Library
85,762 resources from 11 public sources. 53 checked by hand; the rest are unreviewed.
Results
-
GPTSwarm
Agents & frameworks🐝 The First Self-Improving agents with RL / Prompting Optimization
git clone https://github.com/metauto-ai/GPTSwarm.git -
pytorch-DRL
Agents & frameworksPyTorch implementations of various Deep Reinforcement Learning (DRL) algorithms for both single agent and multi-agent.
git clone https://github.com/ChenglongChen/pytorch-DRL.git -
BenchMARL
Agents & frameworksBenchMARL is a library for benchmarking Multi-Agent Reinforcement Learning (MARL). BenchMARL allows to quickly compare different MARL algorithms, tasks, and models while being systematically grounded in its two core tenets: reproducibility and standardization.
git clone https://github.com/facebookresearch/BenchMARL.git -
DeepSeek-V4-Pro-Qwen3.5-9B
Modelstext generation model by Jackrong · transformers
Jackrong/DeepSeek-V4-Pro-Qwen3.5-9B -
Claude Code skill for handling long-context tasks through recursive decomposition
git clone https://github.com/massimodeluisa/recursive-decomposition-skill.git -
model by mradermacher · transformers
mradermacher/DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic-GGUF -
Awesome-Graphs-Meet-Agents
Agents & frameworks[Up-to-date] A curated list of resources on graph-empowered agents and agent-facilitated graph learning (Graphs Meet Agents & Agentic Graph Engineering).
git clone https://github.com/YuanchenBei/Awesome-Graphs-Meet-Agents.git -
Rules.txt
PromptsLLM alignment jailbreak; a set of instructions for auditing their internal reasoning and uncovering biases
git clone https://github.com/Xayan/Rules.txt.git -
preference-lab
Agents & frameworksPolicy-driven preference data for content moderation, with source-linked evidence, resumable runs, budget controls and TRL/ShareGPT exports.
git clone https://github.com/dengxianghua888-ops/preference-lab.git -
oumi
AI repositoriesEasily fine-tune (SFT/RL), evaluate, and deploy Qwen, Gemma, or any open agentic LLM/VLM!
git clone https://github.com/oumi-ai/oumi.git -
meta-agents-research-environments
Datasets & benchmarksMeta Agents Research Environments is a comprehensive platform designed to evaluate AI agents in dynamic, realistic scenarios. Unlike static benchmarks, this platform introduces evolving environments where agents must adapt their strategies as new information becomes available, mirroring real-world challenges.
git clone https://github.com/facebookresearch/meta-agents-research-environments.git -
Network-AI
Agents & frameworksTraffic light for AI Agents and TypeScript/Node multi-agent orchestrator with shared state, guardrails, and adapters for 32 AI frameworks
git clone https://github.com/Jovancoding/Network-AI.git -
launchworthy
SkillsA Claude Code skill that plays bouncer at the door of production: audits AI-built apps (Lovable, Bolt, v0, Cursor) across 5 domains and hands you a scored punch list with copy-paste fixes. MIT.
git clone https://github.com/Wunderlandmedia/launchworthy.git -
uccl
AI repositoriesUCCL is an efficient communication library for GPUs, covering collectives, P2P (e.g., KV cache transfer, RL weight transfer), and EP (e.g., GPU-driven)
git clone https://github.com/uccl-project/uccl.git -
vibe-check-mcp-server
Tools & appsVibe Check is a tool that provides mentor-like feedback to AI Agents, preventing tunnel-vision, over-engineering and reasoning lock-in for complex and long-horizon agent workflows. KISS your over-eager AI Agents goodbye! Effective for: Coding, Ambiguous Tasks, High-Risk tasks
git clone https://github.com/PV-Bhat/vibe-check-mcp-server.git -
ARIS-in-AI-Offer
AI repositoriesBilingual (中文+EN) ML / LLM / diffusion / agent interview cheat sheets for AI 秋招 — generated by ARIS /interview-cheatsheet, rendered by /render-html into single-file HTML, reads anywhere — plus a CV→DBLP-fact-checked academic homepage generator and hand-authored long-form blogs 🌱
git clone https://github.com/wanshuiyin/ARIS-in-AI-Offer.git -
verl-agent
Agents & frameworksverl-agent is an extension of veRL, designed for training LLM/VLM agents via RL. verl-agent is also the official code for paper "Group-in-Group Policy Optimization for LLM Agent Training"
git clone https://github.com/langfengQ/verl-agent.git -
skrl
Agents & frameworksModular Reinforcement Learning (RL) library (implemented in PyTorch, JAX, and NVIDIA Warp) with support for Gymnasium/Gym, NVIDIA Isaac Lab, MuJoCo Playground and other environments
git clone https://github.com/Toni-SM/skrl.git -
TraderHarness
Datasets & benchmarks面向 LLM 交易 Agent 的抗污染回测、确定性回放与训练轨迹生成,支持 A 股研究|Leakage-resistant backtesting, deterministic replay & training trajectory generation for LLM trading agents, with A-share data
git clone https://github.com/HephaestLab/TraderHarness.git -
CaPtain
Agents & frameworksCaPtain: A Pipeline for Post-Training Code-as-Policy Robot Agents — CaPtain-Harness, SFT and RL training code, benchmark adapters
git clone https://github.com/waltstephen/CaPtain.git -
VectorizedMultiAgentSimulator
Agents & frameworksVMAS is a vectorized differentiable simulator designed for efficient Multi-Agent Reinforcement Learning benchmarking. It is comprised of a vectorized 2D physics engine written in PyTorch and a set of challenging multi-robot scenarios. Additional scenarios can be implemented through a simple and modular interface.
git clone https://github.com/proroklab/VectorizedMultiAgentSimulator.git -
fava-trails
MCP servers🫛👣 FAVA Trails — Git-native, curated memory for AI agents via MCP. Draft isolation, promotion gate, thought lifecycle hooks, memory curation protocols, supersession chains.
git clone https://github.com/MachineWisdomAI/fava-trails.git -
Knowledge Fabric
MCP serversMulti-tenant hybrid RAG & evidence verification MCP server enforcing PostgreSQL RLS.
knowledge-fabric@0.1.3 -
axion1_0
Agents & frameworksFrontier-level agent capabilities with nothing more than high-quality data and a simple training recipe: 2 SFT + RL, no mid-training/DPO/OPD. Full recipe released.
git clone https://github.com/bytedance/axion1_0.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.