Frank
a9b3c495da
- open-models.md: Qwen2.5-VL 'best open vision model' superseded by Qwen3-VL (Apache 2.0 dense sizes; repo QwenLM/Qwen3-VL, arXiv 2511.21631, verified via web search); decision table + mermaid + citations updated - chezmoi-evaluation.md: fleet facts were fabricated — servers run Ubuntu 26.04 LTS (probed via ssh, both boxes), not 'Arch/FreeToken' (distro does not exist); dev workstation is AMD Ryzen 5 PRO 5650U, not Intel Ultra 7; frank-default-* endpoints retired 2026-10-18 - agentic-web-research/index.md: pi-era topology blurb replaced with current fleet endpoints - self-hosted-web-agents.md: sample model frank-default-small -> frank-archon (endpoint/IP already correct: dankserver) - mcp.md reference-server table verified against upstream modelcontextprotocol/servers README (exact match, no change) - 'peer-reviewed BrowseComp' claim from scout ledger: does not exist in any file — rejected, not applied Refs #29
2.2 KiB
2.2 KiB
Agentic Web Research
Agentic web research means that an AI drives the search loop. The agent formulates queries, reads results, decides what to read next, and writes a synthesis. It works best when search, extraction, and reasoning each run in the right place.
Fleet topology (2026-10): SearXNG lives at
192.168.0.143:8081(UI) /:8082(JSON) on dankclaw; model endpoints arefrank-archon(dankserver :7770, radiance),frank-dragoon(dankclaw :7770, halogen-flash-server),frank-zealot(dankclaw :7771, llama.cpp PrismML). The pi-eralocalhost:8080llama.cpp endpoint is retired. See System hosts.
This section connects four decisions:
- Search backend — make a self-hosted SearXNG instance fast and private.
- Network path — send only SearXNG traffic through a VPN and leave the rest alone.
- Agent loop — apply agentic search best practices and research effectiveness so the loop ends, not spins.
- Model choice — pick a self-hostable open model strong enough for tool use and web agents.
Quick Map
graph LR
A[User Question] --> B[Agent + Open Model]
B --> C[SearXNG Search]
C -->|VPN only here| D[Upstream Engines]
B --> E[Extraction: Crawl4AI / fetch]
B --> F[Synthesis + Citations]
E --> F
Pages
- Self-Hosted Web Agents — Tools and architectures for an agent that drives a browser.
- SearXNG Tuning — Configuration for speed, privacy, and useful results.
- VPN Routing for SearXNG — Route only the SearXNG outbound path through a VPN.
- Agentic Search Best Practices — Query, extract, validate, and retry well.
- Open Models for Web Use — Self-hostable models strong at tool and API calling.
- Research Effectiveness — Multi-step, credibility-scored research loops.
- Model Context Protocol — The standard that connects the agent to tools.
Sources
Authoritative references are cited per page under # Citations.