#developer-tools

Vet a package before your AI coding agent uses it — authoritative facts (CVEs, license, maintenance) via an MCP server + CLI. Local, no account.

A multi-agent context, rules, and hooks boilerplate generator. With a single command, it scaffolds conventions, namespaced skills, stack-appropriate settings, and interactive guardrails for seven major AI coding environments, matching each agent's native file formats and capability profiles.

Official Go implementation of the UTCP

Your work logs itself. Meridian watches what you build — no prompts, no timers — classifies every session into the right task, and auto-updates Jira, Linear, and GitHub Issues. All data stays on your machine.

PTY session management, WebSocket streaming, and REST API server for Claude Code conversations

Semantic + structural code search for AI-native development

Deterministic documentation generator for TypeScript packages.

From-zero terminal coding agent: a key-holding OpenAI-compatible routing backend + a thin client with ~285 skills, MCP connectors, and ask/plan/auto modes. No build step.

Corezoid AI plugin marketplace for Claude Code and Codex: product knowledge, workflow skills, schemas, templates, playbooks, samples, and MCP references for building Corezoid processes.

TTT Editor - Terminal Text Tool: a terminal text editor IDE. A real alternative to VS Code, Zed, and Sublime that runs in your terminal. Single binary, zero config.

MCP server for Laravel Telescope

A second brain for Claude Code: project memory, real token & cost accounting, local semantic recall, and active guardrails.

okffs is a Model Context Protocol server for GitHub. Create and manage GitHub issues and projects using Claude.ai and your IDE — then push them as matching branches straight into your repo via Claude Code.

A curated, opinionated set of OpenCode plugins for spec-first, review-driven, safer agentic development.

Git worktree CLI for parallel-edit workflows — sibling layout and shell-integrated navigation

All-in-one engineering workflow & knowledge engine for Claude Code. One-command install, runs standalone (Node >=18, no bun). L0-L3 task classification, 13 runtime invariants, code review, browser QA, security audit, and a deduplicated knowledge base that compounds across tasks.

The AI Software Factory. Tickets, docs, designs, and analytics in. Shipped code out. One secure pipeline from idea to review — Claude on the line, human on the floor.

Claude Code & Codex 本地 token 追踪 — 状态栏（Codex 业界首创伪 statusline）、GitHub 风格热力图、多模型成本分析。 | Local token tracker for Claude Code & Codex — status line (industry-first Codex faux statusline), GitHub-style heatmap, multi-model cost analysis

Session viewer for coding agents — browse, search, trace, and export Claude Code, Codex, and Grok conversations

toaster-ready — a CLI that scores how ready a repo is for agents and humans to ramp up on (binary: toaster).

Official Go implementation of the UTCP

Verification runtime and execution observability for AI-generated web apps.

Typed Temporal workflow code generation and embedded Temporal helpers for Go.

Switch between multiple Claude Code and Codex login accounts, locally and safely. A switcher, not a rotator.

Local-first flight recorder for coding agents : replay every run as a live session map, score the context bill, and write the fix back into AGENTS.md — no API key, one npx command.

Across 348 long-horizon benchmark sessions, Tura used up to 83.1% fewer turns on the rewrite benchmark and improved the DeepSWE pass rate by up to 16.7 percentage points compared with Codex CLI.

Backthread keeps the thread on what your AI coding agent ships — it captures the why behind every change and turns it into a living 'How it works' view of your codebase you can actually query.

Contexer captures architecture decisions, constraints, conventions, and patterns from AI coding sessions. Replays them in next session so you don't have to explain it again. It works across multiple AI agents.

A self-hosted browser console for Claude Code and ChatGPT Codex. Run AI sessions from any browser or phone — tool approvals, model selection, context management, session history — without leaving your own machine.

The lifecycle automation layer PostHog doesn't have yet. Code-first email journeys on PostHog + Resend. Self-hosted.