Inside DeepSeek Harness and Its Plugin-Based Agent Runtime
DeepSeek Harness separates models, tools, sessions, permissions, and interfaces into plugins that builders can replace and combine.
Read articleTopic
Field notes on coding agents: loops, context, MCP, skills, and the parts that break in real projects.
DeepSeek Harness separates models, tools, sessions, permissions, and interfaces into plugins that builders can replace and combine.
Read articleLoopX keeps goals, evidence, ownership, quotas, and handoffs stable across long-running agent sessions without replacing the agent runtime.
Read articleA hands-on Kimi K3 backend audit across 68K lines of FastAPI code, including query fixes, measured results, and the full task cost.
Read articlePrompt, context, harness, loop, graph: five stacked layers that move reliability out of the model and into the system around it.
Read articleA DigitalOcean migration that used to take half a day. I set up SSH, described the target state, and Codex did the rest.
Read articleOn July 10, GPT-5.6 Sol deleted a tester's home directory after a failed $HOME expansion. How the incident happened, and three layers of defense.
Read articleHeadroom sits between your agent and the model, classifying and compressing tool output before it fills the context window.
Read articleWrangler --temporary gives an agent a 60-minute Cloudflare account, a live workers.dev URL, and a claim link. No OAuth, no MFA, no human click.
Read articleA leaked Doubao skill pack shows 25 modular skills and 283 files organized around real work objects, not one giant agent.
Read articleloops.elorm.xyz packages 40 agent loop templates by category so you can copy a kickoff prompt into Claude Code, Cursor, Codex, or Gemini CLI.
Read articleA practical roadmap for deciding whether to build an agent loop, then adding automation, state, verification, tools, and security controls in the right order.
Read articlePeter Steinberger and Boris Cherny both say the job is designing loops, not writing prompts. Feedback, stop conditions, and token cost decide if it works.
Read articleYC partner Tom Blomfield's framing: make company knowledge machine-readable, then run loops that sense, decide, act, and improve overnight.
Read article