Developer Tool AI Tools

UltraCompress is a Python-based compression tool for large language models. The repo describes lossless 5-bit transformer compression, verification via SHA-256, a CLI on PyPI, and published model packs on Hugging Face.

Local-first coding agent workbench that runs agents in secretless microVMs, with support for multiple providers, parallel sessions, and shared repository workflows.

BOUND is a deterministic control harness for AI agents. It sits between agent execution and the next decision, using observable evidence to choose ACCEPT, RETRY, REPLAN, or ROLLBACK.

A Linux filesystem defragmenter written in Rust with a Qt Quick/Kirigami UI and CLI. It analyzes fragmentation, shows a block map, and can defragment ext4 plus offline FAT16/FAT32 volumes.

A Rust library for sparse byte-range caching and async read coalescing on immutable objects, with support for range semantics, eviction, and optional read-through caching.

A local AI coding harness that turns business-rule specs into a constrained JSON AST, validates it, and compiles it into Clojure code while logging generation and repair artifacts.

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.

A Python CLI and research toolkit for simulating AI training math before model training. It estimates memory, training time, token budget, config risks, benchmark speed, and reliability, with optional native Rust and C backends.

Open-source PowerShell tool that makes Claude Code chats started in VS Code appear in the Claude Code desktop app by writing the missing session/index-card files.

vid-line is a CLI tool that turns videos into ANSI art and plays them in the Claude Code statusline. It supports YouTube URLs or local files, includes install and usage instructions, and explains how playback works and how to resize or switch videos.

SecretSpec 0.12 adds audit logs and reason-required secret access for coding agents, with CLI, SDK, and config support.

CoreTex is an open-source, Unix-inspired AI harness and knowledge engine that runs on flat files, with local indexing, sandboxed execution, and Obsidian-oriented workflows.

An open-source, headless CRM built for Claude and other agents, centered on a portable .acrm file, a CLI, and versioned SQL-backed workflows for sales data, transcripts, and follow-up tasks.

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 Julia-based projectional editor for structured data with multiple editable views and an AI assistant that edits the same underlying data.

Cloudflare’s changelog post announces optional OAuth scope selection for Wrangler and the Cloudflare API MCP server, letting users grant only the permissions they need during authorization.

A Claude Code skill that rewrites Claude’s responses through Gemini to strip out the over-polished, BuzzFeed-like tone and output plainer English.

An MCP server that converts images into ASCII art so text-only LLMs can attempt image interpretation. The README includes a short explanation, example setup, and a clear description of its limitations.

A CLI/library for line-level provenance in text edited by humans and agents, using version history to estimate which ranges are human-written versus machine-generated.

Self-hosted agentic OS that connects AI engines like Claude Code, Codex, Hermes, and Ollama to messaging and email channels, with an emphasis on EU AI Act and GDPR compliance by design.

A macOS menu bar app that uses Apple Vision OCR to find approval buttons like Run, Fetch, or Retry and clicks them automatically for agent workflows.

A GitHub example that audits LangChain’s RAG quickstart with retrieval-quality metrics, flags off-topic and out-of-distribution queries, and surfaces ranking and calibration issues with charts and results files.

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