Deepank308/hermes-swe-agent

Autonomous AI coding agent triggered by Linear tickets — spins up full dev environments on EC2, writes code, runs tests, and opens PRs with live preview URLs.

11Stars on the repository
8Mods indexed here, across every type
4mo agoLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown

setup

02

Deepank308/hermes-swe-agent

Skill Claude CodeCodex

Interactive guided setup for self-hosting this infrastructure. Walks through .env.local configuration, repos.json, running setup.sh, connecting Linear, and optional AMI baking.

11 4mo ago A 36 tokens original MIT

debugging

03

Deepank308/hermes-swe-agent

Skill Claude CodeCodex

End-to-end workflow for bug reports, production errors, Sentry issues, and regressions. Covers investigation, reproduction, fix, verification, and PR creation.

11 4mo ago A 35 tokens original MIT

full-development

04

Deepank308/hermes-swe-agent

Skill Claude CodeCodex

End-to-end workflow for feature requests, enhancements, refactors, and tasks. Covers planning, TDD implementation, verification, integration testing, and PR creation.

11 4mo ago A 35 tokens original MIT

preview

05

Deepank308/hermes-swe-agent

Skill Claude CodeCodex

Launch a live preview environment from .claude/launch.json. Use after git push or when the user asks to preview a specific service.

11 4mo ago A 30 tokens original MIT

simple-question

06

Deepank308/hermes-swe-agent

Skill Claude CodeCodex

Workflow for questions, clarifications, and information requests. Researches the codebase and answers on the Linear ticket without making code changes.

11 4mo ago A 30 tokens original MIT

At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: