Show HN: Hubzoid – Turns a folder of Markdown into an AI agent your team can use
Hi HN, Kakshil here, I am building an open-source tool which converts a folder of markdown files into an agent, which can be shared with a team with tool based access control. The main goal with this was to have one "brain" or a folder, which I used to make my local Claude Code agents on, work for my team with checks, and also, run workflows on the server. The same "brain" can be used for a chat agent or a workflow agent or an MCP server. Try with: pip install hubzoid hubzoid
Read original source
Source record
Recorded metrics
points · 2 votes
2026-11-11 15:45:06.779Z
cumulative since publication
Research analysis
Project record
Repository: hubzoid/hubzoid. Source account: Hi HN, Kakshil here, I am building an open-source tool which converts a folder of markdown files into an agent, which can be shared with a team with tool based access control. The main goal with this was to have one "brain" or a folder, which I used to make my local Claude Code agents on, work for my team with checks, and also, run workflows on the server. The same "brain" can be used for a chat agent or a workflow agent or an MCP server. Try with: pip install hubzoid hubzoid
Observed adoption & comparisons
Source votes: 2 votes (Nov 11, 2026 UTC; cumulative since publication) Recent records to compare: “addyosmani/agent-skills” (GitHub Trending, Nov 11, 2026); “meta/astryx” (GitHub Trending, Nov 11, 2026). Shared themes are navigation hints; they have not been verified as the same need or independent corroboration.
Adoption decision
Evaluate it against the tool or manual workflow it would replace. The stored record supports discovery; it does not yet establish reliability, lower operating cost or commercial adoption.
Unverified requirements
Not verified: license permissions, required hardware, installation steps, maintenance status and a representative task with its failure cases.
Next test
Choose one real task and a current alternative. Record the commit, environment, input, output, elapsed time and failure behavior; retain the result before recommending adoption.