# sentient-agi/OpenDeepSearch

SOTA search powered LLM

Repository: https://github.com/sentient-agi/OpenDeepSearch
Canonical: https://ross.abutalabs.com/products/opendeepsearch
Language: Python
License: Apache-2.0
License Family: permissive
Last push: 2025-04-04T18:20:24+00:00

## Health v2 (maintenance only)
Score: 26/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 14, release rhythm 35, longevity 37
- inputs: {"age_days": 531, "days_push": 516, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 3842, forks 343 (observed 2026-08-28T04:08:24.027173+00:00)

## What it is
OpenDeepSearch is an open-source search tool that augments LLMs and reasoning agents with web search capabilities, aiming to match closed-source deep research products. It integrates with Hugging Face's smolagents and supports pluggable search backends like SearXNG and Serper.

## Use cases
- add web search to my llm agent
- open source alternative to perplexity deep research
- give my chatbot real-time web search
- build a research agent that searches the web
- deep search with open models
- integrate search tooling into smolagents

## When to choose
- you want an open-source, self-hostable deep search stack for LLM agents
- you already use smolagents or Hugging Face tooling
- you need pluggable search providers and re-ranking

## When to avoid
- you need a polished commercial search API with SLAs
- you want a no-code consumer search product
- your project is not Python-based

## Facets
- artifact type: library
- maturity: active
- function: search-engine, agent-framework, rag, llm-inference, web-scraping
- domain: artificial-intelligence, large-language-models
- platform: python, cli
- tags: open-source-search, reasoning-agents, smolagents, perplexity-clone, web-search-tool, search, retrieval-augmented-generation, ai-agents

## Member repositories
- sentient-agi/OpenDeepSearch (main) score 26

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:24.027173+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T18:26:13.516036+00:00, confidence not recorded.
  - readme: https://github.com/sentient-agi/OpenDeepSearch (fetched 2026-08-28T04:08:24.027173+00:00, sha 13c8806ee558)
- Data as of 2026-08-30T08:39:29.467469+00:00.