OpenTinker is an RL-as-a-Service infrastructure for foundation models
☆677Mar 21, 2026Updated 8 months ago
Alternatives and similar repositories for OpenTinker
Users that are interested in OpenTinker are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- SkyRL: A Modular Full-stack RL Library for LLMs☆2,544Updated this week
- Miles is an enterprise-facing reinforcement learning framework for LLM and VLM post-training, forked from and co-evolving with slime.☆3,379Updated this week
- A Gym for Agentic LLMs☆519Jan 21, 2026Updated 9 months ago
- slime is an LLM training framework for RL Scaling.☆8,850Nov 5, 2026Updated 2 weeks ago
- Checkpoint-engine is a simple middleware to update model weights in LLM inference engines☆1,026Oct 22, 2026Updated 3 weeks ago
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- Democratizing Reinforcement Learning for LLMs☆5,927Oct 16, 2026Updated last month
- Post-training with Tinker☆4,275Updated this week
- Agentic RL Training at Scale☆2,265Updated this week
- Our library for RL environments + evals☆4,797Updated this week
- A lightweight platform for realistic social simulations☆13Oct 24, 2025Updated last year
- [ICLR 2026] RPG: KL-Regularized Policy Gradient (https://arxiv.org/abs/2505.17508)☆78Nov 5, 2026Updated 2 weeks ago
- A scalable asynchronous reinforcement learning implementation with in-flight weight updates.☆444Updated this week
- Scalable toolkit for efficient model reinforcement☆2,145Updated this week
- An Efficient and User-Friendly Scaling Library for Reinforcement Learning with Large Language Models☆3,456Updated this week
- Virtual machines for every use case on DigitalOcean • AdGet dependable uptime with 99.99% SLA, simple security tools, and predictable monthly pricing with DigitalOcean's virtual machines, called Droplets.
- [ASPLOS'26] Taming the Long-Tail: Efficient Reasoning RL Training with Adaptive Drafter☆187Feb 27, 2026Updated 8 months ago
- Agentic RL on Any Harness at Scale☆876Nov 13, 2026Updated last week
- verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework☆24,293Updated this week
- A version of verl to support diverse tool use [TMLR 2026]☆1,056Jul 15, 2026Updated 4 months ago
- Agent RL framework for LLM agents: multi-turn reinforcement learning with StarPO and reasoning-collapse diagnostics☆2,847Oct 28, 2026Updated 3 weeks ago
- The RL Bridge for LLM-based Agent Applications. Made Simple & Flexible.☆5,922Updated this week
- Scaling RL on advanced reasoning models☆698Oct 20, 2025Updated last year
- ☆21Apr 21, 2026Updated 6 months ago
- Implementation for FP8/INT8 Rollout for RL training without performence drop.☆310Nov 7, 2025Updated last year
- Deploy open-source AI quickly and easily - Special Bonus Offer • AdRunpod Hub is built for open source. One-click deployment and autoscaling endpoints without provisioning your own infrastructure.
- An interface library for RL post training with environments.☆2,871Updated this week
- Streamline on-policy/off-policy distillation workflows in a few lines of code☆112Aug 5, 2026Updated 3 months ago
- [EMNLP 2025] DiagramEval: Evaluating LLM-Generated Diagrams via Graphs☆17Nov 1, 2025Updated last year
- Agent Reinforcement Trainer: train multi-step agents for real-world tasks using GRPO. Give your agents on-the-job training. Reinforcement…☆10,866Updated this week
- [ICML 2026] RLVE: Scaling Up Reinforcement Learning for Language Models with Adaptive Verifiable Environments☆265Updated this week
- Ideas for projects related to Tinker☆201Nov 6, 2025Updated last year
- [NeurIPS 2025 Spotlight] Reasoning Environments for Reinforcement Learning with Verifiable Rewards☆1,555Nov 9, 2026Updated last week
- Measuring how well CLI agents like Claude Code or Codex CLI can post-train base LLMs on a single H100 GPU in 10 hours☆627Updated this week
- AllenAI's post-training codebase☆3,942Updated this week
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- Vortex: Programmable Sparse Attention for Agents as Algorithm Designers☆69Aug 22, 2026Updated 2 months ago
- ☆659May 24, 2026Updated 5 months ago
- PyTorch-native post-training at scale☆706Sep 9, 2026Updated 2 months ago
- ToolOrchestra is an end-to-end RL training framework for orchestrating tools and agentic workflows.☆774Mar 25, 2026Updated 7 months ago
- 🌾 OAT: A research-friendly framework for LLM online alignment, including reinforcement learning, preference learning, etc.☆678Jan 29, 2026Updated 9 months ago
- A compact implementation of SGLang, designed to demystify the complexities of modern LLM serving systems.☆5,614May 17, 2026Updated 6 months ago
- An Easy-to-use, Scalable and High-performance Agentic RL Framework based on Ray (PPO & DAPO & REINFORCE++ & VLM & TIS & vLLM & Ray & Asy…☆10,172Nov 3, 2026Updated 2 weeks ago
Are these results useful?