icon

sambaiz-net
github
places
board game arena
aws golang machinelearning kubernetes python etl gcp spark linux web ...

Splitting Tasks Fed into the Hermes Agent Kanban Across Multiple Agents

llm

Hermes Agent is an OSS agent that, in addition to an interactive TUI like Claude Code or Codex CLI, provides a resident gateway process that receives messages from cron, Slack, and other sources and processes them. It supports a variety of models and places no constraints on the environment that runs the gateway, so it avoids vendor lock-in. There is also an official cloud environment called Nous Portal. It often ships forward-looking features first, though similar features tend to be implemented later in other tools.

Install it and run the initial setup.

$ curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
$ hermes
...
Select provider:
  ↑↓ navigate  ENTER/SPACE select  ESC cancel

   (●) Nous Portal (Everything your agent needs, 300+ models with bundled tool use)
   (○) Fireworks AI (OpenAI-compatible direct model API)
   (○) OpenRouter (Pay-per-use API aggregator)
   (○) Mixture of Agents (named presets; aggregator acts after reference models)
   (○) NovitaAI (Cloud: Model API, Agent Sandbox, GPU Cloud)
   (○) LM Studio (Local desktop app with built-in model server)
   (○) Anthropic (Claude models via API key or Claude Code)
 → (○) OpenAI ▸ (Codex CLI or direct OpenAI API)
   (○) Qwen Cloud / DashScope (Qwen + multi-provider)
   (○) xAI Grok ▸ (Direct API or SuperGrok / Premium+ OAuth)
   (○) Xiaomi MiMo (MiMo-V2.5 and V2 models: pro, omni, flash)
   (○) Tencent TokenHub (Hy3 Preview via tokenhub.tencentmaas.com)
   (○) NVIDIA NIM (Nemotron models via build.nvidia.com or local NIM)
   (○) GitHub Copilot ▸ (GitHub token API or copilot --acp process)
   (○) Hugging Face Inference Providers
   (○) Google AI Studio (Native Gemini API)
   (○) Google Vertex AI (Gemini via GCP; OAuth2 service account or ADC, GCP billing/quotas)
   (○) DeepSeek (V3, R1, coder, direct API)
   (○) Z.AI / GLM (Zhipu direct API)
   (○) Kimi / Moonshot ▸ (Coding Plan, Moonshot global & China endpoints)
   (○) StepFun Step Plan (Agent / coding models via Step Plan API)
   (○) MiniMax ▸ (Global, OAuth Coding Plan & China endpoints)
   (○) Ollama Cloud (Cloud-hosted open models, ollama.com)
   (○) Arcee AI (Trinity models, direct API)

Start the gateway.

$ hermes gateway install
$ hermes gateway start

Open the Kanban on the dashboard and add a task to Triage. The gateway picks it up, the task starts, and its status is updated.

$ hermes dashboard
Kanban

By creating a Profile with its own configuration, skills, and memory, each task can be executed by a different agent. Specifying Profiles via swarm, or creating a task through triage, splits the work into tasks for a worker, verifier, and synthesizer. Workers run in parallel, and once all of them finish the verifier runs, and if verification passes the synthesizer runs in order.

$ hermes profile create researcher-a --description "Research official documentation and extract key technical facts"
$ hermes profile create researcher-b --description "Research community feedback, real-world usage, and case studies"
$ hermes profile create reviewer --description "Verify accuracy and completeness of research findings"
$ hermes profile create writer --description "Synthesize verified findings into a single coherent document"
$ for p in researcher-a researcher-b reviewer writer; do
    cp ~/.hermes/config.yaml ~/.hermes/profiles/$p/config.yaml
  done
$ hermes kanban swarm "Research the Hermes Kanban feature and write a summary" \
    --worker "researcher-a:Research official documentation" \
    --worker "researcher-b:Research community feedback and case studies" \
    --verifier reviewer \
    --synthesizer writer
# or
$ hermes kanban create "Research the Hermes Kanban feature and write a summary" --triage
Split tasks