Test Time Scaling Python Packages

massgen

🚀 MassGen is an open-source multi-agent scaling system that runs in your terminal, autonomously orchestrating frontier models and agents to collaborate, reason, and produce high-quality results. | Join us on Discord: discord.massgen.ai

verdict

Inference-time scaling for LLMs-as-a-judge.

fleet-search

Fleet🚀 is an algorithm for distributed test-time scaling of LLM workflows that use local models and can evaluate and rank generated completions.

thinkretrieve

[EMNLP 2026 Findings] Retrieval-augmented test-time scaling: inject retrieved worked examples into a reasoning model's thinking trace, mid-thought.

reasoning-bank

Framework-agnostic ReasoningBank (Ouyang et al., ICLR 2026): agents that learn from successful AND failed trajectories, with MaTTS.

lmctx

Context Kernel for LLM APIs — standardize before/after model calls; keep execution in your runtime.