melchizedek
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
- Doctrine-driven agents — each syndicate member carries engineered laws, not just a persona: communication laws, memory doctrine, safety boundaries, research rules. The Patient Advocate cites the provenance of every remembered fact; the image pipeline’s inventory agent is structurally blind to expectations. Behavior is designed, then enforced.
- Memory that evolves — session transcripts distill into structured records (date, source, exact units, status, index keys); corrections supersede old records, which stay as linked history; recall runs on similarity, index keys, and dates together.
- Multi-model teams — Gemini natively, Claude via a bundled adapter. Each agent in a syndicate can run on a different provider.
- A2A service mode — any syndicate can be served as a stateless JSON-RPC agent-to-agent endpoint over HTTP, with bring-your-own-key routing so inference costs land on the caller.
- One readable file per team — the whole hierarchy (models, prompts, tools, delegation rules) declares itself in a single YAML document you can diff and teach from.
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
| Syndicate | Pattern it demonstrates |
|---|---|
| Global Synthesis Council | parallel research + synthesis |
| Delegation router | routing work to specialist subagents |
| Critic workflow | structured review loops |
| Hierarchical decomposition | breaking goals into subtasks |
| Financial Council | multi-analyst report generation |
| Style Council | voice as engineered communication laws |
| Image Production | spec-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:
| Key | Unlocks | Cost |
|---|---|---|
GOOGLE_GENAI_API_KEY | every syndicate — all Gemini inference, search grounding, and the embedding model behind long-term memory | free 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_KEY | optional — 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 key | optional — 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_SECRET | serving any syndicate as an authenticated A2A endpoint | free — 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.)