Hermes Agent Linear Integration: Issues, Sprint Triage, and Agent Execution
Connect Hermes Agent to Linear with the MCP catalog so an agent can read issues, create follow-ups, triage sprint risk, and connect Linear work to GitHub execution.
Quick answer
Use Hermes Agent with Linear when Linear is your team-visible tracker and you want an agent that can read issues, create follow-ups, connect issues to GitHub work, and report progress. The recommended setup path is the Linear MCP catalog entry (hermes mcp install linear), then a read-only smoke test before enabling write tools.
Best for
Product and engineering teams that already use Linear and want an agent to turn issue context into actual shipped work.
Founders who collect bugs in Telegram, Discord, Slack, or email and need clean Linear issues with acceptance criteria.
Engineering managers who want sprint-risk summaries without manually reading every open issue.
Teams that want Linear as the source of truth and Hermes Kanban as the agent’s internal execution board.
Features
- ✓Linear MCP catalog setup with OAuth-based authorization
- ✓Read Linear issues, projects, teams, labels, and priorities inside an agent run
- ✓Create follow-up issues from meetings, support threads, code review findings, or release notes
- ✓Summarize sprint risk, stale blockers, missing owners, and ambiguous acceptance criteria
- ✓Connect Linear issues to GitHub branches, pull requests, Actions failures, and review comments
- ✓Use Hermes Kanban for agent execution while Linear remains the team-visible tracker
- ✓Tool selection controls so you can start read-only before allowing write actions
Setup path
- 1Install the Nous-reviewed Linear MCP catalog entry:
hermes mcp install linear. - 2Complete the OAuth flow or credential prompt opened by Hermes, then restart or open a fresh Hermes session so the MCP tools are discovered.
- 3Run
hermes mcp configure linearand keep only the Linear tools your team wants the agent to use at first. - 4Start with a read-only smoke test: ask Hermes to summarize open high-priority issues for one team or project.
- 5If the smoke test is correct, enable issue creation/update tools and define default labels, project, team, and status conventions in a skill.
- 6Pair with GitHub when Linear issues should lead to branches, pull requests, code review, or Actions-failure fixes.
What the Linear integration actually does
Hermes connects to Linear through the MCP catalog, so Linear becomes another tool surface inside an agent run instead of a separate chat bot. After the Linear MCP is installed and authorized, Hermes can search issues, open issue details, create new work items, and use that tracker context while it writes code, reviews GitHub changes, or posts a status summary back to your team.
- •Use Linear as the team-visible source of truth and Hermes as the execution layer that can read the issue, gather repo context, perform work, and report the result.
- •Start with read/search tools first, then enable write tools such as issue creation only after one safe smoke test.
- •Keep GitHub, Notion, Slack, or Telegram connected separately when the workflow needs code, docs, or team notifications outside Linear.
A practical Linear workflow
The useful pattern is not “AI writes a ticket.” It is an issue-to-outcome loop: Hermes reads a Linear issue, checks related files or pull requests, asks for missing details only when needed, implements or drafts the next step, then updates the issue with exactly what changed and what still needs human review.
- •Bug triage: summarize the report, find the likely code path, reproduce if possible, and add a clear fix plan or pull request link.
- •Sprint planning: group issues by risk, dependency, owner, and missing context before the planning meeting.
- •Support handoff: turn a Telegram, Discord, email, or Slack thread into a Linear issue with reproduction steps and acceptance criteria.
- •Release cleanup: scan open issues, find stale blockers, and draft the final “what shipped / what slipped” update.
When to use Linear versus the Hermes Kanban board
Linear is best for team planning, product visibility, assignment, labels, priorities, projects, cycles, and reporting. The Hermes Kanban board is best for the agent’s internal execution plan: parent tasks, child tasks, specialist profiles, parallel work, and progress comments while the agent is running. You can use both: Linear tracks the official deliverable; Kanban tracks how Hermes decomposes and executes the work.
- •Use Linear when humans need to own, prioritize, or discuss the issue later.
- •Use Hermes Kanban when one prompt needs several agents or steps before it can be called done.
- •Store the Linear issue ID in the Hermes task title or notes when you want a stable cross-reference.
Safe rollout checklist
Treat Linear as production project data. A good rollout begins with OAuth, read-only inspection, and one low-risk issue. Once the team trusts the output, enable creation or update tools, add a skill that defines your issue format, and decide where Hermes should send completion reports.
- •Install the catalog entry with
hermes mcp install linear, then complete the browser OAuth flow if prompted. - •Use
hermes mcp configure linearto leave destructive or rarely needed tools disabled. - •Run one read-only prompt such as “summarize my highest-priority Linear issues for this project.”
- •Add write access only after confirming team, project, labels, and priority mapping are correct.
- •Pair with GitHub for pull-request work and Telegram/Slack/Discord for human-visible status reports.
Linear as context, not just a destination
Most “AI issue tracker” demos stop at creating a ticket. Hermes is more useful because Linear can become context for a larger agent run. The agent can inspect the issue, look at the repository, check recent pull requests, decide what information is missing, and then produce either a code change, a QA note, a documentation patch, or a clearer follow-up issue.
Routing issue types to specialist agents
Different Linear work should not all go to the same generic prompt. Bugs can load a code-focused profile with GitHub access. Documentation issues can load a writing profile with the docs repo and Notion context. QA issues can load browser and terminal tools. Hermes profiles and skills let you keep those behaviors separate while Linear stays the shared work queue.
Human approval still matters
Linear write access should be staged. Start by letting Hermes read and summarize. Then allow issue creation for low-risk workflows. Only later should it update statuses or post comments automatically, and even then the skill should define exactly when approval is required. That keeps the tracker trustworthy instead of turning it into an unreviewed bot log.
Optional demo video
Hermes Agent Just Became a Project Manager — Nemanja Mirkovic
Nemanja Mirkovic demonstrates using Hermes Agent as a project manager with the Kanban board plugin. Relevant for Linear users: the video shows how to structure multi-step work into agent-assigned cards, route tasks to specialist profiles, track progress, and give feedback via card comments. The same patterns apply to connecting Linear issues to Hermes agent workflows via the Linear API.
- 0:00Introduction — Kanban board as project manager
- 0:47Installing via /update and running /kanban
- 1:52Assigning tasks to writer and designer profiles
- 2:30Watching cards move through the Kanban board
- 3:44Different models per agent profile
- 6:45Card comments for mid-task feedback
- 7:30Parent and child task dependencies
- 9:10GitHub Issues as an alternative orchestration layer
Common setup issues
- No Linear tools show up — run
hermes mcp listand confirm the Linear catalog entry is installed and enabled. Start a fresh Hermes session after changing MCP configuration. - OAuth opens but the agent still cannot read issues — finish the browser authorization flow, then run
hermes mcp test linearor reopen Hermes so the client reconnects. - Hermes creates issues in the wrong place — define the default Linear team, project, labels, and priority mapping in a skill or prompt template before enabling write-heavy workflows.
- The video feels unrelated — treat it as an optional Kanban/project-manager demo. The actual Linear setup uses the Linear MCP; the Kanban demo only explains how Hermes decomposes multi-step work.
Keep building the workflow
FAQ
Does Hermes have a native Linear adapter?
The recommended path is the Linear MCP catalog entry. MCP makes Linear tools available to Hermes without writing a custom native tool first.
What does Hermes need to connect to Linear?
Install the Linear MCP catalog entry, complete OAuth or the credential prompt, then choose which Linear tools Hermes may use. Start read-only and add write tools after one successful smoke test.
Can Hermes create Linear issues from conversations?
Yes. Once Linear write tools are enabled, Hermes can turn meeting notes, support threads, QA findings, or code-review comments into issues with titles, descriptions, priorities, and labels.
Can Hermes connect Linear issues to GitHub pull requests?
Yes. Pair Linear with the GitHub integration so Hermes can read the issue, inspect code, create a branch or pull request, and then report the PR link back to Linear or your messaging channel.
Should I use Linear or Hermes Kanban?
Use Linear for the team-visible tracker. Use Hermes Kanban for the agent’s internal execution plan when a job needs multiple steps, subagents, dependencies, or progress comments.
Is it safe to let an agent update Linear?
It can be safe if you stage permissions: read-only first, issue creation next, and status/comment updates only after your team defines clear conventions and approval points.
How is Hermes different from Linear built-in AI?
Linear AI helps inside Linear. Hermes can operate across Linear, GitHub, terminal tools, browsers, docs, and messaging channels, so it can execute work and not only rewrite issue text.