# TIGER-AI-Lab/OpenResearcher

OpenResearcher: A Fully Open Pipeline for Long-Horizon Deep Research Trajectory Synthesis

Repository: https://github.com/TIGER-AI-Lab/OpenResearcher
Canonical: https://ross.abutalabs.com/products/openresearcher
Homepage: https://github.com/TIGER-AI-Lab/OpenResearcher
Language: Python
License Family: other
Topics: deep-research, llm, retrieval
Last push: 2026-06-10T17:32:58+00:00

## Health v2 (maintenance only)
Score: 54/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 86, release rhythm 35, longevity 15
- inputs: {"age_days": 212, "days_push": 84, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1211, forks 118 (observed 2026-08-28T04:04:00.170677+00:00)

## What it is
OpenResearcher is a fully open-source pipeline for synthesizing long-horizon deep research trajectories using LLM agents with retrieval and web browsing. It includes agent code, training code, a released dataset, and a trained model for building deep research assistants.

## Use cases
- generate deep research trajectories for LLM training
- build an open-source deep research agent
- synthesize long-horizon research datasets with web retrieval
- train a model to do multi-step research with search
- reproduce deep research pipelines without closed APIs
- evaluate agents on long-form research tasks

## When to choose
- you need an open pipeline for generating research agent training data
- you want to train or fine-tune an LLM for deep research tasks
- you need a self-hosted alternative to proprietary deep research tools
- you want to study or extend long-horizon agent trajectories with retrieval

## When to avoid
- you need a polished end-user research assistant UI rather than a research pipeline
- you lack GPU resources for training or running large models
- you need a project with a permissive license - no license is specified
- your task is simple single-shot question answering without multi-step research

## Facets
- artifact type: framework
- maturity: active
- function: agent-framework, rag, llm-inference, search-engine, machine-learning, llm-training
- domain: artificial-intelligence, large-language-models
- platform: python, self-hosted
- tags: deep-research, trajectory-synthesis, open-source-pipeline, research-agent, dataset-generation, web-search-agent, ai-agents, retrieval-augmented-generation, natural-language-processing, linux, docker

## Member repositories
- TIGER-AI-Lab/OpenResearcher (main) score 54

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:00.170677+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 2026-08-30T06:18:02.970113+00:00, confidence not recorded.
  - readme: https://github.com/TIGER-AI-Lab/OpenResearcher (fetched 2026-08-28T04:04:00.170677+00:00, sha a49d5e79b35a)
  - homepage: https://github.com/TIGER-AI-Lab/OpenResearcher (fetched 2026-08-29T12:26:06.038802+00:00, sha e9337eacce01)
- Data as of 2026-08-30T08:39:29.467469+00:00.