Engineering Manager / Technical Lead
A topic hub collecting every article tagged Coding Agents. Use it to explore related posts and follow this theme across the site.
10 articles
A deep-dive tour of Oh My Pi (omp.sh) — examining 'The Harness Problem', why edit tools swing model pass rates by up to 10×, built-in Hashline patching, AST refactoring, visual Snapcompact, and how it compares to OpenCode, Claude Code, and Cursor.
A deep architectural breakdown comparing minimalist micro-harnesses (Pi, Ante, Aider, Goose) against full-stack Agentic Operating Systems (Antigravity CLI, Claude Code, Opencode, GitHub Copilot): analyzing token economics, RAM density, context poisoning, and production two-tier pipelines.
Two vendors call their product an ADE and they do not even agree on what the A stands for — yet Warp, Orca, Cursor, Google, GitHub, herdr and cmux converged on the same primitives anyway. A source-backed look at the three tiers, what is marketing, and which primitives your repo actually needs.
Compare Fable 5 Low, Opus 4.8 Low, and Sonnet 5 Low for coding and planning, including task cost, cross-effort surprises, and a practical routing policy.
Build a small Claude model router with explicit task classes, Low effort, bounded tools and budgets, isolated workspaces, acceptance tests, and cost-per-result evaluation.
A practical Agno-only blueprint using Workflow, native Agents, session state, bounded repair loops, persisted HITL review, and isolated coding workspaces.
A practical LangGraph-centered blueprint using typed graph state, dynamic Send fan-out, PostgreSQL checkpoints, deterministic candidate testing, interrupts, and isolated coding sandboxes.
Compare Fable 5, Opus 4.8, and Sonnet 5 at High effort using CursorBench 3.2, then see when Ultracode changes the model-routing decision.
A source-checked guide to Pi — the minimal terminal coding harness behind OpenClaw — with comparisons to Claude Code, Cursor, Codex, and OpenCode, plus handoff workflows and when the minimal approach wins.
A research-backed guide for engineers and PMs on what is now redundant with stronger coding agents, when a good prompt is sufficient, and when prompts need scaffolding, tools, evals, and workflow design.
Quick find
Search by topic, title, framework, or pattern.