Multi-agent discussion swarm for Hermes Agent
Find a file
2026-06-15 12:22:54 +00:00
examples Initial commit: hermes-swarm skill 2026-06-15 12:22:54 +00:00
scripts Initial commit: hermes-swarm skill 2026-06-15 12:22:54 +00:00
templates Initial commit: hermes-swarm skill 2026-06-15 12:22:54 +00:00
.gitignore Initial commit: hermes-swarm skill 2026-06-15 12:22:54 +00:00
LICENSE Initial commit: hermes-swarm skill 2026-06-15 12:22:54 +00:00
README.md Initial commit: hermes-swarm skill 2026-06-15 12:22:54 +00:00
SKILL.md Initial commit: hermes-swarm skill 2026-06-15 12:22:54 +00:00

hermes-swarm

Multi-agent discussion swarm for Hermes Agent. Replace one expensive reasoning model with several cheap models that argue, refine, and converge.

What it does

  • Runs a round-robin discussion between Hermes profiles via Redis Pub/Sub.
  • Each agent sees the full transcript before replying.
  • First agent synthesizes the final answer.
  • Saves transcript and final answer as Markdown.

Install

git clone https://forgejo.redtask.ru/youruser/hermes-swarm.git
cd hermes-swarm

Install dependency:

pip install redis

Quick start

  1. Start Redis:
docker compose -f templates/docker-compose.redis.yml up -d
  1. Add Hermes profiles (see templates/hermes-profiles.yaml).

  2. Run:

python3 scripts/swarm_chat.py \
  --topic "Refactor this function to use async SQLAlchemy" \
  --agents swarm-architect swarm-critic swarm-coder \
  --rounds 3

Environment variables

Variable Default
REDIS_URL `redis://localhost:***@dataclass
HERMES_WORKDIR .
HERMES_CMD hermes

Example use cases

  • Code review: feed a diff, let critic + reviewer + coder discuss.
  • Design decisions: compare two approaches with architect + critic.
  • Test planning: let tester + coder + architect write a test strategy.

License

MIT