LLM

This multi-agent system combines language models and operations tools to turn natural-language requests into working software.

Localforge runs autonomous coding agents locally through a graphical interface for Codex, Claude, and other language models.

Comet's Opik platform provides AI observability, agent testing, evaluation, and monitoring for developers.

The Hugging Face LLM Course teaches large language model concepts through documentation and related learning resources.

LifeArchitect publishes a reference table of language models and their specifications and data points.

TeamoRouter provides one API key for coding agents and offers provider setup and usage-based payment.

InfraNodus analyzes text with knowledge graphs to reveal themes and gaps across notes, PDFs, surveys, search results, and other data.

Aeon provides an AI agent framework that runs unattended on GitHub Actions and can drive Claude Code, Grok, and Codex.

notesGPT records voice notes, transcribes and summarizes them, and extracts tasks.

FormX.ai automates document workflows by extracting data from PDFs and other business documents.

BrainSoup lets users create AI agents to handle tasks and automate processes using natural language.

SEAL LLM Leaderboards presents expert-driven benchmarks and rankings across coding, reasoning, and other areas.

LangWatch provides evaluations for language models and tests for AI agent applications.

OneCompression is a Python package for compressing large language models.

Dataiku provides an AI platform for coordinating people, workflows, and governance across business AI projects.

Valohai provides MLOps tools for comparing, evaluating, and shipping configurations for AI products using specialized models.

LLMrefs tracks brand visibility, rankings, and citations across generative AI search tools and benchmarks competitors.

Microsoft’s UFO project focuses on AI agents that work across desktop applications and digital workflows.

PhysioNet lets users find, share, and reuse health data, with guidance on access to credentialed datasets.

Andy is an autonomous AI agent that builds search APIs, simulation tools, AI infrastructure, and other tools.

Langfuse provides open-source evaluation and observability tools for tracing and improving AI agents.

LibreWolf WinUpdater helps update installed or portable LibreWolf instances on Windows, with a separate Chromium updater fork also linked.

Search Universal-DB, a database listing homebrew software for Nintendo DS and 3DS systems.

A free downloadable guide covering strategies for testing large language models and analyzing their behavior.