An Agent-friendly way to manage literature.
Agentero is a local research workspace that connects papers, structured reading material, Markdown notes, and AI agents in one place. Researchers use it to read and annotate PDFs, extract formulas and figures, organize literature, and collaborate with agents on research tasks while keeping context locally. Its catalogue skills and instruction support agent-assisted research workflows in Agentero.
Latest release v0.13.0 — Agentero v0.13.0 · 23 Oct 2026
6 files for Claude Code, Codex and OpenCode: bump, commit, interface-details, release and 2 more — 1,706 tokens loaded in every session.
AGENTS.md A 1,706 tok .agents/skills/bump/SKILL.md A 28 tok .agents/skills/commit/SKILL.md A 24 tok .agents/skills/interface-details/SKILL.md A 47 tok .agents/skills/release/SKILL.md A 81 tok .agents/skills/apple-design/SKILL.md A 80 tok These files are poco-ai/Agentero's own configuration — they tell Claude Code, Codex and OpenCode how to work on this repository, so they are not mods to install elsewhere. Copy one as a starting point and replace the parts that are about this project.