Tools

Browser control from the browser-use team: an editable CDP connection lets agents drive the Chrome you are already using, writing missing helper functions as they go and keeping them for reuse. Also offers an MCP server. Allow remote debugging in Chrome on first use.

Version datasets and models the way Git versions code: data lives in remote storage like S3 or GCS while versions are tracked in your Git repo. Also offers reproducible pipelines and local experiment tracking, rerunning only the steps affected by a change.

Turns 18 kinds of sources, including doc sites, GitHub repos, PDFs and videos, into skill packages for Claude and other platforms, or exports RAG chunks and vector store data. Optional MCP server, and it can call a local agent like Claude Code to enrich content. Needs Python 3.10+.

Simon Willison's LLM CLI and Python library: call OpenAI, Claude, Gemini and local models from the terminal, with conversations logged to SQLite automatically, plus embeddings, structured extraction, tool calling and a plugin system.

ByteDance's open-source, general software engineering agent: trae-cli edits files and runs commands from natural language, supports multiple model providers and MCP, and records full execution trajectories. Transparent design suits agent research and customization. Needs your own model API key.

Hugging Face's official skills: manage Hub models and datasets with the hf CLI, fine-tune language and vision models, run model evaluations, and build Gradio apps deployed to Spaces. Needs an HF account; cloud training on HF Jobs requires a paid plan.

Reads the exact position of every character, line and table cell in digital PDFs: the CLI exports layout-preserving text or CSV/JSON details, and the Python API extracts tables and form fields, ideal for invoices, statements and reports. Runs locally with Python; scans need OCR first.

High-accuracy retrieval-augmented Q&A over paper PDFs, text and Office documents, filling in citation metadata, checking retractions and attaching traceable sources to answers. Provides the pqa CLI and a Python library. Needs an LLM API key by default; local models can be configured.

Lightweight OCR built on PaddleOCR models converted to ONNX, recognizing Chinese and English by default on CPU alone. The rapidocr CLI reads text from screenshots, photos and scanned page images. Needs Python; downloads models on first run, then works offline. Convert PDFs to images first.

Offline speech toolkit for Apple Silicon Macs: CLI text-to-speech (including Chinese and voice cloning) and speech-to-text, for voicing lessons and explainer videos or transcribing lectures and interviews, with data staying local. Needs an M-series Mac and Python 3.10+; MP3 export needs ffmpeg.

Open-source LLM evaluation platform: one opencompass command picks the model and datasets and runs the evaluation across hundreds of benchmarks. Works with local Hugging Face models and API models, with vLLM and LMDeploy for faster inference.

Creates, edits and validates reproducible Python and SQL Jupyter notebooks: organizes cells as reports or tutorials, checks conclusions against actual output and reruns top to bottom before handoff. Maintained by OpenAI in the Data Analytics plugin of openai/plugins.

Python library and CLI for extracting main web content: fetches pages, crawls via sitemaps and RSS feeds, strips headers, footers and other noise, and outputs TXT, Markdown, JSON, XML and more with metadata. Also processes downloaded HTML offline.

Language and toolset for double-entry bookkeeping in text files: bean-check validates the ledger, bean-format normalizes it, and Fava or beanquery handle reports and queries. Plain-text ledgers are easy for agents to generate and keep in version control.

Create, read and modify xlsx workbooks without Microsoft Excel installed: formulas, formatting and conditional formatting, charts, pivot tables and tables. Runs locally over stdio or as a remote HTTP service.

Hugging Face's official hf CLI: search, download and upload models and datasets, manage repos and storage buckets, and run jobs on Hugging Face's cloud. Output adapts automatically for agents, and hf skills add installs companion skills. Uploads and similar actions need a login.

Open-source PDF table extraction with a camelot CLI: exports tables from financial reports, bank statements and statistical reports to Excel, CSV or Markdown, with an accuracy score. Needs Python 3.10+; handles text-based PDFs by default, scans need the ml and ocr extras. Double-check results.

Unified search across 20+ academic sources including arXiv, PubMed, bioRxiv, Semantic Scholar and OpenAlex, returning deduplicated, normalized results and downloading full text via open-access channels first. Most sources need no API key.

Python library with a built-in MCP server for US SEC EDGAR data: search 10-K, 10-Q, 8-K and other filings and read XBRL-standardized financial statements, Form 4 insider trades and 13F holdings. Free with no API key; just set an EDGAR_IDENTITY.

Runs open image models like FLUX, Qwen Image and Z-Image locally on a Mac: text-to-image, reference-based edits, inpainting and upscaling, all on-device. Needs Apple Silicon and uv; the first run downloads models and is slow. Check each model's license before commercial use.

Extracts issuer, amount, date, invoice number and other fields from PDF invoices using YAML/JSON templates, exporting CSV, JSON or XML. Ships several text-extraction backends, OCR for scanned invoices and an optional AI fallback.

Self-hostable long-term memory for agents, offering MCP, a REST API and a web dashboard: semantic search, knowledge graph and automatic memory consolidation. Embeddings are computed locally; choose SQLite, Cloudflare or Milvus as the backend.

Connects agents to live Jupyter notebooks: read, write, insert and execute cells and read multimodal outputs like charts, for interactive data analysis. Bring your own JupyterLab or JupyterHub; open source, maintained by Datalayer.

LangChain's official skill collection: framework selection, quickstarts, middleware, persistence, human-in-the-loop approval, RAG and eval design across LangChain, LangGraph and Deep Agents, in Python and TypeScript. Also installable as a Claude Code plugin. Still in early development.