Loading...
Diffsmith is a native macOS app for reviewing uncommitted code changes made by AI coding agents. It lets you leave inline comments on local git diffs and send feedback back to the agent by prompt or through a local MCP server.
Ditto is an open-source website cloner that turns a public URL into componentized Next.js or Vite code. It is designed for developers and AI builders who want a deterministic, maintainable starting point instead of a flat copy.
CreateOS Sandbox is an isolated compute environment for running code and agent workloads inside Firecracker micro-VMs. It is designed for workflows that need machine-level isolation, private networking between sandboxes, and programmatic control through SDK, CLI, or MCP.
OpenChatCut is an open-source, local-first AI video editor that lets agents edit a real multitrack timeline instead of generating a flattened video. It is built for creators, editors, and developers who want conversational editing with editable exports and optional external-agent workflows.
CartAI is an agentic commerce platform for search, checkout, payment sessions, and attribution around user transactions. It helps developers and teams automate order completion on live merchant sites while tracking status through webhooks.
Lunen is an AI governance and agent-control platform that lets teams build agents in plain language while approving actions and keeping an audit record. It is aimed at teams and enterprises that want to run agents in production systems with policy controls.
Agentinel is a local security layer for autonomous coding agents that intercepts package install decisions before they run. It helps block hallucinated or malicious npm packages without requiring a cloud service or account.
BaseRT is an LLM runtime for Apple Silicon Macs that runs local models on your own device. It is positioned for on-device inference and a local coding-agent workflow, with public materials emphasizing speed and privacy by keeping execution on-machine.
FluencyLoop is an AI-assisted development workflow for Claude Code and Codex that helps teams capture decisions, document feature work, and assemble reviewer-ready summaries. It is built around branch-local documentation and a private knowledge profile that adjusts teaching depth across projects.
OpenMarkdown is a local-first Markdown editor for plain .md files, with live preview, source, and reading modes. It also connects to agents through a CLI, MCP server, and Claude Code plugin so they can work on the same file you are editing.
Clark Labs offers two AI agents: Clark Agent for autonomous browser-based work in the cloud, and Clark Code for coding tasks on your own machine. It also provides an OpenAI-compatible Clark Platform API for developers.
AgentGrid is a desktop app for managing multiple AI coding agents on a shared infinite canvas. It helps developers keep agents, terminals, browsers, notes, and project context visible in one workspace.
Kimi K3 is Moonshot AI’s frontier model for coding, knowledge work, and reasoning. It is available across Kimi.com, Kimi Work, Kimi Code, and the Kimi API, with a 1-million-token context window and native vision support.
DevSwat is an agentic AI infrastructure platform for building, running, and scheduling autonomous AI agents. It combines a browser-based IDE, personalized chat, code analysis, workflows, and governance, with support for local tools and cloud LLM providers.
microflow is a visual, flow-based programming tool for hardware prototyping and IoT. It supports local device-stored flows, signed-in collaboration, and alternate circuit/code views.
SonOf connects to your repo and PM tool, audits the codebase and surrounding product context, and turns approved work into shipped tickets with senior engineering review. It is aimed at founders and engineering leaders who need backlog help without hiring a full team immediately.
Graft AI connects AI agents to the software your business already runs by turning real application interfaces into stable, governed tools. It is built for teams that need agents to work inside existing ERP, desktop, web portal, and internal systems without replacing them.
Manta AI is an autonomous web app testing tool for teams that want to map application behavior, catch regressions, and generate tests without writing scripts or maintaining selectors. It works from a URL and supports plain-English test flows, run results with screenshots, and scheduled or deployment-triggered checks.
Zro is a private inference endpoint for coding agents that runs on EU infrastructure and supports OpenAI-compatible and Anthropic-compatible access. It is designed for developers and teams that want open-model inference with zero request retention.
AgentKey is an MCP-based connector for AI agents that adds live web search, social, finance, e-commerce, and crypto data sources through one install. It is presented for use with Claude Code, Cursor, and Windsurf.