Alternatives and similar repositories for tinker

Users that are interested in tinker are comparing it to the libraries listed below

• ServiceNow / PipelineRL
  A scalable asynchronous reinforcement learning implementation with in-flight weight updates.
  ☆357Updated this week
• meta-pytorch / torchforge
  PyTorch-native post-training at scale
  ☆600Updated last week
• test-time-training / discover
  ☆93Updated last week
• thinking-machines-lab / batch_invariant_ops
  ☆952Updated 2 months ago
• axon-rl / gem
  A Gym for Agentic LLMs
  ☆437Updated last week
• ekinakyurek / marc
  Public repository for "The Surprising Effectiveness of Test-Time Training for Abstract Reasoning"
  ☆343Updated 2 months ago
• marin-community / marin
  Open-source framework for the research and development of foundation models.
  ☆731Updated last week
• microsoft / ArchScale
  Simple & Scalable Pretraining for Neural Architecture Research
  ☆307Updated last month
• facebookresearch / RAM
  A framework to study AI models in Reasoning, Alignment, and use of Memory (RAM).
  ☆344Updated last month
• tokenbender / avataRL
  rl from zero pretrain, can it be done? yes.
  ☆286Updated 4 months ago
• PrimeIntellect-ai / prime-environments
  Curated collection of community environments
  ☆208Updated this week
• changjonathanc / flex-nano-vllm
  FlexAttention based, minimal vllm-style inference engine for fast Gemma 2 inference.
  ☆333Updated 2 months ago
• VsonicV / es-fine-tuning-paper
  This repo contains the source code for the paper "Evolution Strategies at Scale: LLM Fine-Tuning Beyond Reinforcement Learning"
  ☆288Updated 2 months ago
• PrimeIntellect-ai / prime-rl
  Async RL Training at Scale
  ☆1,020Updated last week
• NVlabs / RLP
  [ICLR 2026] Official PyTorch Implementation of RLP: Reinforcement as a Pretraining Objective
  ☆226Updated this week
• EleutherAI / nanoGPT-mup
  The simplest, fastest repository for training/finetuning medium-sized GPTs.
  ☆186Updated last week
• pyember / ember
  ☆237Updated 3 weeks ago
• facebookresearch / memory
  Memory layers use a trainable key-value lookup mechanism to add extra parameters to a model without increasing FLOPs. Conceptually, spars…
  ☆370Updated last year
• HazyResearch / zoology
  Understand and test language model architectures on synthetic tasks.
  ☆251Updated 2 weeks ago
• sail-sg / oat
  🌾 OAT: A research-friendly framework for LLM online alignment, including reinforcement learning, preference learning, etc.
  ☆621Updated 3 weeks ago
• microsoft / dion
  Dion optimizer algorithm
  ☆420Updated 2 weeks ago
• HazyResearch / cartridges
  Storing long contexts in tiny caches with self-study
  ☆231Updated last month
• google-deepmind / regress-lm
  Library for text-to-text regression, applicable to any input string representation and allows pretraining and fine-tuning over multiple r…
  ☆313Updated last month
• facebookresearch / aira-dojo
  AIRA-dojo: a framework for developing and evaluating AI research agents
  ☆124Updated last week
• facebookresearch / PhysicsLM4
  Physics of Language Models: Part 4.2, Canon Layers at Scale where Synthetic Pretraining Resonates in Reality
  ☆314Updated 3 weeks ago
• Noumena-Network / nmoe
  MoE training for Me and You and maybe other people
  ☆331Updated 3 weeks ago
• openai / circuit_sparsity
  Open-source release accompanying Gao et al. 2025
  ☆498Updated last month
• facebookresearch / meta-agents-research-environments
  Meta Agents Research Environments is a comprehensive platform designed to evaluate AI agents in dynamic, realistic scenarios. Unlike stat…
  ☆418Updated last week
• facebookresearch / llm-speedrunner
  The Automated LLM Speedrunning Benchmark measures how well LLM agents can reproduce previous innovations and discover new ones in languag…
  ☆127Updated 3 months ago
• test-time-training / e2e
  Official JAX implementation of End-to-End Test-Time Training for Long Context
  ☆478Updated last week