› fix signup on Safari edit src/signup/form.ts ✓ 48 tests pass $ git push origin main ✕ refused: main needs review ✓ opened PR #128
Open source · coming soon
Opinr: An opinionated framework for running teams of AI agents.
Opinr is an open-source framework for running a team of AI agents. Claude Code, Codex and opencode run unchanged, each live in its own terminal on Herdr. Opinr makes the set-up decisions for you, with a separate workspace for each business, side project or part of your life.
Works with
- Claude Code
- Codex
- opencode
- Slack
- Telegram
Herdr
How it fits together
One request, from Slack to the knowledge base.
Every workspace runs the same way. Watch one request go through it, or pick a step.
The opinions
Four opinions, decided for you.
You can rename or tune each one, but not remove it. That’s what makes it a framework.
A chief of staff in every workspace
Each business or area of your life is its own workspace, with its own agents, skills and knowledge. You talk to one chief of staff per workspace, from Slack or Telegram. It knows every project there, and nothing outside it.
The knowledge loop
Every session ends with a note. Notes land in an inbox and are filed into the knowledge base for you. Agents never edit it directly, so it stays something you can trust.
Scoped skills
Skills live in a library that’s never loaded into an agent. Each workspace picks and pins its own set, and each agent picks from that. Nothing leaks everywhere, and nothing changes under you.
Guardrails outside the agent
Every agent has a shell, so asking it nicely enforces nothing. Rules are written once and enforced where the agent can’t switch them off: GitHub, git hooks, the broker and each workspace’s permissions.
Not another agent loop
Herdr is the engine. Opinr is the missing layer on top.
Chatting with one Claude Code session from Slack is useful on its own. Opinr is the set-up around it: a workspace for each part of your life, a chief of staff in each, agents from different providers, a knowledge base that keeps itself up to date, and rules the agents can’t switch off.
| Aspect | Typical agent harnesses | Opinr |
|---|---|---|
| The agent | Their own agent loop calling a model | Claude Code, Codex and opencode, unchanged, each in its own terminal |
| Improvements | Arrive with the harness’s releases | Every Claude Code or Codex update reaches every agent |
| Seeing the work | Logs and chat replies | Every agent is live in Herdr, where you can step in |
| Scope | One instance per business | One install, many isolated workspaces |
| Set-up | Many choices left open | One way to do each thing |
| Cross-checking | One provider | Agents from different providers check each other |
Getting started
From install to your first chat in Slack.
Install it once, connect Slack, create a workspace. Its chief of staff answers from your phone, and every conversation is a Claude Code session you can watch or take over.
$ npm install -g @opinr/hq
$ opinr setup
✓ Created ~/opinr
✓ Slack connected
$ opinr init acme --channel acme-chat
✓ Workspace acme, kept apart from the others
✓ Chief of staff on Claude Code, live in Herdr
$ opinr doctor
✓ Node.js ✓ Herdr core ✓ Claude Code ✓ Slack ✓ ServiceOpinions included.
Where it is, November 2026: milestone 1 of 9, chatting with a chief of staff from Slack, is built and in daily use. The code goes public under Apache 2.0 when it’s ready for others. Until then, the build log says what got built each week, and why.
Or follow @mikejdeeming on X