardware: Expert Offloading and Mixed Quantization

★ 2.3k Python May 10, 2026
LLM Engineering

Mangio-RVC-Fork: When Voice Conversion Meets Ensemble Pitch Detection

★ 1.2k Python May 10, 2026
LLM Engineering

Axolotl: The Config-Driven LLM Fine-Tuning Framework Racing Ahead of Research

★ 11.9k Python May 10, 2026
LLM Engineering

LLM Sherpa: How Smart Chunking Fixes RAG's Biggest Problem

★ 1.8k Jupyter Notebook May 10, 2026
LLM Engineering

RepEng: Steering Language Models in Seconds Without Fine-Tuning

★ 724 Jupyter Notebook May 10, 2026