developer tools

Mouse is a precision file-editing tool for AI coding agents. It adds coordinate-based editing, staged changes with atomic rollback, and richer tool responses to help agents make safer file edits.

Python toolkit for building LLM agents with MCP servers, skills folders, memory, streaming, and metrics support.

Private skill search for AI coding agents. It helps an agent match abstract capability wishes to vetted skills without sending task details off machine.

A Pomodoro timer for Claude Code that shows a live countdown in the terminal status line and includes a backup alarm, CLI controls, and setup commands.

A self-learning skill layer for Claude Code that distills skills from real sessions, merges near-duplicates, updates skills in use, and prunes unused ones.

TypeScript SDK that adds an agent-facing visualize tool and embedded interactive charts to an MCP server. It supports SQL-backed chart rendering, text fallbacks for non-widget clients, and adapters for several warehouse systems.

A CLI/browser skill for AI agents that turns websites into numbered actions with stable references, persistent sessions, and human handoff for auth, CAPTCHA, and MFA.

Mobile SSH and AI agent IDE for iPhone. It lets developers connect to remote servers, run terminals, browse files, manage git and cron jobs, and deploy or supervise agents from a phone.

NakshGuard is a self-hosted reverse proxy for OpenAI and Anthropic chat APIs that detects and blocks runaway AI agent loops before they waste tokens or API spend. It includes per-agent session tracking, configurable thresholds, shadow mode, and hot config reload.

KINETK is an AI infrastructure product that turns social-web content into a real-time IP graph for creators, communities, and narratives. The site highlights an API and MCP for agents, multimodal embeddings, and a query layer for grounded retrieval.

A local-first, privacy-preserving usage meter for AI coding tools. It reads local transcripts to estimate token usage, cost, focus time, and achievements across tools like Claude Code, Codex, Kimi, and Qwen CLI.

git-lrc is a Git-based AI code review tool that runs on commit and surfaces risk categories, inline findings, and a summary deck for each review.

Chrome extension that brings AI coding help directly into the browser for debugging, code explanations, security reviews, and solution generation.

Lathe generates multi-part, hands-on technical tutorials from prompts and provides a local UI plus CLI workflow for working through them with LLM-assisted skills.

A Python filter layer for LLM apps that evaluates responses against a Lean-verified Scherf logic backend and can pass, flag, correct, or block output.

A Git-native CLI task ledger for coordinating work between humans and coding agents, with task claiming, notes, releases, handoffs, and audit history stored in files and versioned in Git.

Chrome extension that extracts AI-generated HTML from ChatGPT, Claude, and Gemini, then previews, downloads, or publishes it to targets like Netlify, GitHub, FTP, or a self-hosted agent.

A weekly security audit of Atlassian’s remote MCP server, focused on OAuth 2.1, RFC 9728 discovery, PKCE, DCR, and token handling. The page documents why the server’s discovery chain fails and includes HTTP evidence links.

A Rust-based CLI that fetches web pages, strips page chrome, and outputs readable Markdown for AI agents and shell workflows.

A Mac menu bar app that schedules Claude Code prompts to run later on the user’s Mac, using local files, skills, and CLI tools. Results post back when the job runs.

Gread is a Skill and MCP server that gives coding agents access to the source code and docs of public GitHub repositories, with support for both skill-based and MCP client integrations.

A Docker-based sandbox for running AI coding agents with dropped capabilities, no-new-privileges, and no Docker socket access. It wraps the pi terminal coding agent and supports local file edits, persistent auth, and skills mounts.

An autonomous neuro-symbolic formal verification engine for Lean 4. The repository describes a proof workflow that generates tactics and then checks them deterministically in Lean, with example proofs, verification steps, and telemetry outputs.

An open-source Llama2 inference engine written in x86 real-mode assembly that fits in 1277 bytes and can boot directly from disk before any OS loads.