--- slug: "figmirror" source_type: "readme" source_url: "https://cdn.jsdelivr.net/gh/vila-lab/figmirror@main/README.md" repo: "https://github.com/vila-lab/figmirror" source_file: "README.md" branch: "main" ---

FigMirror: Plot Your Data in Any Paper's Style.
Pick a reference figure, paste your data, and get an editable matplotlib script plus a camera-ready PDF.

FigMirror turns repeated plotting-code edits into a polished paper figure

English | 中文

🔥 Milestones

- **Jun 1, 2026 — FigMirror release:** shipped FigMirror as Claude Code and Codex skills, with a local Web UI for upload, iteration browsing, and refinement. - **Jun 17, 2026 — Algorithm update:** refined the Codex path with role-separated Drawer / Reviewer agents, far-near visual review views, reviewer bounding boxes, and annotated feedback passed into the next iteration. - **Jul 1, 2026 — Evaluation update:** built an internal hybrid style scorer for repeatable method comparison. - Future — Paper release: release the scorer protocol, benchmark design, baselines, and analysis.

Showcase

FigMirror uses a reference figure as the style target, then renders your data through an iterative Drawer / Reviewer loop until the output looks like it belongs in the same paper family.

Reference	FigMirror Output

Reference	FigMirror Output	Reference	FigMirror Output

_{No high-quality reference at hand? Start from 139 paper figures across 25 chart families.}

Quick Start

Install With Your Claude / Codex

Already inside Claude Code or Codex? Paste this and let the agent do the setup: ```text Install FigMirror for me: https://github.com/VILA-Lab/FigMirror ```

Web UI

Use this when you want upload, preview, iteration history, and refinement in a browser. If `uv` is missing: `python3 -m pip install uv`. ```bash git clone https://github.com/VILA-Lab/FigMirror.git && cd FigMirror bash scripts/install.sh uv run python scripts/figcopy_serve.py --workspace .artifacts/figmirror-workspace --backend codex ``` Open `http://127.0.0.1:8765/`. The installer auto-detects Claude Code and Codex. For Codex, it installs the `figmirror` skill plus the `figmirror-drawer` and `figmirror-reviewer` custom agents used by the current role-separated algorithm.

Skill Only

Use this when you want FigMirror inside your agent, no web UI. ```bash curl -fsSL https://raw.githubusercontent.com/VILA-Lab/FigMirror/main/scripts/install.sh | bash ``` Target one runtime explicitly: ```bash curl -fsSL https://raw.githubusercontent.com/VILA-Lab/FigMirror/main/scripts/install.sh | bash -s -- --codex curl -fsSL https://raw.githubusercontent.com/VILA-Lab/FigMirror/main/scripts/install.sh | bash -s -- --claude curl -fsSL https://raw.githubusercontent.com/VILA-Lab/FigMirror/main/scripts/install.sh | bash -s -- --all ``` Then attach a paper-figure screenshot, paste your data, and ask: ```text Use FigMirror to mirror this figure's style with my data. ``` Need manual target selection, Claude backend, or troubleshooting? See [Detailed Install](https://github.com/vila-lab/figmirror/blob/HEAD/docs/install.md).

How It Works

FigMirror architecture loop and grounded measurement algorithm

> Illustration of FigMirror. The left panel shows the core agentic loop; the right panel introduces Grounded Measurement. FigMirror uses an agentic Drawer-Reviewer loop. In the current Codex path, a top-level Orchestrator delegates drawing to a named Drawer agent and visual audit to a named Reviewer agent. The Reviewer sees a far-view composite plus full-resolution source and candidate views, returns structured feedback with bounding boxes, and the Orchestrator turns that feedback into an annotated image and notes for the next Drawer pass. The Drawer renders a candidate figure with ***Grounded Measurement***. The Reviewer compares it with the reference image, then returns a visual review, a revision checklist, and a preserve list. The preserve list accumulates across iterations as an anchor against style drift. The Aesthetic Lib provides fallback principles, style rules, and figure properties when the agents disagree or the Drawer has low confidence. For 3D figures, FigMirror adds geometry-aware prompting for camera, scale, surfaces, lighting, and repair checks, helping the loop preserve the 3D composition of the reference figure while producing editable matplotlib code. ***Grounded Measurement*** builds on two properties of computer-use-trained foundation models: *Measurement with Axis*, which lets the model return x/y coordinates for visual targets; and *Resonate with Code*, which turns those coordinates into executable checks, such as cropping a line segment and reading its color from pixels. For the detailed algorithm, architecture, product envelope, and spec map, read [docs/method.md](https://github.com/vila-lab/figmirror/blob/HEAD/docs/method.md). For the web UI, see [scripts/README_figcopy_serve.md](https://github.com/vila-lab/figmirror/blob/HEAD/scripts/README_figcopy_serve.md).

Contributing

FigMirror welcomes contributions! Open an issue for bugs, broken installs, or figure cases FigMirror should learn from; open a PR for showcase examples, prompt improvements, UI polish, or small regression tests. - **Showcase cases:** add reference/output pairs that prove the method across chart families. - **UI polish:** make the web workflow feel instant, legible, and forgiving. - **Prompt and reviewer quality:** improve the Drawer / Reviewer loop without weakening the grounding rules. - **Evaluation:** add reproducible cases that catch visual drift, floor violations, and broken exports. Start with [docs/contributing.md](https://github.com/vila-lab/figmirror/blob/HEAD/docs/contributing.md). Good first PRs include adding a showcase example, improving a web UI interaction, tightening install docs, or adding a small regression test around runner behavior.

Star History

_{Rendered by Star History from GitHub stargazer data, so the chart stays current as the repository grows.}

Roadmap

- [x] Ship the reference-to-figure loop as Codex and Claude Code skills. - [x] Add a local Web UI for upload, iteration browsing, and refinement. - [x] Publish a 139-figure gallery so users can start without hunting for references. - [x] Refine the Codex algorithm with role-separated Drawer / Reviewer agents and bbox-annotated visual feedback. - [x] Build an internal hybrid style scorer for repeatable method comparison. - [ ] Release the scorer protocol, benchmark design, baselines, and analysis in a paper. - [ ] Curate a public benchmark set with reference figures, input data, generated outputs, and human preference labels. - [ ] Harden install and runtime docs for more OpenAI-compatible and local-agent backends.