Workflows

Orch8: validate a bounded durable ReAct loop before model or tool calls

Pin and structurally validate Orch8's durable ReAct sequence before deployment, so an unbounded loop, broken route, embedded endpoint, credential field, or unresolved block reference fails in CI before any model or tool can run.

agent-qa: validate Agent Skills before LLM-backed QA runs

Run agent-qa's deterministic skill-pack validator before its authoring, result-triage, or debug-fix skills can drive a model-backed web or mobile QA run, so missing metadata, references, or MCP guidance fail in CI first.

Advisor pattern: cap how often the expensive model gets called, and catch drift

Run a cheap executor with a rarely-consulted expensive advisor, but enforce a hard cap on advisor calls per task and a drift-check before the executor can keep going, so the benchmark's 63% discount doesn't quietly erode into nothing.

Wire GLM-5.2 into Hermes: valid route, 64k-context check, no key in config

Validate a Hermes Agent config that runs GLM-5.2 through a real provider route (direct Z.AI or OpenRouter), clears Hermes's 64k minimum context, and keeps the API key out of config.yaml, before you start a session.

Route through a gateway with a tested open-weights fallback

Keep model access from being a single point of failure: route through an OpenAI-compatible gateway and pin a fallback that is open-weights and has actually been tested, so a pulled or deprecated model is a two-minute config change, not a lost week.

Run GLM-5.2 for the bulk, escalate the hard turns to Opus 4.8

Wire a cost-routing config that sends most work to cheap hosted GLM-5.2 and only the hardest turns to Opus 4.8, instead of paying Opus prices for everything.

Teach OpenCode Go your weekly chore once, then run it in minutes

Capture a repeating chore as a reusable OpenCode command backed by the Go plan's models, so a two-hour weekly task becomes a five-minute run.

OrcaRouter: only fan out when it is worth it

Gate the expensive fan-out behind a difficulty condition so easy chat stays cheap and only hard requests pay for a panel.

OrcaRouter for coding: judge by passing tests, not by vibes

Fan a hard coding task out to a panel and keep the candidate whose patch actually passes your tests, using the tests_pass arbiter.

Rebuild Fable 5's deep-research fan-out on your own keys (OrcaRouter)

Fan a research prompt out to a panel of models you choose, then fuse or judge the answers with an arbiter, in a routing DSL you version and control.

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.

Turn a Hand-Drawn UI into Working Code with tldraw

Sketch a screen on an infinite canvas and have a vision model return a live, working version of it.

Obsidian Vault as the Core of Your Agent Harness

Use an Obsidian vault as the shared memory and control surface for your agents.

Hermes + NotebookLM "Second Brain"

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

Replaces Perplexity Pro

Persistent Memory for Codex using Obsidian

Give Codex durable, searchable long-term memory backed by an Obsidian vault.