Like Claude Code, but for running agents

Joined August 2025
Photos and videos
πŸš€ AgentUse v0.14.0 is here. Our biggest release ever! It refines the human-in-the-loop & serve experience from 0.13.0 and hardens skills, sandboxing, and auth across the board. Here's everything that's new 🧡
1
38
⚠️ Heads up (potentially breaking): the JSON API moved under an /api/* prefix. The old ?format=json negotiation is removed. Update self-hosted health checks and any scripted JSON consumers.
1
5
πŸ”’ Plus lots of hardening: sandbox no longer mounts $HOME, Anthropic OAuth tokens refresh before expiry, stored-XSS fixes on the session page, bounded sandbox exec lifetimes, and more OpenRouter model series. Full notes πŸ‘‡ github.com/agentuse/agentuse…
5
AgentUse went from v0.1 β†’ v0.5 in 5 months. Here's what we learned building an agent runner that works with any model and runs on autopilot:
1
1
104
Making agents "production ready" meant adding: β€’ Security controls for bash/filesystem access β€’ Session logs for debugging β€’ Doom loop detection β€’ Built-in cron scheduling β€’ Hot reload in serve mode Unattended agents need guardrails.
1
8
Try Minimax M2.1 and GLM 4.7 for your agents.
A $0.05 model nearly beat a $0.95 model on the same task. Not on speed. Not on cost efficiency. On pure task completion quality. I used AgentUse to benchmark 5 AI models (claude opus 4.5, minimax m2.1, glm 4.7, sonnet 4.5, and haiku 4.5) on Notion database CRUD operations. Here's the ranking πŸ‘‡
70
20 Oct 2025
πŸš€ AgentUse v0.1.3 is available! Major improvements to plugin system, observability, and developer experience. Thread πŸ§΅πŸ‘‡
1
24
20 Oct 2025
7/ 🏷️ Better Subagent Logging Sub-agent tool calls are now clearly marked in logs, making it easier to trace execution flow in complex multi-agent systems.
1
23