OpenAI adds 12-hour prompt caching; an agent opens an integration PR within minutes
heyneighbor · x · 2026-10-21
OpenAI Developers announced 12-hour prompt caching in the API: persistent agents can reuse context all day, keeping shared instructions, tools, and context cached longer while paying the lower cached-input rate. Developer Peter Steinberger immediately told his RoboClaw agent to research the feature, add a config option, and open a PR — which it did on the spot, demoing an extreme build-in-public workflow of agent-driven integration.
Related event: OpenAI API Adds 12-Hour Prompt Caching for Long-Running Agents(3 posts)→
More from coding & agent
- Screenshot table to Excel in PowerShell: LLM only locates, code does the rest — dfinke · 2026-10-21
- Screenshot to spreadsheet in 4 seconds with one line of PowerShell — dfinke · 2026-10-21
- A mitm proxy that rewrites robots.txt to Allow: all gets you really far — generativist · 2026-10-21
- Anaconda ships MCP to stop coding agents from hallucinating malicious dependency packages — anacondainc · 2026-10-21
- 5-person team uses Claude and 300+ agents to design 318,484 proteins in 64 hours — 141_1337 · 2026-10-21
- Coding agents plan well but still struggle with dexterous, contact-rich robot tasks — ManlingLi_ · 2026-10-21