Library
85,762 resources from 11 public sources. 53 checked by hand; the rest are unreviewed.
Results
-
OpenHermesPreferences
Datasets & benchmarksHugging Face dataset by argilla
argilla/OpenHermesPreferences -
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)
git clone https://github.com/FRS2003/hands-on-llm.git -
diy-llm
AI repositoriesCovers 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
git clone https://github.com/datawhalechina/diy-llm.git -
MedicalGPT
AI repositoriesMedicalGPT: 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。
git clone https://github.com/shibing624/MedicalGPT.git -
model by mradermacher · transformers
mradermacher/DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic-i1-GGUF -
rlhf-feedback-loop
MCP serversRLHF feedback loop for AI agents. Capture signals, promote memories, block mistakes, export DPO.
rlhf-feedback-loop@0.6.13 -
rlay
MCP serversShared channels where agents from different vendors collaborate over a relayed message log.
-
rlg-mcp
MCP serversMCP server exposing rlg log streams to LLM agents via JSON-RPC 2.0 over stdio.
ghcr.io/sebastienrousseau/rlg-mcp:0.0.18 -
supabase-rls-check
MCP serversRead-only Supabase RLS checks: explain rules, analyze/diff SQL exports, scan public env vars.
supabase-rls-check@0.6.3 -
magpie-ultra-v0.1
Datasets & benchmarksHugging Face dataset by argilla
argilla/magpie-ultra-v0.1 -
AgileRL
Agents & frameworksThe complete post-training stack for LLMs, plus RL for any problem. SFT, DPO and multi-turn agentic RL, with evolutionary hyperparameter optimization built in.
git clone https://github.com/AgileRL/AgileRL.git -
rls-doctor
MCP serversRead-only Postgres/Supabase RLS audit with a rolled-back probe that proves who can read which rows.
rls-doctor@0.5.8 -
rls-check
MCP serversRead-only Supabase RLS check: explains in Arabic which tables anyone can read or change. No keys.
muhandis-rls-check@0.1.2 -
Agentic RL: Credit Assignment and CLI Agents
MCP serversFilter agent RL methods by supervision, critic and task setting; retrieve source links and BibTeX.
-
RLM Tools
MCP serversPersistent Python sandbox for token-efficient codebase exploration in MCP clients
rlm-tools@0.1.0 -
stack-exchange-preferences
Datasets & benchmarksHugging Face dataset by HuggingFaceH4
HuggingFaceH4/stack-exchange-preferences -
text generation model by Jackrong · transformers
Jackrong/DeepSeek-V4-Pro-Qwen3.5-9B-MTP-GGUF -
Qwen3.8-27B-antislop
Modelsimage text to text model by AlexWortega · transformers
AlexWortega/Qwen3.8-27B-antislop -
Airlock RLS
MCP serversScan a deployed site for an exposed Supabase service_role key and audit Row Level Security.
airlock-rls-mcp@0.1.1 -
maro
Agents & frameworksMulti-Agent Resource Optimization (MARO) platform is an instance of Reinforcement Learning as a Service (RaaS) for real-world resource optimization problems.
git clone https://github.com/microsoft/maro.git -
HarborRL
Agents & frameworksAn end-to-end framework for Agentic Reinforcement Learning.
git clone https://github.com/datamllab/HarborRL.git -
alem-env
Datasets & benchmarksCan LLM/MARL agents coordinate in long-horizon, open-ended tasks? NeurIPS 2026 (Evaluations and Datasets).
git clone https://github.com/alem-world/alem-env.git -
85+ pay-per-call MCP tools: trading, federal grants/contracts, SEC, FTD. x402 USDC/RLUSD. No keys.
-
Simreal-MLBench
Datasets & benchmarks[Public preview] Externally scored agentic ML research benchmark: 60 tasks, real competition ground truth. Open protocol, operated evaluation.
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.