Show HN: Sifthound – self-hosted, Tavily-compatible search API for AI agents
Sifthound is an open-source, self-hosted web search API designed as a drop-in replacement for the Tavily service used by AI agents. It leverages SearXNG for search capabilities and supports standard endpoints for searching, extracting, crawling, and mapping web content without requiring proprietary search API keys. The tool integrates with popular AI development frameworks like LangChain and offers an MCP server for direct use with clients such as Claude and Cursor.
- ▪Sifthound provides a Tavily-compatible API that allows existing code to run against a local server by simply changing the base URL.
- ▪The system uses SearXNG for metasearch and trafilatura for extracting clean markdown or text from web pages.
- ▪It includes security features like SSRF protection to block private and internal addresses, including those accessed via redirects or DNS rebinding.
- ▪The project is released under the MIT license and can be deployed via Docker Compose, standalone Docker images, or pip installation.
- ▪Sifthound functions as an MCP server, enabling read-only tools for search, extraction, crawling, and mapping within AI coding assistants.
Hacker News (AI / LLM) files mainly under ai. We currently carry 6,428 of its stories.
Story provenance
Source · retrieval · rights · ranking — open for full record
inspect →
Story provenance
Attribution is not the same as permission. This drawer separates discovery metadata, excerpts, WeSearch-generated summaries, reuse status, and whether the publisher receives the visit. Nothing here claims a legal grant the publisher has not made.
Record
| Original publisher | GitHub |
| Canonical URL | https://github.com/khsarvar/sifthound |
| Publication time | Fri, 25 Sep 2026 13:42:02 +0000 |
| Retrieval time | 2026-09-25T13:45:32.933Z |
| Last seen | 2026-09-25T13:45:32.933Z |
| Headline source | Publisher (no WeSearch rewrite) |
| Excerpt source | publisher body |
| Excerpt method | First ~120 words (~800 chars) of extracted publisher body, fair-use limited. |
| Summary | WeSearch · cerebras-chat (WeSearch summarizer) |
| Summary source text | contentText |
| Citation coverage | Summary is a WeSearch-generated derivative; primary citation is the original publisher URL. |
| Cluster | WOOAPbbTFlm- · 1 stories |
| Cluster logic | Grouped by semantic title/content similarity across sources within a rolling window. Same-publisher template collisions are excluded from coverage comparison. |
| Ranking reason | Story pages are not engagement-ranked. Hub feeds use recency, with optional source-diversified chronological ordering (cap consecutive stories per source). No personalized ranking. |
| Publisher visit | Yes — open original |
| Substitutes article? | No — link-out required for full text |
Rights status (four layers)
WeSearch handling by dimension
| Indexing | May the item be indexed (stored, ranked, made findable)? | Allowed |
| Snippet | May a short excerpt of the publisher's text be shown? | Allowed |
| AI summary | May WeSearch generate its own short summary of the article? | Limited |
| Retrieval / RAG | May the content be exposed for third-party retrieval-augmented generation? | Not asserted |
| Model training | May the content be used to train AI models? | Not asserted |
| Commercial reuse | May the content be reused commercially? | Not permitted |
Basis: Derived from the published RSS/Atom feed. Contact: [email protected]. Reviewed: 2026-07-24.
Opening excerpt (first ~120 words) tap to expand
Sifthound — open-source, self-hosted Tavily alternative Sifthound is an open-source, self-hosted web search API for AI agents and LLM apps, and a drop-in replacement for the Tavily API. It serves the same /search, /extract, /crawl and /map endpoints with the same request and response shapes, so code written for Tavily (including the official Python SDK and the LangChain integration) works against your own server by changing only the base URL. It needs no search API key. Search through a SearXNG metasearch instance, with no search API keys Extraction of clean markdown or text from web pages with trafilatura Ranking: BM25 relevance blended with the upstream engine's order; advanced depth fetches each page and returns its most relevant chunks Answers (include_answer) written by Claude from…
Excerpt limited to ~120 words for fair-use compliance. The full article is at GitHub.