SuperAPI AI Directory
Partner with us中文AI newsFavorites

All AI tools

35,738 results · Page 331 of 993

PaperBanana

AI search

PaperBanana is a chart workspace for academic scenarios. Combined with PaperVizAgent technology, it turns research notes, method descriptions, and chart goals into reviewable first drafts. It first reads the research background, then plans the panel structure, labels, and flow, and subsequently generates chart drafts, with support for exporting PNG, SVG, PDF, and other formats for papers, posters, or slides. The official website offers three paid plans, aimed respectively at individual researchers, frequently publishing researchers, and laboratories and teams, including different credits, resolutions, and export formats.

Read more

PaperBanana

AI search

PaperBanana is an academic illustration automation tool for researchers that converts paper text into publication-ready scientific figures through multi-agent collaboration. It supports the generation of methodology diagrams, statistical charts, system architecture diagrams, flowcharts, and poster assets, among others. Users only need to input a natural language description and select a visual style to obtain a scientific illustration within seconds. Its statistical charts ensure numerical accuracy by generating executable Python Matplotlib code, avoiding the numerical hallucination problems common in general-purpose image generators; at the same time, it provides aesthetic enhancement features that can optimize hand-drawn sketches or whiteboard notes into professional illustrations that meet the standards of top conferences.

Read more

PaperBanana-Pro

AI search

PaperBanana-Pro (Paper Banana) is a multi-agent system for academic paper figure generation, independently evolved from the original PaperBanana, having undergone 21 rounds of engineering refinement and 70+ unit test coverage, positioned as a product-grade tool for daily use. By inputting a paper's method section and figure caption, it concurrently generates multiple scientific figure candidates with one click, and supports management features such as favoriting, selecting, or eliminating candidates, ZIP batch packaging and download, and evolution timeline replay. The system provides a fully Chinese GUI and streaming interaction, with a built-in independent refinement workbench that allows setting target resolution and aspect ratio; each refinement round forms a version chain, supporting continuation from or rollback to any historical version. After installation, the paperbanana command can be used, or the GUI can be launched via streamlit run demo.py, or the CLI via python main.py --help. It supports four Providers: Gemini, OpenAI, Openrouter, and Evolink, and can connect to any OpenAI-compatible API. The default text model is gemini-3.8-flash, and the image generation model is gemini-nano-banana-2.1. It is suitable for batch dataset runs and artifact archiving. Note: The original PaperBanana methodology has been patented and must not be used for commercial purposes; this restriction also applies to this extended version.

Read more

PaperFit

AI search

PaperFit is a LaTeX paper typesetting Agent System for Claude Code, Codex, and Cursor. A paper passing LaTeX compilation does not mean the layout is acceptable. Common visual-level problems such as stacked floats, large gaps in two-column layouts, inconsistent table styles, overflowing equations or tables, and objects losing control of their positions after template migration are difficult to find from the .log file alone. PaperFit treats typesetting as a visual closed-loop task: first render the PDF into page images, then judge problems by combining LaTeX logs, cross-references, and template rules, and finally write back to the source and re-render for acceptance. Its goal is not to replace the author in writing the paper, but to hand over the repetitive work of "looking at the layout, fixing the source, and checking again" to the Agent. It is suitable for pre-submission checks, template migration, page-count compression, and fixing wide tables and floats. Users only need to describe the goal in natural language in the project root directory, and it will automatically complete compilation, page-image rendering, visual diagnosis, source repair, and final acceptance.

Read more

Paperspace

AI developer platforms

Paperspace is a cloud GPU computing platform that has now merged into DigitalOcean. It provides GPU instances such as NVIDIA H100 for accelerating AI training, complex simulations, and rendering, supporting the complete process from proof of concept to production deployment, including Notebooks, model training and fine-tuning, API endpoint conversion, and more. The platform emphasizes speed, simplicity, and scalability, offering pay-as-you-go pricing, preconfigured templates, team management, and other features, targeting individual developers and enterprise teams.

Read more

Parallel

AI finance

Parallel is a financial planning software for startups that manages company finances without spreadsheets. It can sync accounting data such as QuickBooks or Puzzle, automatically generate real-time forecasts based on actual data, and help founders track cash runway, plan hiring, model financing scenarios, and forecast revenue and cash flow. Users can build scenario models in minutes and see the impact of hiring, spending, or financing decisions on runway, burn rate, and revenue. A 15-day free trial is offered, no credit card required. The company says it is used by multiple startups, but the specific customer list and pricing are not yet available.

Read more

parallel-code

AI coding

Parallel Code is a free and open-source tool (MIT license) for scheduling multiple AI coding agents in parallel. It supports tools such as Claude Code, Codex CLI, Gemini CLI, and Copilot CLI, automatically creating a separate git branch and worktree for each task, so multiple agents can run simultaneously in the same interface without conflicts. Users can view the diff of each session, review, and merge results. It offers keyboard-first operation, a built-in diff viewer, code Q&A, mobile remote monitoring, and other features, making it suitable for developers who want to improve multitasking development efficiency.

Read more