Developer Tools Tools

opencode zen is a curated, “ready-to-use” gateway of tested models optimized for coding agents. It integrates as an optional provider within opencode, offering pay-as-you-go access to top models (e.g. GPT-5, Claude, Grok) with no lock-in.

Docfarm catches every artifact your AI builds through MCP, hosts it at a clean link, and tracks who opens it. HTML, PDFs, decks, anything. No more zipping files or screenshotting Claude outputs to share. Capture is automatic, so every piece lands in one place. Share it with your team and work on it together, all from the same farm. Most AI work lives in personal accounts and walks out when someone leaves. Docfarm keeps it on infrastructure you own. Your AI tool ships it, Docfarm plants it.

Polygram IDE Agent is an AI-native coding assistant that helps developers plan, design, code, and edit products directly inside their IDE. Unlike traditional coding assistants, Polygram uses intelligent multi-agent workflows and smart model routing to dynamically select the best AI models and agents for maximum token efficiency, speed, and output quality. It plugs directly into VS Code, Cursor, and Antigravity along with visual editor for frontend developers.

PaneFlow now ships an MCP server, so AI agents like Claude and Cursor build real animated slideshows for you - laid out, on-brand, and exportable to code, video, or PDF. Every result is a real, editable project you own. Plus a rebuilt editor and 50 new templates.

Soon, more agents than humans will use your product via MCP. Spanly gives you full observability on the MCP server you ship: error rates, session traces, latency, client analytics, deploy alerts. Drop-in CLI or SDK. US & EU data residency. Built for SaaS engineering teams shipping MCP in production, alongside the Datadog, Sentry, or New Relic you already run.

AI agents don't just chat anymore; they execute. SolonGate is the zero-trust security layer that controls exactly what your autonomous AI agents can do. We sit directly between LLMs and your internal systems, APIs, or databases. Every action your AI attempts is filtered through our deterministic Policy Engine and an isolated AI Judge. We block risky, unauthorized, or destructive actions before execution. Complete action governance.

Write agent logic, and skip the plumbing. Give AI agents reliable access to 2,000+ APIs with retries, idempotency, policy enforcement, and durable state.

Tyto is a lightweight model that runs on your audio stream and predicts whether the audio reaching your agent will cause downstream failures. It outputs a single score plus a breakdown across six dimensions: noise, speaker reverb, speaker loudness, interfering speech, background media speech, packet loss. Try it here: https://ai-coustics.github.io/Project-Tyto-Real-Time-Demo/

Migration triage for legacy codebases in 113 programming languages, powered by the Claude API. GUI and CLI. Scores migration difficulty, flags risky constructs, and drafts target-language conversions — so you know what you're dealing with before the rewrite starts.

A macOS workbench where Claude, Codex, and Hermes run on your specs, research, and Figma files.

NotchSpace turns the Mac notch into a controllable workspace layer. It has three core features: a quick app launcher for instant access, a menu bar manager to clean and rearrange your top bar, and a temporary workspace for dragging and moving files, text, links, and colors between apps. Everything is intentional—you choose what enters the space. No auto-capture. Built natively for macOS with SwiftUI. Fully local, no tracking or uploads.

Deep Work Plan turns any repo into a harness with the context of your best engineer — so any AI agent codes like your smartest model and can't drift from the plan. Not a chat window it forgets, a spec written into the repo: atomic tasks, acceptance criteria, validation gates, resumable state. Long runs survive context resets; any agent picks up where the last left off. Point an agent at it, walk away, come back to work you can verify. Any agent, any repo, no lock-in. Open Source, MIT.

Charlie Labs gives engineering teams always-on AI daemons that keep work moving after coding agents create it. Define recurring roles in your repo, then let Daemons monitor PRs, issues, CI, docs, and Sentry errors over time. Instead of waiting for another human prompt, Daemons leave reviewable updates where your team already works: GitHub, Linear, Slack, and Sentry.

Run more agents. Merge more code. Kepler is GitKraken’s agentic development environment (ADE). It gives you full clarity and control to run parallel agents at scale: plan work, write code, and review what ships, all from one surface.

Canopy runs parallel Claude Code sessions as tabs in one native macOS window — each in its own git worktree, each its own Claude. Close the app and every session resumes with its conversation intact. One-click "Merge & Finish" handles the merge-and-cleanup dance, a split shell pane lets you run git without interrupting Claude, and an Activity dashboard shows where your tokens actually went. Native SwiftUI, no Electron. macOS 14+, AGPL-3.0. Built by someone who uses it daily.

AI prompt workspace for generating, analyzing, optimizing, refining, and saving prompts. Turn ideas into structured prompts, evaluate prompt quality with clear metrics and estimated token usage, improve existing prompts, and convert images, videos, text, or URLs into reusable prompt patterns with Reverse Prompt. Organize your best prompts in the Prompt Library and use them with ChatGPT, Claude, Gemini, image and video generators, coding assistants, and other AI tools.

Know what to build next. Collect feature requests, let users vote, and share your public roadmap. Flat pricing — no per-user fees. An affordable Canny alternative for small SaaS teams, startups, and solo founders.

Bodhiorchard replaces story points, standups, and stale tickets with 12 specialised AI agents. They draft every spec, forecast cycle times with Monte Carlo, and tend your codebase like an orchard. Open-source, self-hosted, Apache 2.0. Runs on Claude Code.

Sklm is a CLI tool that centralizes management of skills (SKILL.md files) for your AI agents. It solves the tension between wanting skills globally available vs. per-project scoped, without polluting your agent's configuration. Multi-agent support - Global store - Registry discovery - Auto-sync

Know what to build next. Collect feature requests, let users vote, and share your public roadmap. Flat pricing — no per-user fees. An affordable Canny alternative for small SaaS teams, startups, and solo founders.

Fantasma helps you build Ghost landing pages with sections Source doesn't ship: hero, FAQ, stats, CTA, feature grids, and more. Same Source look, visual editing, no theme files. Export a standard ZIP (free) or publish to Ghost (Pro). Real Handlebars you can hand to a client. https://www.fantasma.io/