ParseFlow is a document parsing API that converts PDFs, DOCX files, and plain text into structured, evidence-backed JSON output for developers, automations, and AI workflows.

Unlike tools that return opaque extracted values, ParseFlow includes evidence metadata with every result — confidence scores, source character offsets, and evidence snippets showing exactly where each value came from. This makes output easier to verify, debug, and trust in production.

Key features: - Structured JSON extraction with evidence spans - Table-aware chunking with presets for RAG, summarization, and extraction - Async jobs and batch processing - LangChain and LlamaIndex adapters - MCP / OpenClaw tooling support - BYOK for advanced extraction with your own model provider keys - Free deterministic tier for evaluation

Best use cases: invoice processing, contract clause extraction, receipt parsing, document intake pipelines, RAG preprocessing, AI workflow integration.

Built by a student. Priced for builders and small teams.

Free deterministic tier available. Starter: $10/month Growth: $15/month

Docs: docs.parseflow.tech

CodeHerald provides a new way to keep track of your code review queue, grouped by your next action needed.

When would you use CodeHerald?

• You work in a team that does code reviews.
• Your team receives ad-hoc code review requests via multiple channels: DMs, emails, bookmarks of filtered lists.
• Your team sometimes loses track of small pull requests, delaying them days.
• Your team find ad-hoc code review requests distracting, but cannot put a finger on why.
• Your team tried different strategies to improve code review process, and none of them felt right.

If any of the above is true, CodeHerald will help you.

What can CodeHerald do for you?

CodeHerald groups pull requests by next action: must review, needs an update, can be merged. It allows you to replace slack, emails, filters, and browser bookmarks with one single page that you can open at a glance and decide which PR to tackle next.