Model fusion for Pi agents

One prompt. A panel of models. One answer you can trust.

Pi Fusion turns a single high-stakes prompt into independent model answers, surfaces contradictions instead of hiding them, and lets a judge model synthesize, verify, and report the final answer — right inside Pi.

Install Pi Fusion See the workflow Open GitHub
Install 
pi install git:https://github.com/aa2246740/pi-fusion@main

You choose the models · Optional evidence tools · Local artifacts and cost reporting

P1
P2
P3
P4
Judge
final-answer.mdConsensus + caveats

The single-model problem

One model answer isn’t always enough.

When the stakes are high, a single response can miss tradeoffs, bury contradictions, or commit to one viewpoint before alternatives are even considered.

The fusion answer

Run a panel. Reconcile differences. Decide with evidence.

Pi Fusion runs multiple participant models in parallel, compares their answers, and uses a judge model to synthesize a final response — with optional evidence gathering, verification, and durable artifacts kept locally.

Capabilities

Built for decisions that deserve more than one guess.

Use it for research, planning, architecture decisions, debugging hypotheses, code review, vendor comparisons, writing, and document synthesis.

01

Parallel participant models

Independent answers from multiple models, side by side.

02

Judge synthesis

A judge model reconciles, notes contradictions, and reports the final answer.

03

Verification & revision

Optionally re-check and refine before the answer is final.

04

Optional evidence layer

Connect provider-agnostic search and fetch tools when current, sourced answers matter.

05

Local artifacts & costs

Evidence summaries, token usage, and cost reporting stay with you.

06

Fallback & retry policy

Configurable fallback and retry behavior keeps panel runs resilient.

Workflow

From prompt to verified artifact.

The panel fans out, evidence is attached when available, and the judge turns disagreement into a stronger answer.

  1. 01

    Prompt in

    One prompt enters the fusion panel.

  2. 02

    Parallel answers

    Participant models respond independently.

  3. 03

    Evidence optional

    Search, fetch, and local read-only context can be used when configured.

  4. 04

    Judge synthesis

    The judge compares agreements, contradictions, and missing evidence.

  5. 05

    Verified artifact

    The final answer, evidence summary, token usage, and cost report are saved locally.

Pi-native

Three commands. That’s the surface area.

Configure the panel, diagnose availability, then run fusion from the place you already work.

Commands
/pi-fusion-config       Configure participants, judge, fallbacks, tools
/pi-fusion-doctor       Diagnose model and evidence backend availability
/pi-fusion <prompt>     Run a fusion panel
Examples
/pi-fusion Should we migrate this module to a plugin architecture?
/pi-fusion --fast Summarize the tradeoffs of these three plans.
/pi-fusion --quality Compare vendors and cite current sources.

DRACO benchmark

Pi Fusion exceeds the Fusion API budget baseline.

Pi Fusion is not just a demo of multi-model prompting. We tested it on the same DRACO 10-case benchmark protocol used to evaluate Fusion API budget mode. Pi Fusion exceeded the 64.70 Fusion API budget baseline, reaching 66.40 in full validation and 66.20 in the latest repeat validation, with all 10 cases completed and no judge failures.

Best validation66.40
Delta vs budget+1.70
Judge failures0
System / runfull10 scoreΔ vs Fusion API budget
Fusion API budget baseline64.70—
Pi Fusion kept validation65.30+0.60
Pi Fusion best validation66.40+1.70
Pi Fusion latest validation66.20+1.50

Generation used sanitized prompt-only case files. The benchmark answer/rubric/scoring artifacts were not available to Pi Fusion during generation and were used only after generation by the scorer.

Safety & control

Powerful tools, kept on a short leash.

No multi-agent writes to your real workspace. Evidence and artifacts are explicit, reviewable, and local.

Sandboxed bash

Deterministic calculations run in a sandboxed environment.

Read-only local context

Imported files are explicit evidence, not hidden state.

Optional backends

Fusion still works without search or fetch tools.

Pi-native control

You choose the models, fallbacks, tools, and reporting behavior.

Docs

English-first repo, Chinese docs included.

The GitHub repository is English-first for open-source discoverability, with Chinese documentation for local users and contributors.

README Chinese README Benchmark notes Chinese benchmark notes

Install

Put your next hard question to a panel.

Install Pi Fusion, configure your participant and judge models, then run your first fusion panel in minutes.

Open GitHub Configure models Run /pi-fusion-doctor