TanStack
Featured
router
TanStack Router is a type-safe, data-driven React router with built-in caching, prefetching, and nested layouts, while TanStack Start extends it into a full-stack SSR framework.
AI repository intelligence
FR-AI / ANALYSISWhy it is worth attention
It implements the 'architect/editor' fusion pattern as a first-class, on-camera-clear workflow with hard-labeled roles, a gate-first validation loop, and per-line provenance, allowing engineers to combine compute instead of choosing a single model.
Who it is for
- Developers using AI coding agents (Claude Code, Pi) who want to leverage multiple models
- Teams evaluating frontier models for coding tasks and needing a systematic comparison mechanism
- Engineers building multi-agent workflows or extending agentic coding harnesses
- Researchers and practitioners interested in agentic engineering and model fusion patterns
Use cases
- Get two independent model perspectives on a coding question (/opinion)
- Fuse plans or code from two models into a single, attributed result (/fusion)
- Automatically validate a build against a pre-designed acceptance gate (/auto-validate)
- Chain opinion, fusion, and validation to run a micro-software development lifecycle in one session
Strengths
- Concrete three-command value ladder (opinion, fusion, auto-validate) on the same two agents
- Clean-room child processes with no skills, extensions, or context files for deterministic behavior
- Gate-first validation loop that designs acceptance criteria before building, preventing self-grading
- Per-line provenance and attribution (Consensus & Divergence) in fused outputs
Considerations
- Requires specific external tools and API keys (Pi, just, jq, uv, Anthropic/OpenAI keys)
- Parallel workers can clobber files if asked to write the same path without using identity-in-filename
- Stale persistent architect sessions may need manual reset (/fh-reset), and Anthropic usage-policy false positives can occur on fable-5 with long transcripts
README quick start
fusion-harness
Fuse frontier models instead of racing them. AND, not OR. A standalone Pi coding agent extension harness for two-model agentic engineering.
📺 Watch this video to get the full breakdown of this codebase: GPT-5.6 Sol vs Fable 5 Is the Wrong Question (Fusion) on YouTube
"Which model is best" is a benchmark question, not an engineering question. One model plans, another builds, and the results fuse: you combine compute instead of selecting it. Aider called the pattern architect/editor (the original fusion); Devin calls it fusion; OpenRouter calls it model fusion. This repo makes the pattern a first-class, on-camera-clear workflow: two hard-labeled agents, a gate-first validation loop, and attributed fusion. You don't have to pick a winner when you can hire both.
Install
Agentic Install
claude "/install" # runs the /install slash command in Claude Code (or Pi, or your favorite agentic coding tool)
The /install command lives at .claude/commands/install.md and handles toolchain checks, key checks, and project-specific setup.
Manual Install
npm install -g @earendil-works/pi-coding-agent # the Pi coding agent
brew install just jq uv # task runner, json inspection, gate runner
printf 'ANTHROPIC_API_KEY=sk-ant-...\nOPENAI_API_KEY=sk-...\n' >> .env # architect + builder keys
just fh-workhorse # launch on the cheap test pair
Why this exists
Every frontier release restarts the same argument: GPT-5.6 Sol or Fable 5? Benchmarks crown a winner, teams switch, and next quarter the crown moves. Meanwhile the two models are genuinely different animals: one plans and critiques with more depth, the other ships working diffs faster. Picking one means losing the other's edge on every single task.
The deeper problem is review, the second constraint of agentic engineering. A single unchecked agent drif
Related repositories
Similar projects matched by category, topics, and programming language.
vercel-labs
Featured
scriptc
scriptc compiles ordinary TypeScript into small, fast native executables without needing Node.js, V8, or any JavaScript runtime in the binary.
Jakubantalik
Featured
thinking-orbs
A React component library that renders six hand-tuned animated thought orb loading indicators on a plain 2D canvas, with two purpose-tuned sizes and automatic theme detection for AI and agent UIs.