Codex caps subagents at 3 by default — config tweak unlocks 64 concurrent threads
daniel_mac8 · x · 2026-09-07
- By default OpenAI Codex runs a max of 3 subagents concurrently; OpenAI tested Astra with up to 64 Luna subagents in parallel.
- Unlock it via config.toml:
[agents]
maxconcurrentthreadspersession = 64
- Author notes Astra orchestrating 64 Luna subagents at once is "a sight to behold".
Related event: Codex caps subagents at 3 by default; one config line unlocks 64(5 posts)→
More from coding & agent
- 35 CVEs tied to AI coding tools this year, with no review budget to match — YvesMulkers · 2026-10-23
- dsh-market: a visual plugin marketplace with 6,000+ plugins for DeepSeek Harness — aigclink · 2026-10-23
- Indie dev's agent tracks 519 directories, 311 submitted for SEO backlinks — fekdaoui · 2026-10-23
- ScienceClaw Hackathon at MIT Media Lab to build decentralized AI agent collectives for science — ProfBuehlerMIT · 2026-10-23
- What should a native agent harness handle beyond tool calling? — Glittering812 · 2026-10-23
- Running ~100 DeepSeek v4.1 flash agents in parallel for under $20/month — zack_overflow · 2026-10-23