@stainlu: we built an open-source version of workspace agents - any model, self-hosted - per-session sandbox - credential isolati…
Summary
OpenClaw is an open-source, self-hostable workspace-agent platform that sandboxes each session and isolates credentials.
Similar Articles
I made a small open-source benchmark runner for testing OpenClaw agents on my own real workflows
A developer shares a personal open-source benchmark runner for testing OpenClaw agents on real, messy workflows. The tool allows users to define private evaluation cases, run agents in their actual workspace, and generate reports, aiming to provide more relevant signals than public benchmarks.
WeClawArena: An Auditable Sandbox and Benchmark for Cross-User Agents Collaboration and Security in Human-Centered Agent Networks
WeClawArena is an auditable benchmark and runtime sandbox for evaluating multi-party cross-user agent collaboration and security in human-centered agent networks, measuring task utility and attack success rates across personal workspace tasks.
I built a multi-agent platform on top of OpenClaw — 72 specialized agents, each with their own domain, all connected through ClawSwarm
A user built AI Pair, an open-source coordination layer on top of OpenClaw, enabling 72 specialized agents to discover, register, and collaborate on complex tasks across domains.
Show HN: OpenClawMachines – Extending OpenClaw to the Enterprise
OpenClawMachines is an open-source platform for running OpenClaw AI agents in hardware-isolated Firecracker microVMs on your own infrastructure, with a control plane, host agent, and LLM proxy.
Don’t keep your laptop open. Opensource agent workspace that deploys microVMs.
Krowoc is an open-source agent workspace that launches micro-VMs to give each AI agent an isolated machine with shell, filesystem, and headless Chrome. It supports multiple model providers via Fireworks or bring-your-own-key, and lets long-running tasks persist independently of your laptop.