Trace mining for post-training. Filter trajectories, draft verifiers, export SFT and RL data.
☆137Nov 3, 2026Updated this week
Alternatives and similar repositories for bandits
Users that are interested in bandits are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Small System One decision models (17M–400M) for Yes/No, Choice, Score, and reranking. Training toolkit, Python inference, and ONNX suppor…☆41Oct 15, 2026Updated 3 weeks ago
- Training Jev-like decision models using Qwen3 with choice-order invariance☆83Oct 4, 2026Updated last month
- ☆28Feb 26, 2026Updated 8 months ago
- Jev-compatible API endpoint based on open models (prefill-only)☆334Oct 1, 2026Updated last month
- ☆112Jun 10, 2026Updated 4 months ago
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- Endless OMP chat with durable history and binary summary-tree memory, inspired by OptChat☆81Oct 23, 2026Updated 2 weeks ago
- Typed-decision models (noul / choice / score) trained by a self-improving loop of AI agents — checkpoints, the code that produced them, a…☆134Updated this week
- A GEPA proposer with less overfitting and helpful parameters.☆60Oct 6, 2026Updated last month
- ☆142Oct 26, 2026Updated last week
- ☆46Feb 20, 2026Updated 8 months ago
- A framework for building decision-model harnesses for any kind of task. Your program offers the model a short list of next steps, and the…☆434Oct 30, 2026Updated last week
- A self-modifying, durable agent that lives on your iPhone. Brain on the phone, hands on your machines.☆39Oct 23, 2026Updated 2 weeks ago
- ☆43Sep 30, 2026Updated last month
- ☆13Updated 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.
- quickly mix LLMs together☆19Jan 5, 2025Updated last year
- ☆311Updated this week
- reproducing the flapping airplanes megakernel, in collab with magni☆131Updated this week
- AutoGEPA automates the tedious parts of setting up a DSPy optimization pipeline: converting raw data into dspy.Examples, generating a met…☆19Jul 4, 2026Updated 4 months ago
- Clean reproducible benchmark suite for the self-hosted cascade RC (ARC-AGI-2, HMMT-2026, HLE, MMMU-Pro, SWE-Bench Pro, Terminal-Bench 2.1…☆13Updated this week
- LLM serving engines that SkyDiscover builds on the fly for specific AI models and hardware: Qwen3.6-35B-A3B, Qwen3.8-Flash-Next and Flint…☆26Updated this week
- A simple library for generating instruction tuning datasets locally☆119Sep 20, 2026Updated last month
- ☆28Sep 27, 2026Updated last month
- Mirror is Reflection's coding harness☆215Oct 22, 2026Updated 2 weeks ago
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- Build calibrated AI Functions from human feedback using Jev and GEPA.☆315Updated this week
- ReBase: Training Task Experts through Retrieval Based Distillation☆27Sep 22, 2026Updated last month
- Storing the LongCoT-mini results for RLM(GPT-5.2)☆20Apr 26, 2026Updated 6 months ago
- TypeLLM: LLMs with type-safe generation☆978Oct 25, 2026Updated last week
- Anabasis: automatically solve hard-to-verify, domain-specific problems from one prompt.☆68Updated this week
- A local prompt-difficulty classifier that automatically sets Pi reasoning effort.☆12Jul 3, 2026Updated 4 months ago
- General plug-and-play inference library for Recursive Language Models (RLMs), supporting various sandboxes.☆17Apr 26, 2026Updated 6 months ago
- Benchmark harness for evaluating DSPy RLMs on data analysis tasks (InfiAgent-DABench)☆24Mar 22, 2026Updated 7 months ago
- FlashREINFORCE: Critic-Free, Single-Rollout, Asynchronous RL for Agentic Language Models☆106Sep 14, 2026Updated last month
- 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.
- Permutation Invariant Jev☆33Sep 28, 2026Updated last month
- A proxy for minimax-m2, enabling interleaved thinking, and tool calls.☆38Nov 21, 2025Updated 11 months ago
- Realtime semantic review for coding agents☆135Oct 31, 2026Updated last week
- Breaking the quadratic memory barrier in AI☆60Oct 13, 2026Updated 3 weeks ago
- Local computer use on Apple silicon: on-device typed decisions with laya and form filling with CUA-S1-FORMS, driven through the macOS Acc…☆543Oct 28, 2026Updated last week
- FineEnvs — RL Environments 101: building and scaling RL environments in the age of LLMs☆547Updated this week
- Halo is an open-source framework built by White Circle for training large language and multimodal models☆847Updated this week