“writing”

Open durable execution: write async await code that runs on the database or queue you choose.

Single-file memory layer for AI agents with persistent, versioned and portable memory and no database.

Isolated Linux devboxes for running AI agents and their code, with snapshots and reusable blueprints.

Open-source Python library for evals, red teaming and test generation for agentic systems

No-code builder for AI agents with a free plan, 200+ models without API keys, and self-hosting on its Business plan

Retool platform for building agents that combine code, LLM decisions and human review, connected to external systems of record