Open office →

Consilium Router

by Synenergy

One question. A council of AI minds. One vetted answer.

Need a second opinion? Several models answer and disagree in the open. Need answers from a pile of files that will not fit one prompt? Consilium reads your documents with quotes, checks them, and shows the cost — without stuffing everything into the expensive main model. One API.

Blind spots — and context that does not fit.

One model means one perspective — and one set of hallucinations. Ask several by hand and you still reconcile the pile yourself. And when the real work is a stack of specs, logs, and notes, cramming it all into one frontier chat wastes money and still loses the thread. Consilium covers both: a plural panel for open judgment, and a document mode that works through large context with quotes, a quote-check, and a visible bill.

What it's used for

Modes

Why Consilium

How it works

  1. Send one request

    your prompt and how wide a panel you want.

  2. The panel works

    independent answers, cross-examination, fusion.

  3. You get the verdict

    one answer, with disagreements surfaced, not hidden.

Consilium as a provider for agents

Point Cursor, Claude, Codex, Hermes, or OpenClaw at Consilium — “Your documents” when the pile will not fit one prompt (quotes + cost control), a panel for a plural second opinion, or one model for everyday work. Broader is not always more accurate.

Route Lab

Research which models and routes fit a class of tasks — before you hard-code a default. Free: discover, propose, stub-benchmark. Paid: route_lab_run_experiment (approve spend). Not a substitute for compare, deliberate, vote, or “Your documents.”

Case: when Route Lab pays off · docs: ROUTE_LAB.md.

Agent model picks

When you set base_url to Consilium /v1, start from these solo roles — not a single “best model.” Vendor agent claims (including Meta on Llama tool use) are hypotheses until we publish our own harness ratings. Panel fuse is separate: panel=diversified* via MCP.

Role model id Best for
Controller (default) meta-llama/llama-4-maverick Tool loops, schema follow-through, short agent steps.
Planner deepseek/deepseek-v4-pro Architecture, trade-offs, multi-step plans.
Implementer openai/gpt-oss-120b Code-shaped edits and patches.
Skeptic mistralai/mistral-large-2512 Independent critique before merge.
Cheap worker openai/gpt-4.1-mini Mechanical chores, high volume.
Fast / light google/gemma-4-31b-it Quick drafts when cost and latency matter.

Subagents: architect → DeepSeek V4 · implementer → gpt-oss-120b · skeptic → Mistral Large · orchestrator → Llama 4 Maverick. Full notes: agent_model_picks.md.

Connect / verify

Already have a Consilium service Bearer from an operator? Download the auth smoke script, then run it locally — it checks /health, /v1/models, and a tiny non-stream chat. It does not create tokens and never prints yours.

curl -fsSL https://consilium.synenergy.ai/connect.sh -o consilium-auth.sh
chmod +x consilium-auth.sh
CONSILIUM_TOKEN=… ./consilium-auth.sh

Prefer download-then-run. Optional pipe: curl -fsSL …/connect.sh | bash -s -- "$CONSILIUM_TOKEN". Hermes / OpenAI drop-in: base_url=https://consilium.synenergy.ai/v1. Default agent solo: model=meta-llama/llama-4-maverick (see agent model picks).

For assistants. Panel = second opinion on a question. Your documents = answers with quotes from files you provide (same connection; after an update, reconnect once so new tools appear). Route Lab = research a default route for a class of tasks before you hard-code it — not for one-shot user questions. A normal single-model chat link alone does not run “Your documents” or Lab.

Stop betting on a single model.

Early access is limited — join the waitlist and we'll send your API key as soon as a seat opens.