Productivity

Developer Productivity & Workflow

AI-powered tools for managing context, snippets, and developer documentation.

101 tools · 101 with full reviews · 72 free or open source · Updated Oct 9, 2026

Pieces for Developers Freemium

Pieces Pieces for Developers is an AI-powered memory layer that captures and preserves developer context across browsers, IDEs, and terminals using an on-device LTM-2.7 engine. It functions as a persistent, privacy-first workspace that allows developers to search past work, code snippets, and workflow history without data leaving their machine.

agenttrace Open Source

luoyuctl Agenttrace is a local-first terminal TUI and report generator designed to audit AI coding-agent session history. It aggregates logs from various agents to provide insights into token usage, estimated costs, latency, and health without requiring a hosted backend or prompt uploads.

Vibe Kanban Free

Vibe Vibe Kanban is an open-source orchestration layer for AI coding agents that manages tasks via a kanban board and isolated git worktrees. It allows developers to run multiple agents in parallel, review diffs inline, and automate the development lifecycle from planning to pull request.

AI-MEMORY Open Source

AkitaOnRails AI-MEMORY is a long-term memory server for coding agents that captures session observations and consolidates them into a versioned, human-readable Markdown wiki. It enables seamless context handoffs between different agents and machines by maintaining a shared, persistent knowledge base that agents can query to avoid repeating work.

smolvm Freemium

smol machines smolvm is an open-source engine and CLI for running isolated, hardware-virtualized Linux microVMs that boot in under a second. It allows developers to run untrusted code, manage agent sandboxes, and create portable, stateful VM artifacts that run identically on local machines or in the cloud.

coop Open Source

Trail of Bits coop is a Rust CLI that manages disposable, isolated virtual machines for running AI coding agents like Claude Code and Codex. It provides a secure, reproducible environment with full tool access—including Docker, git, and compilers—without exposing the host machine to potential risks from autonomous agent execution.

Claude Code Templates Open Source

Daniel Avila Claude Code Templates is a CLI tool and web catalog that provides ready-to-use configurations, agents, commands, hooks, and MCP integrations to enhance Claude Code workflows. It includes built-in observability tools like real-time analytics, health checks, and conversation monitoring for development sessions.

Director Freemium

Director Director is a no-code browser automation platform that allows users to describe web tasks in plain English for AI agents to execute. It bridges the gap between no-code prototyping and production by allowing successful workflows to be exported as Stagehand code.

Claudete Freemium

Claudete Claudete is a native macOS control panel designed to orchestrate multiple Claude Code, Codex, and Grok agent instances from a single, unified window. It provides a centralized hub for managing parallel coding tasks, monitoring real-time resource usage, and broadcasting instructions across a fleet of agents.

Fractal OS Free

Nubler Digital Fractal is an organic operating system that integrates humans and AI agents into a single, adaptive workspace. It moves beyond reactive chat by maintaining persistent memory, orchestrating autonomous agents, and executing real-world tasks across your files and services.

Zuse Zuse is an autonomous terminal-based AI agent for macOS designed to handle coding, shell commands, browser automation, and local workflows. It features a persistent agentic loop that can read and edit files, manage sub-agents, and maintain long-term memory across sessions.

Cydonia Freemium

Crabtalk Cydonia is an open-source desktop workspace designed for developers to manage coding agents and their output as durable files on disk. It serves as a project-oriented environment where agents that support the Agent Communication Protocol (ACP) can operate, replacing traditional chat-log interfaces with persistent artifacts like articles, boards, and tables.

AI Product Adoption Deck Paid

aiproduct.cards The AI Product Adoption Deck is a 124-page working playbook containing 104 cards designed to help product teams diagnose and resolve common AI adoption failures. It provides a structured, tactical workflow that includes diagnostic cards, action patterns, and workshop templates to improve user retention and engagement.

CoderPlan Freemium

CoderPlan CoderPlan is a developer-focused API gateway that provides unified access to Claude, GPT, Gemini, and other LLMs for tools like Claude Code, Cursor, and various CLI interfaces. It enables users to manage AI coding costs through transparent, per-request billing and high-efficiency context caching.

AIFlowLearn Freemium

AIFlowLearn / 木子霖 AIFlowLearn is an AI-native learning platform that transforms technical documentation, codebases, and articles into structured, hands-on learning paths. It utilizes an AI coach to provide real-time guidance, helping developers and engineers master AI frameworks and workflows through project-based practice.

Faryo Open Source

Snailflyer Faryo is a lightweight project and mobile workbench designed to interact with live tmux-backed AI coding sessions like Codex CLI or Claude Code. It allows developers to monitor status, send instructions, and manage approvals from a phone or browser without requiring a remote desktop or creating a secondary chat history.

Tree Ring Memory Open Source

TerminallyLazy Tree Ring Memory is a framework-agnostic, local-first memory lifecycle layer for AI agents that prevents memory from becoming raw transcript sludge. It uses a ring-based aging model to distill, compress, and preserve information, ensuring that durable truths and lessons remain accessible while ephemeral data is managed or forgotten.

OpenAgentRelay Open Source

ShakespeareLabs OpenAgentRelay is a local-first tool that allows users to expose their local AI agents or automations as team-callable capabilities over a trusted LAN. It uses a small CLI to bridge communication between agents without requiring the caller to access the publisher's source code or dependencies.

Better Agent Free

Ofek Ron Better Agent is a local, web-based workspace that centralizes multiple coding agents like Claude, Codex, and Gemini into a single, persistent, and inspectable hub. It allows developers to manage sessions, track tool calls, and orchestrate multi-agent workflows while maintaining full control over data and project context.

Tura-AI Tura is an open-source agent runtime harness designed to improve coding agent performance while significantly reducing token usage. It replaces standard ReAct architectures with a structured command graph and runtime-managed context to minimize redundant model round trips.

fractal Open Source

Plasma AI Fractal is a system for orchestrating hierarchical, recursive agent loops designed to handle complex, long-horizon tasks that exceed single context windows. It organizes agents into a tree of isolated git worktrees, where each node manages its own lifecycle, memory, and budget while coordinating with parent and child nodes.

WolfMarkDown Open Source

WolfMark WolfMarkDown is an AI agent skill designed to transform messy, AI-generated output into professional, production-ready Markdown. It combines agent-based semantic structure recovery with deterministic tooling to verify, clean, and format documents while preserving technical content.

Codex Quota Overlay Open Source

cpys (maintainer; independent community project) Codex Quota Overlay is a privacy-focused desktop utility that displays remaining usage, reset times, and credits directly beside the active Codex Desktop conversation title. It functions as a lightweight companion that automatically hides when Codex is inactive or minimized.

DeskCue Open Source

Alexander Kornev DeskCue is a local-first control center that provides a unified interface for monitoring and steering AI coding agents like Codex and Claude Code. It allows developers to track task progress, inspect project changes, and provide feedback from mobile or remote devices while the agents continue running on their primary workstation.

SandBase CLI Freemium

SandBase SandBase CLI is an open-source tool and local Model Context Protocol (MCP) bridge that connects AI coding agents to over 2,000 AI models and APIs. It eliminates the need for manual API key management by providing a secure, OAuth-based configuration for major AI clients.

Abhishek Srivastava AIPM is a package manager designed to help teams install, version, and share reusable AI agent skills and prompts. It functions similarly to npm for code, allowing users to track AI instructions and workflows across projects with pinned versions.

Superagent Free

pungme Superagent is a native macOS application that provides a graphical workspace for coding agents, moving them beyond the terminal. It integrates a real browser, an iOS Simulator, and git worktrees to allow agents to perform tasks in a persistent, visual environment that mirrors a developer's actual workflow.

XiuLab Inc XiuRouter is a model API service that allows developers to access various AI models, including GPT, Claude, and Gemini, through a single account and API key. It acts as a gateway that supports multiple protocols, including OpenAI Chat Completions, OpenAI Responses, Anthropic Messages, and Gemini GenerateContent.

QwenCloud Freemium

Alibaba Cloud QwenCloud is an AI-native platform by Alibaba Cloud that provides unified access to the Qwen model family, third-party models, and agentic tools. It features a three-entry-point architecture designed for human exploration, workflow automation via CLI, and autonomous agent integration.

OrcaReplay Open Source

Continuum AI OrcaReplay is an open-source record-and-replay engine that allows developers to capture, debug, and fork AI agent executions. It attaches to agents as a local proxy to record model calls, shell commands, and file operations, enabling deterministic offline replay and cross-model testing.

Magic Patterns Freemium

Magic Patterns Magic Patterns is an AI-powered design and prototyping tool that enables product teams to generate high-fidelity UI and interactive prototypes from prompts or existing design systems. It integrates directly with development workflows by producing production-ready React code and supporting real-time multiplayer collaboration.

Builder.io Visual Copilot Freemium

Builder.io Visual Copilot, now often referred to as Fusion, is an AI-powered design-to-code tool that converts Figma designs into production-ready frontend code. It integrates directly with your codebase and design system to ensure generated components align with your existing frameworks, syntax, and styling libraries.

Jackalope Freemium

Jackalope Digital LLC Jackalope is an open-source desktop workspace designed to orchestrate multiple AI coding agents in parallel. It centralizes project context, manages isolated Git worktrees, and provides a unified interface for reviewing agent-generated code changes.

Cabinet Freemium

Cabinet AI Cabinet is an AI-first, self-hosted startup operating system that stores all knowledge as markdown files on your local disk. It functions as a persistent memory layer where AI agents, human team members, and automated workflows collaborate within a unified, version-controlled workspace.

PI-Desktop Open Source

vastsa PI-Desktop is a local-first, model-agnostic desktop workspace designed for AI coding agents. It provides a persistent environment where projects, sessions, and multi-agent workflows are managed locally without requiring accounts, cloud relays, or telemetry.

ruvnet Ruflo is an agent meta-harness that transforms Claude Code and Codex into a coordinated swarm of autonomous agents. It provides an execution layer featuring persistent memory, federated communication, and enterprise-grade security guardrails.

Context Mode Free

mksglu Context Mode is an MCP server and hook-based system that optimizes AI coding agent context windows by sandboxing tool outputs and providing persistent session memory. It reduces context consumption by up to 98% by keeping raw data out of the conversation and using a local SQLite FTS5 database for intelligent retrieval.

Worktrunk Open Source

Worktrunk Worktrunk is a command-line interface for Git worktree management, specifically optimized for running multiple AI agents in parallel. It simplifies the Git worktree workflow by providing branch-based navigation, unified status reporting, and automated lifecycle hooks.

RTK Open Source

RTK-AI RTK is an open-source CLI proxy that intercepts shell commands and compresses their output before it reaches an AI coding agent. By filtering out boilerplate, progress bars, and irrelevant noise, it helps keep context windows focused and reduces token consumption for developer workflows.

Gentle-AI Open Source

Gentleman Programming Gentle-AI is an ecosystem configurator that adapts existing AI coding agents on your machine by adding persistent memory, structured workflows, and curated skills. It does not install agents itself but instead equips them with tools like Engram for memory, Spec-Driven Development (SDD), and bounded native review.

Affaan Mustafa ECC is an agent harness performance system that provides a coordinated engineering layer for AI agents. It offers a suite of skills, instincts, memory optimization, and security scanning to improve agentic workflows across multiple harnesses like Claude Code, Cursor, and Codex.

pacifio Atlas is an open-source desktop IDE designed as source control for AI coding agents. It records agent sessions, links them to Git commits as checkpoints, and provides a shared memory layer that allows multiple agents to collaborate on the same codebase.

tt-a1i Archify is an agent skill that transforms codebase or system descriptions into validated, interactive technical diagrams. It uses a deterministic compiler to turn agent-generated JSON into self-contained HTML artifacts, ensuring diagrams are grounded in source evidence rather than invented topology.

workmux Open Source

raine workmux is an opinionated workflow tool that orchestrates git worktrees and terminal multiplexers like tmux to create isolated development environments. It is specifically designed to enable parallel AI agent workflows by providing a conflict-free, terminal-first interface for managing multiple tasks simultaneously.

Spec Kit Open Source

GitHub Spec Kit is an open-source toolkit for Spec-Driven Development (SDD) that structures AI-assisted coding by requiring explicit specifications, plans, and task lists before implementation. It acts as a process layer that integrates with over 30 AI coding agents to ensure development is repeatable, traceable, and aligned with project requirements.

Agent Skills Open Source

Addy Osmani Agent Skills is a collection of production-grade engineering workflows designed to guide AI coding agents through the software development lifecycle. It enforces senior-engineer discipline by providing structured steps, verification gates, and anti-rationalization measures that prevent agents from skipping critical tasks like testing, security reviews, and documentation.

decolua 9Router is an open-source, smart AI gateway that connects coding tools like Cursor, Cline, and Claude Code to over 60 AI providers through a single OpenAI-compatible endpoint. It optimizes workflows by automatically routing requests across subscription, cheap, and free tiers to ensure zero downtime and maximize quota usage.

i-have-adhd Free

ayghri i-have-adhd is an output-shaping skill for coding agents designed to make responses more actionable for ADHD readers. It enforces a strict set of rules that prioritize immediate next steps, numbered tasks, and the removal of conversational filler or tangents.

Oh My Hermes Free

rlaope Oh My Hermes (OMH) is an orchestration layer that adds professional operating capabilities to Hermes Agent without replacing it. It provides deterministic local routing, workflow management, and explicit evidence boundaries for tasks like planning, research, and coding handoffs.

Superpowers Free

obra Superpowers is an open-source skills framework and software development methodology that enforces disciplined engineering practices on AI coding agents. It uses a SessionStart hook to inject a library of composable skills that guide agents through structured workflows like brainstorming, planning, test-driven development, and subagent-driven reviews.

BlaBla Open Source

Petro Yakovyshyn (independent; I maintain BlaBla) BlaBla is an executable project memory tool for coding agents that moves requirements, architecture, and behavioral intent out of transient chat context into small, queryable contracts. It provides a coverage-guided behavior verifier and a static structure verifier to ensure agents maintain project integrity across long sessions.

OpenSpec Open Source

Fission-AI OpenSpec is a lightweight, vendor-neutral framework that provides a structured, spec-driven workflow for AI-assisted development. It enables developers and AI agents to align on requirements, design, and implementation tasks in writing before any code is generated, ensuring that intent is preserved beyond a single chat session.

BrowserSkill Open Source

Tencent BrowserSkill is a local bridge that allows shell-capable AI agents to operate your existing, logged-in browser without interrupting your work. It uses a CLI and browser extension to run tasks in a separate, visible Agent Window, inheriting your active sessions and cookies.

Multica Freemium

Multica Multica is an open-source, self-hostable workspace that acts as a command center for managing and orchestrating AI coding agents. It allows teams to assign tasks, track progress, and review work from various agent CLIs as if they were human teammates.

Gentleman Programming Engram is a persistent memory system for AI coding agents that uses a single Go binary and SQLite with FTS5 to store project context. It functions as an agent-agnostic MCP server, allowing agents to save and retrieve decisions, bug fixes, and conventions across sessions without requiring Node.js, Python, or Docker.

WebCodex Open Source

yyjeqhc WebCodex is a self-hosted Rust runtime that bridges AI chat clients like ChatGPT and Claude with your local development environment. It allows AI agents to interact directly with your repositories, Git, and local toolchains without requiring you to move code into a cloud-hosted workspace.

shadcn lint Open Source

shadcn An agent-first linter for Tailwind CSS design systems that allows developers to define enforceable rules for AI coding agents. When an agent violates a rule, the linter provides specific, actionable error messages that suggest fixes based on the project's actual components, variants, and theme.

Codenotch Open Source

vinzdg Codenotch is a macOS utility that pins a compact notch to your screen edge to monitor usage limits for various AI coding assistants. It provides real-time visibility into quota consumption, reset times, and agent activity states by reading local credentials and configuration files from the tools you already use.

Agent-Native Freemium

Builder.io Agent-Native is an open-source framework for building applications where AI agents and human users operate as equal partners on the same data, actions, and state. It enables the creation of 'cloneable SaaS' products where the UI and the agent are always in sync, allowing for both visual interaction and autonomous agentic workflows.

Screenpipe Freemium

Screenpipe (Negentropy Labs, Inc.) Screenpipe is a local-first, source-available AI memory layer that continuously captures screen and audio activity to create a searchable history. It enables AI agents to query this data via a local API or MCP server to automate workflows and provide context for tasks.

antiburn Freemium

antiburn Antiburn is a local-first AI observability and cost-management tool that monitors AI coding session logs to identify and prevent excessive token usage. It provides granular cost visibility and active guardrails to help developers and teams avoid hitting token limits and manage AI spending.

claude-mem Freemium

thedotmack Claude-Mem is a plugin for Claude Code and other agents that provides persistent, long-term memory across sessions. It automatically captures tool usage, compresses observations into semantic summaries, and injects relevant context into future sessions to maintain project continuity.

Oh My OpenAgent Open Source

Sisyphus Labs (code-yeongyu) Oh My OpenAgent is a multi-model agent orchestration harness that transforms a single AI coding assistant into a virtual dev team of 11 specialized agents. It automatically routes tasks to the most suitable model based on intent, enabling parallel execution and advanced features like hash-anchored editing.

CLI-Anything Open Source

HKUDS CLI-Anything is a framework that automatically generates production-ready, stateful command-line interfaces for GUI applications by analyzing their source code. It enables AI agents to control complex software like Blender, GIMP, and LibreOffice through structured commands and JSON output, bypassing the fragility of traditional GUI automation.

farion1231 CC Switch is a cross-platform desktop assistant that provides a unified management interface for multiple AI coding tools, including Claude Code, Claude Desktop, Codex, Gemini CLI, Grok Build, OpenCode, OpenClaw, and Hermes. It eliminates the need for manual configuration file editing by offering visual provider management, system tray switching, and built-in utilities for MCP and Skills.

magpie Open Source

yetone magpie is a local gateway and menu bar application that unifies model selection for various AI coding agents. It allows users to route multiple agents through a single interface, share authenticated subscriptions like Claude or ChatGPT across different tools, and manage complex model routing with smart quota handling.

Hindsight Freemium

Vectorize Hindsight is an agent memory system that uses biomimetic data structures to provide long-term, evolving memory for AI agents. Unlike traditional RAG, it consolidates information into structured facts, observations, and mental models to enable temporal reasoning and nuanced agent behavior.

Superdesign Treg is an open-source tool registry and proxy that allows AI agents to access thousands of cataloged API endpoints using a single token. It acts as a server-side vault for credentials, enabling teams to share tools and keys without exposing them to the agent's local environment.

Impeccable Free

Paul Bakaus Impeccable is a design skill and vocabulary system for AI coding agents that helps prevent common AI-generated design flaws. It provides deterministic quality checks, persistent project context, and live browser iteration to ensure AI-generated frontend code meets professional design standards.

Chrome DevTools MCP Open Source

Google (Chrome DevTools) Chrome DevTools MCP is an official server that connects AI coding assistants to a live Chrome browser, enabling them to perform real-time debugging, performance analysis, and browser automation. It acts as a bridge that allows agents to inspect the DOM, analyze network requests, run Lighthouse audits, and interact with web pages as if a human developer were using DevTools.

Mobile MCP Open Source

Mobile Next Mobile MCP is a Model Context Protocol server that provides a platform-agnostic interface for automating iOS and Android applications. It allows AI agents and LLMs to interact with emulators, simulators, and real devices using accessibility trees and screenshot-based coordinate controls.

OpenRig Open Source

Esoteric Labs OpenRig is a local control plane that manages multi-agent coding topologies by coordinating Claude Code and Codex sessions as a single, persistent team. It uses YAML-based specifications to define agent roles, communication edges, and pod structures, ensuring that agent context and team state survive reboots and session interruptions.

Cua Cua is open-core infrastructure that provides AI agents with isolated sandboxed environments, cross-OS drivers, and evaluation tools for computer-use tasks. It enables agents to interact with native desktop applications, browsers, and operating systems through a unified SDK, CLI, and MCP interface.

OpenShell Open Source

NVIDIA OpenShell is an open-source runtime designed to execute autonomous AI agents within secure, sandboxed environments. It uses kernel-level isolation and declarative YAML policies to enforce strict controls over filesystem access, network egress, process execution, and model inference.

agent-manager Freemium

YoanWai Agent-manager is a terminal user interface (TUI) that orchestrates multiple AI coding agents within tmux sessions. It provides a centralized, keypress-driven workflow for spawning, monitoring, and reviewing the work of various AI coding agents side-by-side.

Block Buzz is an open-source, self-hostable collaboration workspace built on the Nostr protocol that treats AI agents as first-class members with their own cryptographic identities. It unifies chat, code hosting, and automated workflows into a single, searchable, and signed event log.

Beacon Open Source

Asymptote Labs Beacon is an open-source, local-first telemetry layer designed to capture and normalize activity from AI agent harnesses. It provides security and IT teams with visibility into agent prompts, tool calls, file edits, and approvals across local, CI, and cloud environments.

Hyperconsciousness Open Source

Louis Beaumont (maintainer) Hyperconsciousness is an encrypted, append-only knowledge store designed for both humans and AI agents. It enables signed records to be synchronized across devices, with access managed through scoped, expiring grants.

Garry Tan gstack is Y Combinator CEO Garry Tan's open-source skill pack that turns Claude Code into a virtual engineering team. Chained slash-command roles cover product framing, architecture and design review, code review, debugging, browser-based QA, security audit, shipping and deployment, with each step passing artifacts to the next.

Beads Open Source

Steve Yegge Beads (bd) is an open-source, distributed graph issue tracker that gives coding agents persistent, structured memory. It replaces markdown plans with a dependency-aware graph stored in Dolt, so agents can find ready work, claim it and close it across long-horizon tasks without losing context.

Gaurav Gosain TUIOS is an open-source terminal multiplexer and tiling window manager written in Go that understands the coding agents running in its panes. It shows each agent's state, collects approvals and questions into a single Inbox across sessions and machines, and can fan one prompt out to several agents in separate git worktrees.

Diego Souza (diegosouzapw) OmniRoute is an open-source, self-hosted AI gateway that exposes one OpenAI-compatible endpoint for coding tools like Claude Code, Codex, Cursor and Cline across 350+ providers. Model combos with automatic failover keep agents running when quotas run out or providers fail.

Pydantic Monty is a minimal, secure Python interpreter written in Rust for running code written by AI agents. It avoids the latency and cost of container sandboxes: a new sandbox starts in under a millisecond and can only reach the host through the functions and mounts you explicitly provide.

Grafana Labs gcx is Grafana's CLI for you and your AI coding agent, giving structured access to dashboards, alerts, SLOs, metrics, logs, traces and Grafana Cloud products from the terminal. It works with any agentic coding tool and ships Agent Skills so coding agents can query production and act on real telemetry.

agentgateway Open Source

Agentic AI Foundation (Linux Foundation) agentgateway is an open-source Rust proxy and gateway control plane built for agentic AI traffic. It provides one data plane for LLM, MCP, A2A, HTTP and gRPC traffic with built-in security, governance and observability, running standalone or on Kubernetes.

Weave Router Freemium

Weave Weave Router is a model router for coding agents that sits in front of Anthropic, OpenAI and Gemini APIs and sends each agent request to the most cost-effective model likely to complete it. It plugs into Claude Code, Codex, Cursor, opencode or pi with one command.

Cloudflare cf is Cloudflare's agentic CLI for the entire Cloudflare API, built so coding agents can discover and run the command they need. It mirrors the full API, defaults to JSON output condensed for agents, and introduces a TypeScript cloudflare.config.ts configuration format starting with Workers.

Taste Skill Free

Leon Lin Taste Skill is an open-source pack of portable agent skills that upgrades AI-built interfaces with stronger layout, typography, motion and spacing instead of generic boilerplate UIs. It also includes image-generation skills for web and mobile comps and brand kits that can be handed to Codex, Cursor or Claude Code for implementation.

Skills Manager Free

Jay.TL Skills Manager is a lightweight desktop app that manages, syncs and organizes AI agent skills across 50+ coding tools such as Claude Code, Codex, Cursor, Copilot and Gemini CLI. It keeps one central skill library, deploys skills per agent or per project, and lets agents themselves install and deploy skills through it.

HyperFrames Free

HeyGen HyperFrames is HeyGen's open-source framework for turning HTML, CSS, media and seekable animations into deterministic MP4 videos, built to be driven by AI coding agents. It ships a CLI, a Claude Code plugin and 21 agent skills that teach agents to plan, write, lint, preview and render videos.

BashCut Open Source

Nolan / dongnguyenvie BashCut is a native macOS video editor built on AVFoundation with a Claude Code / Codex terminal docked beside the timeline. Everything the UI does, coding agents can do through the bashcut CLI or MCP server, using the same atomic, undoable edit operations.

Matt Pocock Skills Free

Matt Pocock Matt Pocock Skills is an open-source set of small, composable agent skills built to fix common failure modes of Claude Code, Codex and other coding agents. Instead of owning the whole process like spec frameworks, the skills cover focused steps such as grilling you about a change before work starts, writing specs, triaging issues, diagnosing bugs and reviewing code.

morluto REA (Reverse Engineer Anything) is an open-source MCP server and CLI that lets coding agents investigate applications without their source code. It inspects native binaries, JavaScript and Electron apps, .NET assemblies, Android APKs and websites, explains how a feature works with the evidence behind each conclusion, and helps the agent build a similar feature for your project.

Diagram Design Free

Cathryn Lavery (LittleMight) Diagram Design is an open-source agent skill that produces editorial-quality diagrams as self-contained HTML and SVG instead of generic rounded-box output. It supports dozens of technical and business diagram types, matches your brand by reading your website, and works in Claude Code, Codex, GitHub Copilot, Factory Droid, Pi and other Agent Skills-compatible hosts.

DBX DBX is a lightweight, open-source database client of about 25 MB that connects to more than 100 databases, message queues and middleware from desktop, Docker or the browser. It includes an AI SQL assistant and a separate MCP server so AI coding agents can query databases through the connections already configured in DBX.

Obsidian Mind Open Source

Brenno Ferrari (breferrari) Obsidian Mind is an Obsidian vault template that gives AI coding agents persistent memory across sessions. Built for Claude Code with working hooks for Codex CLI and Gemini CLI, it lets the agent maintain linked notes, decision records, people and project indexes as you talk about your work.

GBrain Open Source

Garry Tan GBrain is an open-source agent memory layer from Y Combinator CEO Garry Tan that gives the agents you already use a memory you control. It stores explicit facts with sources, supports corrections and withdrawal, and shares the same memory across Claude Code, Codex, OpenClaw, Hermes and other harnesses.

agent-browser Open Source

Vercel Labs agent-browser is a fast native Rust command-line tool that lets AI agents drive a real Chrome browser. Agents take accessibility-tree snapshots with element refs, then click, fill, read text and capture screenshots through simple shell commands.

BMAD Method Open Source

BMad Code BMAD Method (Breakthrough Method for Agile AI-Driven Development) is a set of agent skills and workflows that guide AI coding tools from idea to working software. It keeps briefs, PRDs, architecture and stories explicit as context and scales the amount of process to the size of each change.

Tale Open Source

Ruler GmbH Tale is a self-hosted, MIT-licensed project workspace where teams plan tasks on a shared board, delegate work to AI coding agents like Claude Code and Codex running in persistent sandboxes, and review deliverables together. It combines task boards, shared knowledge, automations, and governance controls for data-sensitive organizations.

Screen Browser Paid

MiCCA OÜ Screen Browser turns a plain-language guide into a narrated demo or tutorial video of a deployed web app: a real browser signs in with a demo account, follows the guide, records the screen, adds narration and effects, and returns an MP4 with GIF, subtitles, chapters and a thumbnail. It is also a remote MCP server with a companion skill so coding agents like Claude Code, Codex or Cursor can write the guide from source and trigger the recording.

FAQ

What are the best Productivity tools?

The most complete Productivity listings on ai.dosa.dev include Pieces for Developers, agenttrace, Vibe Kanban. Every tool has a detail page with pricing, key features, and a verdict - see the full list of 101 tools below.

Are Productivity tools free?

72 of the 101 Productivity tools listed here are free or open source. Others offer freemium or paid plans - check each tool's detail page for current pricing.

How is this list curated?

ai.dosa.dev is manually curated from community submissions and editorial review. Entries are enriched with pricing, features, and reviewer notes, and the directory is updated continuously.