InnerVault

Library

85,762 resources from 11 public sources. 53 checked by hand; the rest are unreviewed.

Results

  1. OpenHermesPreferences

    Datasets & benchmarks

    Hugging Face dataset by argilla

    Stale Hugging Face Hub, argilla 221 ♥otherUpdated 2 years ago

    argilla/OpenHermesPreferences
  2. hands-on-llm

    Agents & frameworks

    动手学大模型全栈:CS336 中文精讲 · PyTorch 手搓 Transformer · 单卡复现 Pretrain/SFT/LoRA/DPO/GRPO/RLVR · PEFT/Agent/RAG 落地(含真实实验、曲线与复现脚本)

    Stale GitHub, FRS2003 127 ★MITUpdated 2 months ago

    git clone https://github.com/FRS2003/hands-on-llm.git
  3. diy-llm

    AI repositories

    Covers pre-training data, Tokenizer, Transformer, MoE,distributed training, Scaling Laws, inference & alignment .6 progressive code assignments for full-stack LLM learning | 涵盖预训练数据、分词器、Transformer、MoE、分布式训练、缩放定律、推理与对齐,6 项渐进代码作业,掌握 LLM 全栈知识

    Stale GitHub, datawhalechina 2,648 ★Updated 14 days ago

    git clone https://github.com/datawhalechina/diy-llm.git
  4. MedicalGPT

    AI repositories

    MedicalGPT: Training Your Own Medical GPT Model with ChatGPT Training Pipeline. 训练医疗大模型,实现了包括增量预训练(PT)、有监督微调(SFT)、RLHF、DPO、ORPO、GRPO。

    Stale GitHub, shibing624 5,861 ★Apache-2.0Updated 2 months ago

    git clone https://github.com/shibing624/MedicalGPT.git
  5. model by mradermacher · transformers

    Stale Hugging Face Hub, mradermacher 302 ♥apache-2.0Updated 7 days ago

    mradermacher/DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic-i1-GGUF
  6. rlhf-feedback-loop

    MCP servers

    RLHF feedback loop for AI agents. Capture signals, promote memories, block mistakes, export DPO.

    Stale Official MCP Registry, io.github.IgorGanapolsky Updated 8 months ago 1 note

    rlhf-feedback-loop@0.6.13
  7. rlay

    MCP servers

    Shared channels where agents from different vendors collaborate over a relayed message log.

    Stale Official MCP Registry, dev.rlay Updated 2 months ago 1 note

  8. rlg-mcp

    MCP servers

    MCP server exposing rlg log streams to LLM agents via JSON-RPC 2.0 over stdio.

    Stale Official MCP Registry, io.github.sebastienrousseau Updated 9 days ago 1 note

    ghcr.io/sebastienrousseau/rlg-mcp:0.0.18
  9. supabase-rls-check

    MCP servers

    Read-only Supabase RLS checks: explain rules, analyze/diff SQL exports, scan public env vars.

    Stale Official MCP Registry, io.github.Tthanh2k6 Updated 3 days ago 1 note

    supabase-rls-check@0.6.3
  10. magpie-ultra-v0.1

    Datasets & benchmarks

    Hugging Face dataset by argilla

    Stale Hugging Face Hub, argilla 227 ♥llama3.1Updated 24 months ago

    argilla/magpie-ultra-v0.1
  11. AgileRL

    Agents & frameworks

    The complete post-training stack for LLMs, plus RL for any problem. SFT, DPO and multi-turn agentic RL, with evolutionary hyperparameter optimization built in.

    Indexed GitHub, AgileRL 968 ★Apache-2.0Updated today

    git clone https://github.com/AgileRL/AgileRL.git
  12. rls-doctor

    MCP servers

    Read-only Postgres/Supabase RLS audit with a rolled-back probe that proves who can read which rows.

    Stale Official MCP Registry, io.github.subhajitlucky Updated 36 days ago 1 note

    rls-doctor@0.5.8
  13. rls-check

    MCP servers

    Read-only Supabase RLS check: explains in Arabic which tables anyone can read or change. No keys.

    Stale Official MCP Registry, io.github.Muhandis-online Updated 17 days ago 1 note

    muhandis-rls-check@0.1.2
  14. Filter agent RL methods by supervision, critic and task setting; retrieve source links and BibTeX.

    Stale Official MCP Registry, space.hf.hoyant-su-agentic-rl Updated 2 months ago 1 note

  15. RLM Tools

    MCP servers

    Persistent Python sandbox for token-efficient codebase exploration in MCP clients

    Stale Official MCP Registry, io.github.stefanoshea Updated 9 months ago 1 note

    rlm-tools@0.1.0
  16. stack-exchange-preferences

    Datasets & benchmarks

    Hugging Face dataset by HuggingFaceH4

    Stale Hugging Face Hub, HuggingFaceH4 137 ♥cc-by-sa-4.0Updated 3 years ago

    HuggingFaceH4/stack-exchange-preferences
  17. text generation model by Jackrong · transformers

    Indexed Hugging Face Hub, Jackrong 185 ♥apache-2.0Updated 9 days ago

    Jackrong/DeepSeek-V4-Pro-Qwen3.5-9B-MTP-GGUF
  18. image text to text model by AlexWortega · transformers

    Stale Hugging Face Hub, AlexWortega 39 ♥apache-2.0Updated 31 days ago

    AlexWortega/Qwen3.8-27B-antislop
  19. Airlock RLS

    MCP servers

    Scan a deployed site for an exposed Supabase service_role key and audit Row Level Security.

    Stale Official MCP Registry, io.github.mateuszingano Updated 33 days ago 1 note

    airlock-rls-mcp@0.1.1
  20. maro

    Agents & frameworks

    Multi-Agent Resource Optimization (MARO) platform is an instance of Reinforcement Learning as a Service (RaaS) for real-world resource optimization problems.

    Stale GitHub, microsoft 929 ★MITUpdated 19 months ago

    git clone https://github.com/microsoft/maro.git
  21. HarborRL

    Agents & frameworks

    An end-to-end framework for Agentic Reinforcement Learning.

    Indexed GitHub, datamllab 230 ★MITUpdated 4 days ago

    git clone https://github.com/datamllab/HarborRL.git
  22. alem-env

    Datasets & benchmarks

    Can LLM/MARL agents coordinate in long-horizon, open-ended tasks? NeurIPS 2026 (Evaluations and Datasets).

    Stale GitHub, alem-world 57 ★MITUpdated 11 days ago

    git clone https://github.com/alem-world/alem-env.git
  23. 85+ pay-per-call MCP tools: trading, federal grants/contracts, SEC, FTD. x402 USDC/RLUSD. No keys.

    Stale Official MCP Registry, io.github.Timwal78 Updated 3 months ago 1 note

  24. Simreal-MLBench

    Datasets & benchmarks

    [Public preview] Externally scored agentic ML research benchmark: 60 tasks, real competition ground truth. Open protocol, operated evaluation.

    Stale GitHub, Simreal-AI 301 ★Apache-2.0Updated 53 days ago

    git clone https://github.com/Simreal-AI/Simreal-MLBench.git

Indexed entries aren't reviewed or tested by InnerVault. Details come straight from each source. Anything that can reach your accounts, files or browser can do damage, so read the source before you install it.