devtools — independent software & tools
-
comandos
Mission control for running many Claude Code agents in parallel — live dashboard, actionable popups with full markdown, voice alerts, tabbed terminals, one-key answers, Telegram remote control. Linux, no cloud, survives reboots.
-
bitbox
A community-built collection of tiny Python CLI tools. One file. One function. One contributor.
-
trytokka
TryTokka — AI API spend alerts (Scout). Synced spend across OpenAI, Anthropic, Gemini & more. By Acsaven.
-
Grove
🍀 Opinionated Agents Development Environment for Teams. Run a forest of agents in parallel, manage, and monitor them.
-
Dxrk
Dxrk Ecosystem Configurator — supercharge AI coding agents
-
agent-rules-kit
Diagnose AI agent instruction files like AGENTS.md, CLAUDE.md, and Cursor rules using this local read-only Python CLI.
-
agentflare
Run AI coding agents efficiently, and coordinate more than one of them. Zero fluff, zero runtime deps.
-
herdr-sandbox
Windows-native counterpart to a dev container.
-
github-code-linkify
A lightweight, high-performance Chrome extension that enhances GitHub browsing by providing instant plaintext URL highlighting and click functionality directly on code lines in pull requests, commits, and code blobs.
-
resume-skills
Offline, local-only context migration skills across 9 coding-agent sources × 9 destination hosts (registry-derived 81 cells). Stdlib-only; inert handoff for fresh sessions, not live restore.
-
agent-monitor-for-claude
Local Windows desktop monitor for your running Claude Code agents - live status, estimated cost, model, host and one-click focus, grouped by project. Read-only and fully offline.
-
sshnav
A terminal UI for managing SSHFS mounts and SSH ProxyJump tunnels
-
sdkproof
Type-check how well AI coding agents use your SDK's current API.
-
cli-dashboard
📊 Beautiful terminal dashboard for monitoring CPU, RAM, disk, network, and Git stats. Built with TypeScript.
-
dev-prune
Reclaim disk space from idle Git repositories. A Rust CLI that deletes node_modules, .venv, target and vendor only after the project's own package manager proves a lockfile can rebuild them.
-
wechat-opencode
Bridge WeChat to local OpenCode for chat, permission approvals, slash commands, and session persistence on macOS and Linux
-
open-max
Minimal Rust terminal harness for coding. Small, extremely fast, and self-extensible.
-
OpenSweep
AI agents that keep your codebase healthy — sweep repos, keep docs alive, file findings, and drive PRs to green. Free to self-host (ELv2).
-
SSHCommander
Cross-platform SSH/SFTP client with terminal, tabs, widgets and biometric auth for Android & Windows.
-
MCPSafari
Control Safari on macOS for AI agents with native MCP tools for tabs, forms, HTML, JavaScript, screenshots, and network data
-
nightgauge
Open-core, AI-powered issue-to-PR pipeline with enforced quality gates.
-
DevToggle
Supercharge your Android Quick Settings. Securely and instantly toggle Developer Options, ADB USB Debugging, and Wireless Debugging directly from your notification shade without root using Shizuku.
-
vtx-coding-agent
Minimalist coding agent harness with a Textual TUI and headless CLI. <1k-token system prompt, 18+ LLM providers, AGENTS.md + skills context, session tree, prompt/auto permissions.
-
pandev-cli
What your AI coding agents actually cost — by task, branch, model and file. Runs locally, dashboard on 127.0.0.1:4976, no telemetry.
-
patchloom
Single-binary CLI that gives AI agents safe, structured file editing
-
patchloom
Structured file edits for AI agents (JSON/YAML/TOML, markdown, AST, dry-run, MCP). Not a generic filesystem MCP.
-
glance
Agents deploy, you comment, agents fix. A self-hosted human-in-the-loop review loop for coding agents — $0 on Cloudflare's free tier.
-
portato
SSH port-forwarding manager with a TUI — toggle local, remote and SOCKS5 tunnels from one screen. Single Go binary, background daemon, autostart.
-
holt
Know what your agents made, and don't lose any of it — what each worktree produced, which ones collide, which are safe to delete, and a guard that stops an agent deleting work that exists nowhere else.
-
vendo
Embedded agents your customers use to automate work, build views, and connect their tools.
-
rolecraft
Zero-dependency CLI to install AI agent skills directly from any source. No marketplace, no registry, no signup — just point it at a local folder or a GitHub repo and it works. Works with opencode, claude-code, cursor, and all spec-compliant agents.
-
zero-operators
Autonomous AI research team: write a plan.md, spawn agents, train, verify, and deliver a clean ML repo.
-
clearedforpush
Catch merge conflicts before you push.ClearedForPush tells you about merge conflicts before you push. Not during CI, not in PR review. Locally, in under 2 seconds.
-
devspec
Enterprise-ready spec-driven development framework that helps software teams and technical leaders standardize AI-assisted delivery across architecture, planning, implementation, review, governance, and recovery.
-
hookstack
Claude Code hooks catalogue — production-ready hooks for Claude Code, OpenAI Codex & GitHub Copilot. Install in one npx command.
-
ClAudit
Catch false-positive Claude Code safety/policy blocks, scrub PII, and auto-file clean GitHub issues. FOSS.
-
yapui
Yap at your UI — live HTML preview with a two-way feedback loop, as a Claude Code skill
-
pkgwrap
One command. Every package manager. Universal CLI wrapper for 17 package managers across Linux, macOS, Windows, Termux and BSD. Installed from source.
-
ApexTerm
Native macOS terminal workspace with tabs, split panes, history, tmux, and optional agent workflows
-
simplicio-loop
🔁 Finishes your entire backlog while you sleep. The AI orchestrator that DOES the work end-to-end on ANY LLM — discover → implement → verify → merge → 24/7 — behind safety gates, at up to 90% fewer tokens. 48 extension points. Not a chatbot. A worker.
-
repo-bridge
Turn ChatGPT Web into a real coding agent on your own repos - read, edit, build, test, git, PRs. MCP server with OAuth 2.1, driven by GPT-5.6 Sol on ChatGPT Plus/Pro. No OpenAI API key, no per-token API bill.
-
aurix-ai
Open-source terminal AI agent for coding, deep research, automation, and multi-platform task execution.
-
ccjk
Claude Code JinKu - Advanced AI-powered development assistant with skills, agents, and LLM-driven audit
-
codeam-cli
Workflow-continuity bridge for AI coding agents. Wrap Claude Code or Codex in a PTY and supervise, approve, and redirect the session from any device — async. The terminal companion for CodeAgent Mobile.
-
contextspin
Replace Claude Code spinner/statusline text with live org context (meetings, Slack, CI, incidents, PRs) aggregated from your existing MCP servers, CLIs, and HTTP endpoints.
-
loki-mode-sdk
TypeScript SDK for Loki Mode - autonomous multi-agent development platform
-
mcp-jira-cloud
A Model Context Protocol (MCP) server for Jira Cloud integration. Enables AI assistants like GitHub Copilot and Claude to search issues, manage tickets, log work, handle sprints, and interact with your Jira instance seamlessly. Features 91 tools for compr
-
ngx-ai-devtools
Network-tab-style DevTools for LLM calls in Angular apps. See every prompt, response, token, and dollar your app spends — without leaving the browser.
-
@trymesh/cli
Mesh terminal agent CLI — token-efficient coding agent with a shared LLM gateway.
-
stacklens
Offline Java CLI that analyzes Spring Boot logs and stack traces — detects 13 failure types, shows exact location (class + line), occurrence counts, and severity. Pipe from kubectl or docker logs
-
starmap
An auto-updating AI Model Catalog available as a CLI Tool, HTTP Server w/ SDKs, or Golang Package.
-
MantaUI
Open-source, self-hosted Claude Code and opencode client. Agents run in real > tmux on your own Linux box or Mac, and you drive them from desktop, phone or > browser over HTTPS.
-
gh-safe-repo
Python CLI that creates GitHub repos with safe defaults — branch protection, Dependabot, secret scanning, and pre-flight security scanning — applied automatically.
-
rust-doctor
Your agent writes bad Rust. This catches it.
-
mocker
Manage Docker-compatible containers on macOS using Apple’s Containerization framework with familiar commands and native performance.
-
open-table
Open-source table UI framework for the OpenClaw community. Build powerful Clay alternatives and data-driven SaaS apps.
-
open-todo
✅ Open-source Linear alternative. A lightweight issue tracker for SaaS to manage tasks, projects, and labels with OpenClaw.
-
setup-goose-action
GitHub Action to install and cache Goose AI agent for workflows
-
copyleftdev
Systems-level software engineer building security tools, developer infrastructure, and AI-native systems in Rust, Go, and Zig. 560+ open source repositories.
-
port-daddy
Authoritative port assignment service for development servers. Prevents port conflicts across multiple AI agent sessions.