Qsearch — AI skill for Claude Code
Open-source search API for AI agents — corpus-first hybrid search with x402 micropayments.
How to install Qsearch
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open theYahia/qsearch and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Qsearch does
Open-source search API for AI agents — corpus-first hybrid search with x402 micropayments. Self-hosted; bundled MCP server (9 tools) you run from source.
Alternatives in AI
- Invisible Dots — Open-source, self-hosted alternative to OpenAI Dots, Meta Muse, Grok Bot, Manus Cue and Claude Cowork 31.8k ★
- Xerj — Local-first search engine and MCP server for AI agents 12.5k ★
- Open Dots — Open-source, self-hosted AI agent workspace and alternative to OpenAI Dots, Meta Muse, Grok Bot, Instinct, Man 5.5k ★
README
qsearch
I built this for my own daily research. After running 100+ research sprints, my agent kept hallucinating because it read 200-char snippets. qsearch gives it full content with multi-engine provenance — running locally, owned by me.
     [](https://registry.modelcontextprotocol.io/v0/servers?search=io.github.theYahia/qsearch)
AI agents lose **17–33% of facts to hallucination** because they read 200-character snippets, not full pages ([Stanford 2024](https://dho.stanford.edu/wp-content/uploads/Legal_RAG_Hallucinations.pdf)). Existing search APIs hide *which engines agreed* on a result. Existing knowledge graphs are enterprise-priced or vendor-locked.
**qsearch is the open-source search layer that gives agents full content with multi-engine provenance** — running on your machine, owned by you, ready for MCP today.
✅ **v0.4.0 live at [qsearch.pro](https://qsearch.pro).** Multi-engine attribution, trust corpus with per-URL provenance (`engines[]`, `sweep_count`, `trust_score`), corpus viewer at `/ui`, MCP-over-HTTP for Claude Code and any spec-compliant client. 📖 **Architecture:** [ARCHITECTURE.md](./ARCHITECTURE.md) · **Vision:** [docs/VISION.md](./docs/VISION.md) · **Technical spec:** [docs/TRUST_MESH.md](./docs/TRUST_MESH.md) · **Federation deep-dive:** [docs/FEDERATION_ARCHITECTURE.md](./docs/FEDERATION_ARCHITECTURE.md)
Demo

60-second tour: `/health` (it's up, local) → `/s
Related Skills
Flyarchive
FlyArchive — self-hosted personal document archive and knowledge base with hybrid semantic + full-text search.
Complicheck Skill
Deterministic sub-10ms cosmetic compliance API for AI agents. Resolves INCI/CAS to EU CosIng regulations via x
Jiro
Jiro Search: local-first, AI-native web search & scraping API. Self-hosted SerpAPI alternative with MCP server
Open AI Agents Hub
Open-source, self-hosted platform to build, host, and chat with AI agents — LLM chat bots and image/video gene
Recollect
Self-hosted AI memory and MCP coordination for coding agents. Persistent context across repositories and sessi
Memrain
Self-hosted memory for your AI agents: hybrid vector + keyword + entity-graph search over your notes and code,
Related Agents
Firecrawl Scraper
Web scraping and research subagent. Dispatched to scrape URLs, search the web, crawl sites, and extract struct
Diva MCP Integrator
Wires MCP servers into a Diva agent — external tool servers via MCP.stdio/MCP.http (Python or TypeScript) and
Beardrive User
Usability evaluator playing the END-USER persona on a self-hosted BearDrive hub — a non-admin employee onboard