#developer-tools

Local-first ROI analytics for Claude Code, OpenAI Codex, and GitHub Copilot

Universal, language-agnostic development standards for software projects. Includes coding standards, git workflows, testing guidelines, documentation structure, and AI collaboration rules.

One source of truth for AI agents, skills, rules, and hooks. Transpile to every AI CLI you use.

Local-first personal agentic OS and everything app for coding, knowledge work, web design, automations, and artifacts.

📐 Bidirectional spec-to-code drift detection. Rust CLI and MCP server that catches undocumented exports and vanished symbols in CI.

Torollo is an open-source interactive visual playground designed to learn system design and networking, all locally.

Launch each project's AI coding agent (Claude Code, Codex, Cursor) in its own terminal and auto-tile every window across all your monitors - DPI-correct on mixed-scale setups.

Graph-aware TUI for the Beads issue tracker: PageRank, critical path, kanban, dependency DAG visualization, and robot-mode JSON API

The Destructive Command Guard (dcg) is for blocking dangerous git and shell commands from being executed by agents.

A minimal CLI time tracker for developers.

Spec-driven development framework — AI agents that think before they type

Multi-agent orchestration for Pi: subagents, swarms, worktrees, schedules, handoffs and live TUI observability.

Some more derive(Trait) options

Local-first runtime for project-scoped AI coding-agent sessions, with durable state, authority boundaries, and multi-harness interoperability.

Local spend monitor for Claude Code with hard budget caps: track cost per project and git branch, get phone alerts, and stop a runaway agent before the bill lands. Zero keys, zero prompts, zero latency. roninforge.org/budgetclaw

The operating layer for Claude Code + OpenAI Codex: persistent project memory, intent routing, safety hooks, cost telemetry, and parallel agent fleets.

High-performance multi-data-source database client — ~30MB, AI & MCP ready, zero Electron bloat. | 高性能多数据源数据库客户端：约 30MB，AI 与 MCP 就绪，告别 Electron 膨胀。

ANTLR-based PostgreSQL query parser for Go. Extracts tables, columns, joins, CTEs, parameters, DDL actions, and full column-usage metadata from SQL into a structured IR.

Yadflow (yad = يد, "hand") — the AI-driven SDLC where a human hand moves every gate. Gated, team, multi-repo: author → review → build, with a PR-driven review gate and a zero-dependency CLI. Ships as a BMAD module + 17 skills.

An auto-updating AI Model Catalog - Single binary CLI, REST/SSE Server - SDKs - Golang Package.

Self-hosted browser terminal manager for AI coding agents. Control Claude Code, Codex, Gemini, and shell sessions from your phone or browser over Tailscale.

Spec-first AI development: describe a feature → AI creates spec + plan + tasks, builds autonomously, syncs to GitHub/JIRA. Domain-expert skills for PM, Architect, Frontend, QA learn your patterns permanently. Claude Code, Codex, Cursor, Copilot & more.

Neutral control plane for coding-agent fleets: claims, roles, mailbox reliability, receipts, audit, federation, dead-letter visibility, sandbox receipts, and cross-agent coordination. This is still pre-1.0.0 - Software works however you might need help from your local agents to set it up.

Persistent memory for AI coding agents. Your agent learns your codebase the way a senior engineer would — what files go together, what you usually edit next. Works with Claude Code, Cursor, Cline, Continue. 100% local. (Side effect: 12-50× cheaper code questions.)

Control plane for your harness across many repos — durable personas, per-task workspaces, and a credential vault the model never reads from

Coding Agent singularly focused efficiency and context curation. Reduces API costs by 50-80% vs other agent AND improves the code quality at the same time. Uses Hash Anchored edits, massively parallel operations, AST manipulation and many many other optimizations. https://dirac.run/

You, multiplied. Mission control for Claude Code, Codex, and OpenCode: see every session, approve what your agents do, and run them on a schedule. Self-hosted, MIT.

Local-first MCP tools and dashboard for investigating Codex token usage, credits, costs, caching, and thread patterns.

Local proxy that compresses your LLM API requests so you pay less, with no change to the answers. Trims wasted tokens from prompts, history, tool output, and code before they're sent: -31% input / -74% output, measured live. Any provider, no extra model calls. Also an MCP server and embeddable library (Rust, Python, Ruby, Kotlin, Swift, JS/TS).

The AI agent that lives in your framework/browser