Latest

Every published item, in order · 4309 items
Nov 3
How-toBuildersMulti-sourceSelected14:50
GitHub Actions CI speedup workflow from Mole, Kaku and Pake maintainer

The core insight is that setup, not test execution, is usually the bottleneck, so caching and parallelisation yield bigger wins than optimising tests themselves. Teams with slow CI can paste the prompt directly into an agent like Claude Code or Cursor and iterate on measured run timings. The 5-job macOS concurrency limit makes the Ubuntu offloading tip especially valuable for cross-platform open-source projects.

Event
Tw93@HiTw93Source
Tomorrow 08:00, the daily lands in your inboxTelegram channel or email. Same screening as this page, no ads.
How-toBuildersMulti-sourceSelected14:49
DeepSeek Harness write-up details agent team coordination design

The practical value lies in the architecture pattern itself: separate state, compute, and environment, then layer on event triggering and asynchronous ReAct-style communication. Builders designing multi-agent teams or persistent agent workflows can apply the design to any harness, not only DeepSeek's. It reads as a hands-on reference for moving from single-prompt agents to always-on agent systems.

Event
elvis@omarsar0Source
How-toBuildersMulti-sourceSelected14:44
GitHub Actions CI speed guide from Mole, Kaku and Pake maintainer

The prompt turns CI optimisation into a repeatable agent task: paste it into Claude or another coding agent and get a before-and-after timing report. The trap to watch is that skipping required checks on docs-only PRs can block merges unless branch protection is adjusted. Developers running Actions on free plans, especially with macOS runners capped at five concurrent jobs, get the most direct benefit.

Event
Tw93@HiTw93Source
How-toBuildersSelected14:31
Code Mode: Agents Collapse Tool Calls into Typed Code Sandboxes

The shift from listing dozens of MCP tools to writing code against them changes how agents scale with large toolsets, cutting token overhead and improving reliability. Developers building agent workflows can try the Gemini 4 Argon example or the pi framework directly. Schmid's bet that MCP remains the underlying protocol, just invoked through code, is a useful planning signal for anyone wiring up tool infrastructure.

Event
Philipp Schmid@_philschmidSource
How-toBuildersSelected04:07
SGLang HiCache Extends KV Reuse Across Parallelism Configurations

Cache-aware serving is becoming the bottleneck as agentic pipelines resend long prefixes on every call, and HiCache's unified KV layout means cached prefixes survive changes in parallelism setup rather than being discarded on redeployment. Teams running GLM, DeepSeek or other long-context models on SGLang can pair HiCache with external stores like Alibaba Tair KVCache to cut TTFT without re-architecting their serving topology. The iFLYTEK deployment is a concrete reference point for production coding-agent workloads.

Official accountLMSYS Org (SGLang)@lmsysorgSource

Only the latest 2000 items are listed; for older ones see the daily archive