Showing all 12 posts

When your coding agent says it is done

Agents report success after running no tests at all, and review is now the bottleneck. How to make completion a check the harness runs instead of a sentence the model writes.

Engineering16 Oct 2026 · 5 min read

The coding agent harness, explained

A coding agent is a model plus a harness. The harness owns the tools, permissions, context and verification, and it decides most of the quality you actually experience.

Comparison15 Oct 2026 · 5 min read

Quaka and the cloud coding agents

A side by side of local-first and cloud coding agents on data, model choice, review control and cost, using public complaints and incident reports rather than marketing claims.

Guides14 Oct 2026 · 6 min read

What is a local AI coding agent?

A local AI coding agent runs on your own machine, edits your real repo and shows a diff before anything is committed. How it works, what stays private, and when a cloud agent still wins.

Benchmarks13 Oct 2026 · 5 min read

How to read coding agent benchmarks

Top scores on SWE-bench Verified vary by ten points depending on who reports them, and a 100-line harness scores 65%. What these benchmarks measure and what to do instead.

Safety11 Oct 2026 · 5 min read

Guardrails, snapshots and rewind

Nine public incidents in fourteen months, and the sandbox escapes that did not need to break out. What guardrails a coding agent needs before you point it at a real repository.

Models9 Oct 2026 · 4 min read

Bring your own model

Provider choice is the difference between a tool you own and a tool you rent. How BYOK, local models and provider-neutral threads work in practice.

Standards8 Oct 2026 · 4 min read

MCP and the quiet tax on your context window

Tool schemas for a popular messaging integration can occupy nearly 70% of a context window. How MCP costs show up, and what to do about it before it decides your model choice.

Models7 Oct 2026 · 5 min read

Where a coding agent run spends its money

Savings of 80 to 89% from caching, a timestamp that drops one to 6%, and why cached output costs more than fresh output. The economics of a long agent run.

Workflows5 Oct 2026 · 4 min read

Running several agents on one repository

Two agents editing one directory start stepping on each other within minutes. How worktrees, isolation and collision detection make parallel runs actually work.

Standards3 Oct 2026 · 4 min read

Agent Client Protocol: swapping agents like editors

ACP lets an editor talk to any agent through one interface, and a public registry launched in January 2026. What it changes for anyone tired of one-vendor lock-in.

Engineering1 Oct 2026 · 4 min read

Why Quaka is a Tauri and Rust desktop app

A 3.8MB binary against a 165MB one, 25MB of memory against 180, and why an agent that runs your shell needed a native permission boundary.

Get an invite

Read the posts, then try the thing.

Quaka is in private beta on macOS, Windows and Linux. Bring your own key or run a local model.

Read the source on GitHub