Alternatives to Plimsoll

Microsoft Execution Containers: an open, cross-platform sandboxed code-execution system for running untrusted model output, plugins, and agent tools.

An open-source sandbox engine that applies OS isolation and policy rules to AI agent tools, network access, and MCP calls.

Open-source Microsoft sandbox and benchmark that verifies AI agents reliably complete stateful business tasks, exposing the discovery-reliability gap.

Preview MIT agent filesystem on Durable Objects. Not production. Pay Workers usage, not a $0 computer SKU.

NVIDIA OpenShell runs AI agents in policy-controlled sandboxes with filesystem restrictions, network rules, and protected provider credentials.

Daytona is now a closed-source sandbox cloud. GitHub is archived. Starter $20, Plus $200, Scale $500, plus compute after included credits.

Firecracker microVM sandboxes for AI agents. Hobby is $0 plus usage; Pro is $150/month. Open-source SDK on GitHub.

An open-source CLI and optional MCP server that gives AI agents cited, ranked answers from large local record sets.

Python serverless compute with a Sandbox API for untrusted agent code, scale-to-zero, and per-second CPU/GPU billing.

ByteDance's open-source SuperAgent harness for long-horizon tasks. Orchestrates sub-agents, memory, sandboxes, and skills on LangGraph, with a browser-equipp.

Vectorize's open-source agent memory system. Retain, recall, and reflect over structured facts and mental models in PostgreSQL, ranked first on LongMemEval.

Open-source TypeScript agent framework: agents, workflows, RAG, memory, MCP, and eval with a hosted platform. About 27,437 GitHub stars (2026-08-25).

Persistent, searchable memory for AI coding agents with 95.2% recall on LongMemEval, running locally on SQLite with MCP, hooks, and 54 tools for Claude Code,.

Token-efficient microkernel AI agent with ML-based smart routing, persistent memory, a layered sandbox, built-in search, and local embeddings. Apache 2.0.