Reliable research infrastructure for AI agents. Evidence-backed web search with citations, confidence scores, and Clarity anti-hallucination. MCP server, REST API, Python SDK.
~95% on SimpleQA (e.g. Qwen3.6-27B on a 3090). Supports all local and cloud LLMs (llama.cpp, Ollama, Google, ...). 10+ search engines - arXiv, PubMed, your private documents. Everything Local & Encrypted.
The unified web layer for AI agents. Search (8 engines), stealth browse, auth, and act on 24 platforms. One npm install, self-hosted.
Keep searching, reading webpages, reasoning until it finds the answer (or exceeding the token budget)
Zero-config domain availability MCP for Claude & ChatGPT. AI suggestions, premium/auction detection via GoDaddy, RDAP/WHOIS fallback. Stdio + HTTP.
Verified knowledge for AI agents. Compress context, extract and store facts, define rules, and ask questions — get deterministic answers with proof, not LLM guesses. Connect agents via MCP, Python SDK, TypeSc
One memory. Every AI tool. Yours to keep. Local-first, MCP-compatible, Apache 2.0.
4 captures since 2026-05-22
AI agent config detected
Key config paths
.agents
.claude
CLAUDE.md
.agents
.agents/skills
.agents/skills/browse-research
.agents/skills/browse-research/SKILL.md
.claude
.claude/skills
.claude/skills/browse-anti-hallucination
.claude/skills/browse-cite
.claude/skills/browse-compare-claims
.claude/skills/browse-deep-dive
.claude/skills/browse-extract
.claude/skills/browse-fact-check
.claude/skills/browse-monitor
.claude/skills/browse-research
.claude/skills/browse-sessions
CLAUDE.md