Hermes Repo Agent
Long-running local repository work
Runs long, self-directed jobs across your local repo — a sweep over many files, a dependency upgrade, a cleanup. It scopes the work and gets that agreed first, since a long job with the wrong definition is the most expensive failure here. It reports progress in batches as it goes, because silence for two hundred file edits isn't acceptable output.
Add to your OasisConnects with
No app connections are included in this template. Check its foundation and setup requirements before your first run.
- +Custom toolConnect any other tool from thousands of available integrations.
How it runs
- Foundation
Hermes Agent
- Reasoning
- Medium effort
- Per run
- Up to 55 turns
- Memory
- Learns across runs
- Browsing
- Off
- Category
- Engineering
- Hermes
- Local
- Automation
Frequently asked questions
What repository jobs are a good fit for Hermes Repo Agent?
It handles long self-directed work such as a many-file sweep, dependency upgrade or cleanup across the local repository.
Why must Hermes Repo Agent agree the definition of a large cleanup first?
A long run with the wrong definition is expensive. It scopes the work and gets that definition agreed before broad edits begin.
How does Hermes Repo Agent make hundreds of file edits observable?
It reports progress in batches, so a long run does not go silent while changes accumulate across the repository.
Can Hermes Repo Agent handle a dependency upgrade that touches many files?
Yes. Dependency upgrades are one of its named long-running local repository jobs, alongside broad sweeps and cleanups.
Agents like this one
MCP Server Builder
Builds MCP servers that agents can actually use well. It designs the tool surface around real workflows rather than wrapping every API endpoint, because the tool list is a prompt and a bloated one degrades every call. Descriptions say when to use a tool and when not to, errors explain what to do differently, and each tool is tested against a realistic task.
Try this Agent
Oasis PlatformEngineeringSpreadsheet Cleanup
Takes the messy export and returns something you can analyse. It profiles the file first — fill rates, distinct values, the specific inconsistencies present — and agrees the target format before touching anything. Original values are preserved in adjacent columns so every change is reversible, and unparseable rows are flagged rather than dropped.
Try this AgentOasis PlatformOperationsJira Sprint Runner
The same sprint discipline for Jira. It audits for unestimated stories, missing acceptance criteria, unassigned work, tickets stuck beyond your team's norm, and subtasks out of sync with their parent. Findings are grouped by assignee so each person sees only their own list, and nothing transitions without approval.
Try this AgentOasis PlatformEngineeringAPI Docs Writer
Documents endpoints from the code that implements them, not from what the last doc said. Every parameter gets its real type, requiredness, default and constraints, and every error the endpoint can return is documented with what triggers it — the half that's usually missing and the half developers need. Discrepancies between existing docs and current behaviour are listed separately as bugs.
Try this AgentOasis PlatformEngineeringPi Dev Assistant
A general hand in your local checkout. It defaults to reading and explaining, makes small changes when asked, and shows the diff rather than describing it. When a request is ambiguous it asks instead of picking, and it never runs destructive git operations or touches files outside the repo it was pointed at.
Try this AgentOasis PlatformEngineeringNotion Workspace Librarian
Stops your Notion from rotting. It finds the duplicate pages, the stale docs still linked as current, the database rows missing required properties, and the titles that don't say what the page is. Nothing is ever deleted — it archives, and tells you what it archived.
Try this AgentOasis PlatformProductivityFrontend Design Reviewer
Reviews UI changes for what code review misses. It checks the states nobody builds — empty, loading, error, long content, slow network — real breakpoints rather than the one the developer had open, and accessibility properly: keyboard path, focus visibility, contrast, reduced-motion. Findings are ordered by user impact, and subjective taste is left out unless it breaks an established pattern.
Try this AgentOasis PlatformEngineeringResearch Synthesizer
Takes a pile of sources — papers, reports, transcripts, interviews — and produces the synthesis rather than a reading list. It organises by theme, shows where sources agree and whether they're genuinely independent or just citing each other, and never resolves a real conflict by averaging. It ends with the questions the evidence leaves open.
Try this AgentOasis PlatformResearchGrowth Researcher
Digs into a growth question until there's an answer with evidence behind it. It makes the question answerable first — which step, which segment, which source — then checks the boring explanations like broken tracking or an ended campaign before reaching for behavioural theories. You get the finding, the numbers supporting it, and an honest confidence level.
Try this AgentOasis PlatformResearchDevin CLI Task Runner
Hands a scoped, well-specified ticket to Devin in your local environment and keeps the loop tight. It restates the task as acceptance criteria before starting, which is the highest-value step given autonomous agents fail most often on under-specified work. It stays inside the stated scope and notes unrelated problems rather than expanding the change.
Try this AgentOasis PlatformEngineering
Put Hermes Repo Agent to work today
Add it to your Oasis, review its setup, and hand it the first task.