Workflows

14 recipes, filter by use case, license, or difficulty.

SecurityFreeMachine-verified

STACK: allow GitHub issue reads and block issue creation

Prepare a narrowly scoped STACK GitHub Passport that permits one issue-list read while denying issue creation, with the submitted runner contract verified offline and live provider enforcement kept as a separate credentialed check.

STACK· advanced
CodingFreeAuthor-tested

Oh My Design: evidence-led UI work with deterministic delivery gates

Turn an AI-assisted interface request into an evidence-backed brief, traceable copy, deliberate structure, one production build, and a blind rendered critique, while using Oh My Design's local CLI gates to catch contract drift, stale source, unsafe stack replacement, and reviewable UI-risk signals before delivery.

Oh My Design· advanced
Local InferenceFreeMachine-verified

Unsloth: write parametric memory in with a fine-tune config

Write a valid Unsloth fine-tune config that bakes stable, always-needed domain knowledge into a small model so the knowledge is native rather than carried in a prompt on every call.

Unsloth· advanced
AgentsFreeMachine-verified

Text your own AI assistant on WhatsApp: Hermes wired to FreeLLMAPI

Point Hermes Agent at a FreeLLMAPI backend and connect it to WhatsApp, so a memory-keeping assistant runs 24/7 on a free always-on server and costs nothing per message, with the wiring validated before you link a number.

Hermes AgentFreeLLMAPI· advanced
AgentsFreeMachine-verified

Run GLM-5.2 fully local on a Mac Studio and drive it with Hermes

Serve GLM-5.2's 2-bit GGUF on a Mac Studio over an OpenAI-compatible endpoint, point Hermes at it as a custom provider, and hand it long hands-off agentic jobs.

Hermes AgentLM StudioGLM-5.2· advanced
Local InferenceFreeMachine-verified

Serve NVIDIA Nemotron 3 Ultra yourself for high-throughput agents (vLLM)

Stand up the NVFP4 Nemotron 3 Ultra checkpoint as an OpenAI-compatible endpoint for fast, long-running agent loops, validated serve flags + endpoint.

vLLMNVIDIA Nemotron 3 Ultra· advanced
Local InferenceFreeMachine-verified

Serve GLM-5.1 yourself for long-horizon agentic coding (vLLM)

Stand up the MIT-licensed GLM-5.1 FP8 checkpoint as an OpenAI-compatible endpoint for long agentic runs, validated serve config + endpoint.

vLLMGLM-5.2· advanced
Local InferenceFreeMachine-verified

Serve MiniMax M3 yourself for agentic coding (vLLM)

Stand up MiniMax M3 on an 8x H200 node as an OpenAI-compatible endpoint and point any coding agent at it, validated serve flags + endpoint config.

vLLMMiniMax M3· advanced
CodingFreeMachine-verified

OpenHands + Fable 5: Autonomous Issue to Pull Request

Hand Fable 5 a GitHub issue and let OpenHands plan, edit, run tests, and open a PR in a Docker sandbox.

OpenHands· advanced
SecurityFreeMachine-verified

Claude Code Auto Mode: A Classifier Instead of an Allowlist

Set Auto Mode as your default so a classifier reviews each action instead of pre-listing every command.

Claude Code· advanced
AgentsFreeMachine-verified

Hermes Kanban: The Swarm

Fan a goal out to N parallel workers, gate a verifier on all of them, then a synthesizer on the verifier.

Hermes Agent· advanced
AgentsFreeLocal hardware

Fine-Tune an Open LLM to Make It Yours

Adapt an open-weight model to your domain with a small dataset.

vLLM· advanced
ResearchFreeVerified on a mock

Hermes + NotebookLM "Second Brain"

Pair Hermes with NotebookLM to build a self-researching, self-teaching knowledge system.

Replaces Perplexity Pro

Hermes AgentObsidianNotebookLM· advanced
Agents$5/monthLocal hardware

Self-Hosted Self-Improving Agent with Hermes

Stand up a Hermes agent that remembers and improves over time on your own VPS.

Hermes AgentOllamaHetzner VPS· advanced