v0.3.0 — Futuristic UI Revamp

What's New

Complete Site-Wide UI Revamp

Every page rebuilt with a futuristic theme — grid backgrounds, glow effects, animated borders, hover lifts, text shimmer, and terminal-card styling. Inspired by the best of modern design.

Landing Page Reimagined

• Interactive use case browser — click to explore, use template via GitHub
• 13-tool toolkit with click-to-reveal MCP commands, REST endpoints, SDK methods
• Trust layer flow graphic: Your Agent → BrowseAI Dev → The Web
• Steve Jobs-inspired copywriting throughout

Mobile First

All layouts responsive — sidebars stack, grids collapse, flows wrap gracefully on any screen size.

Developer Roadmap

Consolidated from 23 items to 11 — punchy, impact-focused, no implementation details. Vertical timeline with shipped/in-progress/coming-soon states.

Apache 2.0 License

Updated from MIT to Apache 2.0.

New Agent Examples

5 domain-specific examples: education, financial, healthcare, legal, scientific research agents.

Bug Fixes

• Logo now visible and clickable to home on every page
• Compare page shows login modal on demo limit (instead of error text)
• SSE CORS: origin whitelist instead of wildcard
• Animation performance: prefers-reduced-motion support + will-change hints

Pages Revamped

Index, Dashboard, Docs, Developers, Playground, Results, Recipes, Alternatives, AlternativeDetail, Compare, Sessions, NotFound

v0.2.0 — Clarity Answer Engine

v0.2.0 — Clarity Answer Engine + Full Research Platform

What is BrowseAI Dev?

Reliable research infrastructure for AI agents. Real-time web search with evidence-backed citations and confidence scores — designed for programmatic evaluation by agents, not chat-based search.

Available As

• MCP Server: npx browseai-dev (13 tools)
• REST API: https://browseai.dev/api/browse/*
• Python SDK: pip install browseaidev
• LangChain: pip install langchain-browseaidev
• CrewAI: pip install crewai-browseaidev
• LlamaIndex: pip install llamaindex-browseaidev

---

New in v0.2.0: Clarity Answer Engine

Clarity is no longer a prompt rewriter — it's now a full anti-hallucination answer engine with two modes:

Fast mode (verify: false)

• LLM-only answer with anti-hallucination grounding techniques
• No internet required — fast, low-latency
• Returns structured claims with confidence score

Verified mode (verify: true)

• Runs LLM answer + browse pipeline in parallel
• Fuses the best of both into one source-backed answer
• Claims classified by origin: confirmed (both agree), source (web-only), llm (LLM-only)
• Full citations, contradiction detection, confidence scoring

New types: ClarityClaim with origin: "llm" | "source" | "confirmed", updated ClarityResult with answer, claims[], sources[], confidence, verified

---

Full Capabilities

Capability	Description
Search	Web search returning ranked results with domain authority
Answer	Full pipeline — search, fetch, extract claims, verify, cite, score confidence
Extract	Structured claim extraction from any URL
Compare	Side-by-side raw LLM vs evidence-backed answer
Clarity	Anti-hallucination answer engine (fast LLM-only or verified with web fusion)
Sessions	Persistent multi-query research with knowledge accumulation
Recall	Retrieve knowledge from past sessions
Feedback	Submit result feedback to improve future accuracy

Verification Pipeline

1. Multi-provider web search (Tavily + Brave + Exa)
2. Page fetch and parse
3. Atomic claim decomposition
4. Hybrid BM25 + dense embeddings retrieval (RRF fusion)
5. NLI semantic entailment reranking (DeBERTa)
6. Cross-source consensus detection
7. Contradiction detection
8. Multi-pass consistency checking
9. Per-claim evidence retrieval for weak claims
10. Counter-query adversarial verification
11. Domain authority scoring (10,000+ domains, Bayesian blending)
12. 7-factor evidence-based confidence score (auto-calibrated from feedback)

Confidence Score

Not LLM self-assessed. Computed from: verification rate (25%), domain authority (20%), source count (15%), consensus (15%), domain diversity (10%), claim grounding (10%), citation depth (5%). Contradiction penalty applied. Auto-calibrated via isotonic regression from user feedback.

Thorough Mode

depth: "thorough" runs iterative confidence-gated loop (up to 3 passes) with per-claim evidence retrieval and counter-query adversarial verification. Early termination via query similarity detection.

Install / Upgrade

# MCP Server
npx browseai-dev@latest

# Python SDK
pip install --upgrade browseaidev

# LangChain
pip install --upgrade langchain-browseaidev

# CrewAI
pip install --upgrade crewai-browseaidev

# LlamaIndex
pip install --upgrade llamaindex-browseaidev

# REST API
curl -X POST https://browseai.dev/api/browse/answer \
  -H "Content-Type: application/json" \
  -d '{"query": "your question", "depth": "thorough"}'

Links

• Website: https://browseai.dev
• Docs: https://browseai.dev/docs
• GitHub: https://github.com/BrowseAI-HQ/BrowseAI-Dev
• Discord: https://discord.gg/ubAuT4YQsT
• npm: https://www.npmjs.com/package/browseai-dev
• PyPI: https://pypi.org/project/browseaidev/

v0.1.6

BrowseAI Dev v0.1.6

Evidence-backed web research infrastructure for AI agents.

What's included

• MCP Server — npx browse-ai setup for Claude Desktop, Cursor, Windsurf
• REST API — search, answer, extract, compare endpoints
• Python SDK — pip install browseai with LangChain & CrewAI integrations

Highlights

• Evidence-based confidence scores (source count, domain diversity, claim grounding)
• Compare mode: raw LLM vs evidence-backed answers side-by-side
• BYOK (bring your own keys) — completely free with your own Tavily + OpenRouter keys
• Admin dashboard with metrics, waitlist management, and package stats
• Pro waitlist system

Links

• Website & Playground
• npm
• PyPI
• Discord