Runtools
AI Native infrastructure to build & deploy agents
Runtools launched on May 20, 2026 with 2 votes, #6,288 of 20,538 launches that month.
What it does
Runtools is the execution layer for AI agents. Instead of stitching together sandboxes, agent frameworks, tool integrations, credentials, and storage, Runtools gives you the core infrastructure in one place: secure cloud sandboxes, persistent workspaces, hosted Tool Hub integrations, cloud threads, and a visual/programmatic agent builder. Build agents that can run commands, edit files, connect to apps like GitHub/Gmail/Slack, and keep state across runs.
AI-native infrastructure for agents. Sandboxes, tools, workspaces, workflows, and a visual agent builder — everything you need to build, deploy, and manage AI agents.
Tell Autopilot what you need in plain English. It asks the right questions, provisions the infrastructure, and ships a fully operational agentfrom runtools.ai
Does a similar job
all alternatives →

Tilde.run – Agent sandbox with a transactional, versioned filesystemMay 2026 · tilde.run · ▲205Tilde started from a simple observation: AI agents are only as useful as the environment they can work in. Giving an agent a prompt is easy. Giving it the right files, credentials, tools, context, and execution environment, safely and repeatably, is much harder. Over the past year, we learned a lot

AgentRun: DSL to turn agents into Workflows28d ago · github.com · ▲51The Agentrun Workflow DSL. Contribute to Parcha-ai/agentrun development by creating an account on GitHub.

More ai this month
the category →



Paintings by AI models: programs run through a simulation of oil paint.
AI · 20d ago · stillwet.art
PixVerse R2▲381A real-time world model you can explore and change
AI · 29d ago · world.pixverse.video

Source: Product Hunt launch ↗
Launched alongside, May 2026
the whole month →

Parallel agents, diff reviewer, and multi-model comparisons
Dev tools · May 2026 · kilo.ai



Hey HN, Henry here from Cactus. We open-sourced Needle, a 26M parameter function-calling (tool use) model. It runs at 6000 tok/s prefill and 1200 tok/s decode on consumer devices. We were always frustrated by the little effort made towards building agentic models that run on budget phones, so we conducted investigations that led to an observation: agentic experiences are built upon tool calling, and massive models are overkill for it. Tool calling is fundamentally retrieval-and-assembly (match query to tool name, extract argument values, emit JSON), not reasoning. Cross-attention…
Life & fun · May 2026 · github.com

🌱 Private, quiet space for thinking. Simple app for .md files. - zakirullin/files.md
Dev tools · May 2026 · github.com