melchizedek

status: active · source

Melchizedek is a headless Node.js CLI for running hierarchical agent graphs — called Syndicates — built on the Google Agent Development Kit. It’s the reference implementation for many of the orchestration ideas discussed in the posts: delegation, critic loops, hierarchical task decomposition, and long-term memory.

what it does

why it matters for this curriculum

Most agent frameworks hide the orchestration inside code. Melchizedek makes the shape of a multi-agent system a readable artifact — you can diff two syndicates the way you diff two configs. For teaching, that’s the point: the architecture of delegation is on the page, not buried in a call stack.

Posts that use melchizedek as their worked example will link here, and this page will grow into the framework’s public home — walkthroughs, example syndicates, and eventually live demos served from its A2A mode.

example syndicates

SyndicatePattern it demonstrates
Global Synthesis Councilparallel research + synthesis
Delegation routerrouting work to specialist subagents
Critic workflowstructured review loops
Hierarchical decompositionbreaking goals into subtasks
Financial Councilmulti-analyst report generation
Style Councilvoice as engineered communication laws
Image Productionspec-first generation + blind inventory / spec audit

Each pattern above is taught hands-on in the curriculum, with the syndicate’s verbatim YAML as a download.

api keys required

One key runs the whole curriculum; the rest unlock specific tiers. What each costs, honestly:

KeyUnlocksCost
GOOGLE_GENAI_API_KEYevery syndicate — all Gemini inference, search grounding, and the embedding model behind long-term memoryfree at aistudio.google.com; the free tier covers every text syndicate AND the memory embeddings. The image-generation model alone is paid-tier only (no free-tier access), and heavy search grounding draws paid quota
ANTHROPIC_API_KEYoptional — only agents with claude-* model ids (the Claude Chat example, or any agent you point at Claude)paid — usage-billed, no free tier
Supabase URL + service_role keyoptional — persistent sessions and long-term memory (Knowledge Keeper, Patient Advocate)free — the free project tier is plenty; run the schema + hardening SQL from the repo docs
A2A_SERVER_SECRETserving any syndicate as an authenticated A2A endpointfree — not a vendor key; you generate it yourself (openssl rand -hex 32)

The private financial syndicates (the Financial Council pattern) add market-data keys on top: price and fundamentals data comes from Yahoo Finance without a key, but technical indicators come from TAAPI, a paid subscription — without it the indicator tool falls back to slower, manually computed values from Yahoo history and labels them as such. Running the financial stack fully means paying for TAAPI; everything the public repo and the curriculum teach runs without it.

Set it up with your coding agent: melchizedek-agent-setup.md — a paste-ready prompt that has your coding agent do the machine steps, the steps that stay yours (keys, database), how to begin testing the agents, and the follow-up prompts for wiring a syndicate into your own app. The same file ships in the repo as AGENT_SETUP.md.

Source code and full documentation live in the public repository: github.com/jhwadman/melchizedek-agents — every syndicate the curriculum teaches, the structured-memory pipeline, the A2A server, and the database schema, with quickstart and deployment docs. (The Financial Council pattern remains private; the repository ships the teaching syndicates.)