Dosu
AI knowledge agent that answers questions and triages issues from your codebase
Dosu moved from maintaining your repo to measuring what your coding agents actually did.
◆Recent moves
- 1d ago
Introducing Decant: Insights for your Claude Code and Codex sessions
⚡ SPARKDecant is Dosu's first product aimed at the coding agents themselves rather than the repository they work in, turning Claude Code and Codex session logs into usage and cost numbers. It extends the measurement instinct behind Dosu's docs-freshness scores and usage analytics into a category the company had not previously entered.
View source ↗ - 22d ago
July Dosu Drop: Addition by Subtraction
Dosu removed its waitlist, simplified the Knowledge Cache tools, and added impact stats. Opening access is the notable half — it marks the point where Dosu stopped rationing onboarding, which is a prerequisite for launching adjacent products like Decant.
View source ↗ - 1mo ago
June Drop: Introducing Libraries and Agents
An overhaul of how Dosu is configured, reorganized around Libraries and Agents. This is the structural change that lets the product carry several distinct behaviors instead of one fixed assistant.
View source ↗ - 1mo ago
Automate recurring work with Dosu Templates
Templates turn recurring judgment-heavy work — release notes, status updates, triage — into reusable definitions Dosu drafts from connected sources. It is the same pattern the company keeps applying: take a repeated manual chore and make it a configurable artifact.
View source ↗ - 2mo ago
A stale AGENTS.md is worse than no AGENTS.md
A blog post on keeping AGENTS.md files current, citing Cloudflare's internal platform. Positioning content for the docs-freshness product rather than a shipped change.
View source ↗ - 2mo ago
May Drop: New usage analytics to see Dosu's impact
Usage analytics arrive so teams can quantify Dosu's impact, alongside bulk doc generation and agent-driven setup. The analytics thread started here and runs directly to Decant three months later.
View source ↗