Open source
Open source tools to make your agents document experts
Extend's OSS helps developers build AI pipelines that can handle the world's hardest docs.
Open Tools
UI Kit, templates, MCP, CLI, and SDKs for your agents
Extend on GitHub
Source for the UI Kit, CLI, SDKs, skills, and benchmarks
Open Benchmarks
Public datasets for parsing, extraction, and splitting
Open Tools
Everything your agent needs to ship a document pipeline
Start from a working recipe, connect your agent, and ship a review UI for the output. Each tool starts with one command or one link.
Extend UI Kit
React components for document apps
PDF, DOCX, XLSX, and CSV viewers, bounding box citations, file upload, and e-signature. Add components to your codebase from a shadcn registry and restyle them like your own.
- 15 components
- shadcn registry
- MIT
npx shadcn@latest add https://www.extend.ai/ui/r/styles/new-york/pdf-viewer.jsonExtend Templates
Ready-made pipelines for 50+ document types
Each recipe ships a sample document, schema, processor settings, expected output, and a provisioning script. Send one to Claude Code or Codex and adapt the pipeline it creates.
- 51 recipes
- workflow.json
- skill.md
https://www.extend.ai/template-catalog/llms.txtExtend MCP
Document tools for any MCP client
One hosted server gives Cursor, Claude Code, Codex, ChatGPT, and any MCP client tools to parse, extract, classify, split, and edit documents. Sign in with OAuth, nothing to install.
- 86 tools
- 9 tool groups
- OAuth
https://mcp.extend.ai/mcpExtend CLI
Document processing from the shell
Parse, extract, classify, split, and edit documents with one command. The setup wizard signs you in and installs a skill, so coding agents can drive the CLI too.
- Homebrew, npm, Go
- Agent skill included
- MIT
curl -fsSL https://extend.ai/install.sh | sh && extend setupExtend SDK
Typed API clients for your stack
Python, TypeScript, Java, and Go clients for parse, extract, classify, split, and edit, with polling and webhook helpers. Add the extend-api skill and your coding agent writes the integration for you.
- Python, TypeScript, Java, Go
- extend-api skill
- MIT
pip install extend-ainpm install extend-aigo get github.com/extend-hq/extend-go-sdknpx skills add extend-hq/extend-agent-plugin --skill extend-apiOpen Benchmarks
Public benchmarks with open data
Each benchmark publishes its corpus, metric, and comparison scope, with datasets on Hugging Face so you can reproduce the results or score your own pipeline.
RealDoc-Bench
Benchmark for document agents
581 real documents from logistics, healthcare, financial services, and real estate, with human-annotated layouts and verified Q&A prompts. Extend Parse 2.0 scores 95.7% field-level Q&A accuracy. Run the harness to score any parser against the same ground truth.
- 581 documents
- 4 industries
- CC BY 4.0
hf download Extend-AI/RealDoc-Bench --repo-type datasetExtraction
LongArray-Extract
Tests whether extraction returns complete, schema-faithful arrays when the output grows from a dozen rows to thousands.
99.2%
Mean accuracy, Extend
45 financial, clinical, and legal PDFs, up to ~2,200 records
Splitting
PoliTax Split
Tests boundary detection on long compound tax filings, where frontier models miss subtle boundaries across hundreds of pages.
+17–44 pts
Recall lift across models, Extend harness
The 30 largest compound filings in the PoliTax corpus
