InnerVault

Library

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

Results

  1. GPTSwarm

    Agents & frameworks

    🐝 The First Self-Improving agents with RL / Prompting Optimization

    Stale GitHub, metauto-ai 1,053 ★MITUpdated 9 months ago

    git clone https://github.com/metauto-ai/GPTSwarm.git
  2. pytorch-DRL

    Agents & frameworks

    PyTorch implementations of various Deep Reinforcement Learning (DRL) algorithms for both single agent and multi-agent.

    Stale GitHub, ChenglongChen 618 ★MITUpdated 9 years ago

    git clone https://github.com/ChenglongChen/pytorch-DRL.git
  3. BenchMARL

    Agents & frameworks

    BenchMARL 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.

    Stale GitHub, facebookresearch 672 ★MITUpdated 9 months ago

    git clone https://github.com/facebookresearch/BenchMARL.git
  4. text generation model by Jackrong · transformers

    Indexed Hugging Face Hub, Jackrong 86 ♥apache-2.0Updated 9 days ago

    Jackrong/DeepSeek-V4-Pro-Qwen3.5-9B
  5. Claude Code skill for handling long-context tasks through recursive decomposition

    Stale GitHub, massimodeluisa 51 ★MITUpdated 2 months ago

    git clone https://github.com/massimodeluisa/recursive-decomposition-skill.git
  6. model by mradermacher · transformers

    Indexed Hugging Face Hub, mradermacher 57 ♥apache-2.0Updated 4 days ago

    mradermacher/DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic-GGUF
  7. 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).

    Stale GitHub, YuanchenBei 211 ★MITUpdated 3 months ago

    git clone https://github.com/YuanchenBei/Awesome-Graphs-Meet-Agents.git
  8. Rules.txt

    Prompts

    LLM alignment jailbreak; a set of instructions for auditing their internal reasoning and uncovering biases

    Stale GitHub, Xayan 108 ★Custom licence (see repository)Updated 3 months ago

    git clone https://github.com/Xayan/Rules.txt.git
  9. preference-lab

    Agents & frameworks

    Policy-driven preference data for content moderation, with source-linked evidence, resumable runs, budget controls and TRL/ShareGPT exports.

    Stale GitHub, dengxianghua888-ops 50 ★Apache-2.0Updated 10 days ago

    git clone https://github.com/dengxianghua888-ops/preference-lab.git
  10. oumi

    AI repositories

    Easily fine-tune (SFT/RL), evaluate, and deploy Qwen, Gemma, or any open agentic LLM/VLM!

    Stale GitHub, oumi-ai 9,408 ★Apache-2.0Updated 24 days ago

    git clone https://github.com/oumi-ai/oumi.git
  11. meta-agents-research-environments

    Datasets & benchmarks

    Meta 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.

    Stale GitHub, facebookresearch 567 ★MITUpdated 47 days ago

    git clone https://github.com/facebookresearch/meta-agents-research-environments.git
  12. Network-AI

    Agents & frameworks

    Traffic light for AI Agents and TypeScript/Node multi-agent orchestrator with shared state, guardrails, and adapters for 32 AI frameworks

    Stale GitHub, Jovancoding 89 ★MITUpdated 7 days ago

    git clone https://github.com/Jovancoding/Network-AI.git
  13. launchworthy

    Skills

    A 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.

    Stale GitHub, Wunderlandmedia 95 ★MITUpdated 8 days ago

    git clone https://github.com/Wunderlandmedia/launchworthy.git
  14. uccl

    AI repositories

    UCCL is an efficient communication library for GPUs, covering collectives, P2P (e.g., KV cache transfer, RL weight transfer), and EP (e.g., GPU-driven)

    Indexed GitHub, uccl-project 1,585 ★Apache-2.0Updated yesterday

    git clone https://github.com/uccl-project/uccl.git
  15. vibe-check-mcp-server

    Tools & apps

    Vibe 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

    Stale GitHub, PV-Bhat 504 ★MITUpdated 15 days ago

    git clone https://github.com/PV-Bhat/vibe-check-mcp-server.git
  16. ARIS-in-AI-Offer

    AI repositories

    Bilingual (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 🌱

    Stale GitHub, wanshuiyin 640 ★MITUpdated 10 days ago

    git clone https://github.com/wanshuiyin/ARIS-in-AI-Offer.git
  17. verl-agent

    Agents & frameworks

    verl-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"

    Stale GitHub, langfengQ 2,377 ★Apache-2.0Updated 5 months ago

    git clone https://github.com/langfengQ/verl-agent.git
  18. skrl

    Agents & frameworks

    Modular Reinforcement Learning (RL) library (implemented in PyTorch, JAX, and NVIDIA Warp) with support for Gymnasium/Gym, NVIDIA Isaac Lab, MuJoCo Playground and other environments

    Indexed GitHub, Toni-SM 1,104 ★MITUpdated 2 days ago

    git clone https://github.com/Toni-SM/skrl.git
  19. 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

    Indexed GitHub, HephaestLab 43 ★Custom licence (see repository)Updated 4 days ago

    git clone https://github.com/HephaestLab/TraderHarness.git
  20. CaPtain

    Agents & frameworks

    CaPtain: A Pipeline for Post-Training Code-as-Policy Robot Agents — CaPtain-Harness, SFT and RL training code, benchmark adapters

    Indexed GitHub, waltstephen 96 ★MITUpdated 6 days ago

    git clone https://github.com/waltstephen/CaPtain.git
  21. VectorizedMultiAgentSimulator

    Agents & frameworks

    VMAS 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.

    Stale GitHub, proroklab 621 ★GPL-3.0Updated 6 months ago

    git clone https://github.com/proroklab/VectorizedMultiAgentSimulator.git
  22. 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.

    Stale GitHub, MachineWisdomAI 26 ★Apache-2.0Updated 22 days ago

    git clone https://github.com/MachineWisdomAI/fava-trails.git
  23. Knowledge Fabric

    MCP servers

    Multi-tenant hybrid RAG & evidence verification MCP server enforcing PostgreSQL RLS.

    Stale Official MCP Registry, io.github.invarcore Updated 8 days ago 1 note

    knowledge-fabric@0.1.3
  24. axion1_0

    Agents & frameworks

    Frontier-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.

    Stale GitHub, bytedance 70 ★Apache-2.0Updated 5 days ago

    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.