llm

Lagotto Meter is a beta web tool that checks how an AI agent perceives a website versus what the site claims about itself. It positions itself as a semantic truth/readability analyzer with a reproducible analysis method and public tools.

A pull request adding AMD GPU support to tiny-vLLM through ROCm/HIP while keeping the existing CUDA build path unchanged. The snapshot describes the compatibility header, CMake option, architecture selection, and validation on multiple AMD GPUs.

An experimental programming language and compiler designed for LLM-written code, with a Python-based toolchain that compiles to native macOS binaries. The repo also includes a full NES emulator written in Laze and usage examples for both the compiler and emulator.

A small post-trained Qwen2.5-0.5B-Instruct model tuned to write in Gen Z slang, with training and inference notebooks plus dataset files in the repo.

Windows desktop chat client for OpenRouter with streaming completions, model browsing, multi-session history, local storage, and PySide6 UI.

An open-source desktop client for editing LLM context with a separate AI model, context maps, compression tools, and revision rollback.

An Apple Silicon–optimized inference build of Bonsai 1.7B with custom Metal kernels, benchmark results, quick-start instructions, and a bundled OpenAI-compatible server.

A detailed technical write-up about training a 3.8B-parameter language model from scratch, including setup, throughput improvements, ablations, benchmarks, and cost/performance results.

A lightweight Markdown variant designed to reduce token usage for LLM consumption using single-character markers and context-aware parsing.

A DeepSeek Harness plugin that uses an LLM to verify and rank candidate outputs with select, compare, track, and rollout tools.

Vomit is a Go-based CLI that converts Claude output into readable English by sending it through a separate local LLM. It supports install/setup commands, a scrub mode for Claude hooks, and sidecar commands for listing and tailing sessions.

A pricing analysis article comparing batch API discounts across Google, OpenAI, Anthropic, xAI, and OpenRouter, with a focus on where batch rates differ from standard pricing.

HyperSAE is a Python package for mechanistic interpretability that trains hyperbolic sparse autoencoders on LLM activations. The page includes installation steps, a quickstart example, benchmark tables, and a short software architecture overview.

OneRingAI is an open-source TypeScript library for building AI agents with integrations and graph memory. The repository shows a substantial codebase with docs, setup files, testing, MCP-related material, and references to supported models and multimodal capabilities.

An open-source project for running a small LLM and limited agent workflows on ESP32-P4 hardware, with model details, architecture notes, examples, and setup instructions.

A Python tool manager for AI agents that uses an LLM-tools.txt registry to install, pin, describe, and execute tools with one predictable contract.

A GitHub repository for an engine-agnostic KV cache fragment system for on-device LLM inference, with Android and Go components, adapters for llama.cpp/MLC-LLM/ONNX Runtime, and benchmark and monitoring code.

A local-first desktop environment for dispatching coding tasks to any model and any agent, with diff review, terminal streaming, task history, and per-project configuration.

An open-source ID library that generates human-readable, token-efficient IDs for AI agents and LLM workflows, with parsing, validation, deterministic IDs, and alias mapping utilities.

An experimental autonomous bare-metal OS agent that uses an LLM, VirtualBox, and screenshot inspection to iterate on low-level code, boot a VM, and refine behavior from execution results.

A TypeScript markdown parser built for incremental streaming, aimed at parsing LLM markdown output on the server or client. It exposes a typed AST, supports CommonMark and GFM tables, and includes examples for full and streaming parsing.

Apple Machine Learning Research paper proposing LaDiR, a reasoning framework that combines a VAE-based latent space with latent diffusion to improve LLM text reasoning and iterative refinement.

Public evaluation code for an Agent Memory Leaderboard, including answer-generation and scoring contracts for comparing LLM agent memory systems.

A write-up of a custom French-learning system built around spaced repetition, grammar tracking, and a voice practice app. It explains the problem, the workflow, and the model/API stack used to keep costs low.