OpenResearcher alternatives
Curated alternatives to OpenResearcher — and why you'd switch.
DeepDive
THUDM recipe for deep-search agents: synthesize hard multi-hop QA from knowledge-graph random walks, then multi-turn GRPO RL — DeepDive-32B hits 14.8% BrowseComp; data feeds GLM-4.5/4.6.
Why switchRival open recipes for training deep-research agents: DeepDive synthesizes hard QA from knowledge-graph walks and trains with multi-turn RL on slime (checkpoints still pending); OpenResearcher distills 96K long trajectories from GPT-OSS-120B and ships data, 30B model and eval framework complete.
Full comparison →hyperresearch
Deep-research harness for Claude Code: a 16-step, tier-adaptive pipeline with adversarial critics, cite-checking and 250+ sources per run, every source kept in a persistent markdown+SQLite vault.
Why switchopenresearcher is a training recipe for a deep-research model; hyperresearch gets there with harness engineering on a frontier model - no training, more steps.
Full comparison →Search-R1
RL framework for training reasoning-and-search interleaved LLMs — the open recipe behind DeepSeek-R1-style search agents: PPO/GRPO on veRL, any search backend, models and data on HF. Two papers.
Why switchTwo open deep-research training recipes: OpenResearcher ships trajectories + a trained model; Search-R1 ships the RL framework to train your own from scratch.
Full comparison →