Topic cluster · 28 items

llm

repo

parsehawk/parsehawk

Local-first document AI. Run 100% locally by default, with API, CLI, and Web UI.

repo

holasoymalva/guia-de-programacion-con-ai

Guia de desarrollo y programacion con herramientas de Inteligencia Artificial y LLMS

repo

Moh4696/free-ai-models

10 legit ways to access major AI models (GPT, Claude, Llama, DeepSeek & more) for FREE — step-by-step guides, no subscription, no card.

repo

teixeirazeus/fablize-for-hermes

This project adapts fablize's verified procedures — verification grounding, multi-story evidence gating, investigation protocol, and early-stop prevention.

repo

Noshkoto/Noshy

Your agent has amnesia. Noshy fixes that. Persistent memory for AI agents — LLM extraction, hybrid search, zero deps.

repo

likithamadala/ai-pm-learning-fleet

A self-running fleet of AI agents that teaches its owner to think like an AI product manager - and maintains itself daily with no babysitting. Built on Claude Code.

repo

las7/memharness

Bi-temporal agent long-term memory: SQLite-backed MCP server with recall ranking, hybrid vector+FTS recall, and a source-staleness signal

repo

engineering87/llm-atlas

Interactive, in-browser visualization of how a transformer language model works: tokens, attention, quantization, and sampling, rendered live.

repo

nomad505050/ions-genesis

Open protocol for traversable knowledge networks. CBB traversal lets an 8B model match frontier AI on domain-specific queries.

repo

nicolbl95/MultiAgent-Financial-Analyzer

Multi-agent AI system that analyzes financial reports, identifies risks, and generates executive summaries using LangGraph, RAG and LLMs.

glossary_term

Context window

How much text a model can consider at once.

company

Northwind AI

An applied-research lab building reliable reasoning models.

repo

minimal-diffusion-lm

A tiny, readable diffusion language model.

article

Why small models are having a moment

Distillation and better data are closing the gap with giants — here's what it means.

paper

Sparse attention at million-token context

A linear-cost attention variant that holds quality past a million tokens.

paper

Diffusion language models, revisited

Bringing diffusion objectives to text generation with competitive quality.

model

Helix-7B

A 7B general model with strong math and code benchmarks.

model

Retrace-1.5B

A small reasoning model tuned to self-correct via failure traces.

model

CodeForge-15B

A code model trained on permissively licensed repositories.

paper

Scaling laws for mixture-of-experts models

How sparse expert routing changes the compute-optimal frontier for large models.

glossary_term

Transformer

The neural network architecture behind most modern language models.

tutorial

Fine-tune a small model on your own data

A practical guide to LoRA fine-tuning end to end.

tutorial

Build your first transformer from scratch

Step through attention, MLPs, and training on a toy task.

glossary_term

Token

A chunk of text (often a word-piece) that a model reads and predicts.

tool

PromptLab

An editor for testing and versioning prompts.

glossary_term

Attention

A mechanism that lets a model weigh which parts of the input matter most for each output.

paper

Grokking in small transformers

When and why tiny models suddenly generalize long after overfitting.

repo

attention-zoo

Implementations of many attention variants, benchmarked.

Related topics