SimplePDF Copilot: Client-Side AI Tool Calling for PDF Form Filling

SimplePDF Copilot is an AI assistant that interacts with the SimplePDF editor to fill forms, answer questions, focus fields, add fields, and delete pages. The PDF never leaves the browser — parsing, rendering, and field detection run entirely client-side. The LLM only receives the text content and your messages, sent to your chosen provider (default DeepSeek V4 Flash, rate-capped; BYOK supported for cloud or local via LM Studio).
Key details
- Tool calling executed client-side: The LLM issues tool call intents, but execution happens in the browser via iframe postMessage. This enables speed (client-to-client) and data control — you can remove the tool that exposes document content and the LLM never sees it.
- Field detection uses CommonForms by Joe Barrow with extra post-processing heuristics for accurate form field identification.
- Stack: Tanstack Start, AI SDK from Vercel, Tailwind.
- Open source: The Copilot overlay and client-side tool calling logic are open source on GitHub. SimplePDF itself (the iframe) remains proprietary.
- Privacy first: Designed for healthcare customers where PII cannot leave the browser. The PDF is never uploaded.
By default the demo sends document content to the LLM, but you can sever that connection by removing the content-exposing tool. The demo is fully functional at the link below.
📖 Read the full source: HN AI Agents
👀 See Also

Introducing Xrouter: A Smart Hybrid LLM Router to Optimize Cost and Performance
Discover Xrouter, an open-source creation that dynamically integrates local with cloud inference, designed to slash AI costs while boosting efficiency.

Stagent: Open-source ops layer for Claude Agent SDK with local governance and workflow orchestration
Stagent is an open-source, local-first coordination workspace built on top of Claude Agent SDK and Claude API that provides workflow orchestration, budget guardrails, and human-in-the-loop governance for AI agents. It includes 15 product surfaces, 6 workflow patterns, 52+ reusable agent profiles, and runs entirely locally with SQLite.

Fine-Tuning Qwen 14B for Discord Autocomplete
A developer fine-tuned the Qwen 14B model using his Discord message dataset to create an autocomplete tool.

Apideck CLI: A Low-Context Alternative to MCP for AI Agents
Apideck CLI is an AI-agent interface that uses ~80 tokens for its agent prompt instead of tens of thousands for tool schemas, addressing MCP's context window consumption problem. Benchmarks show MCP can cost 4 to 32× more tokens than CLI for identical operations.