Dev argues agents need just two tools—monitors and state access—to run autonomously
ebetica · x · 2026-11-07
Developer ebetica is iterating on his agent harness Recurse and asks a core design question: what's the minimal tool set for agents to work autonomously for long stretches? His answer: essentially just a monitor tool plus read/write access to shared state (e.g. messaging other agents).
In a quoted tweet he complains that Codex's harness, despite improvements, still lacks monitors—an essential feature he says only the Claude ecosystem supports. Follow-up replies note that goals, loops, automated reviews, dynamic workflows and more can all be implemented with just these two primitives.
Related event: Recurse: Open-Source Harness for Long-Running Autonomous Agents(3 posts)→
More from coding & agent
- Gemini /teamwork agents caught live: four parallel task logs all running that second — RyanSpunk · 2026-11-13
- Codex CLI 0.168.0 adds model provider picker, side-by-side TUI workspace and animated GIF generation — github-actions[bot] · 2026-11-13
- Free MCP server lets Claude read Altium, Allegro, KiCad and Gerber PCB files directly — woodisruff · 2026-11-13
- a16z Partner Clones Open-Source Game with Fable 5.2 Agent, Which Finds Its Own Horse Animation Asset — FinanceYF5 · 2026-11-13
- OpenAI team shares how it runs and governs fleets of persistent agents internally — romainhuet · 2026-11-13
- Perplexity's Decider scanned 1B tokens across 7,000 agent sessions, found 14 security fixes — denisyarats · 2026-11-13