InnerVault

Library

85,340 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.

Results

  1. DiscoveryRSI

    Agents & frameworks

    DiscoveryRSI: Recursively Learning to Discover Valuable Hypotheses

    Stale GitHub, Gen-Verse 142 ★Custom licence (see repository)Updated 17 days ago

    git clone https://github.com/Gen-Verse/DiscoveryRSI.git
  2. paperthin

    Skills

    The skillbook for recursive self-improvement (RSI). NVIDIA's latest proof, unpacked with timeless engineering. Distilled from the OpenAI harness engineering hackathon winner's zero-touch method.

    Indexed GitHub, LilMGenius 1,445 ★MITUpdated yesterday

    git clone https://github.com/LilMGenius/paperthin.git
  3. awesome-rsi

    Docs & tutorials

    A curated research map of Recursive Self-Improvement (RSI): models, agents, harnesses, embodied systems, automated AI R&D, benchmarks, and safety.

    Stale GitHub, lobehub 766 ★CC0-1.0Updated 32 days ago

    git clone https://github.com/lobehub/awesome-rsi.git
  4. A curated list for Self-Improvement in Foundation Model Based Agentic Systems.

    Stale GitHub, selfimproving-agent 626 ★MITUpdated 4 days ago

    git clone https://github.com/selfimproving-agent/Awesome-Self-Improving-Agents.git
  5. Raven

    Agents & frameworks

    The Harness of Harnesses • Super Agent: a trusted, persistent, self-evolving multi-agent ecosystem for all-domain collaboration.

    Indexed GitHub, EverMind-AI 6,223 ★Apache-2.0Updated today

    git clone https://github.com/EverMind-AI/Raven.git
  6. Proteus

    Agents & frameworks

    Self-evolution for any agent harness. Plug in. Evolve. Measure.

    Indexed GitHub, proteus-evolve 112 ★MITUpdated 2 days ago

    git clone https://github.com/proteus-evolve/Proteus.git
  7. Awesome-AI4AI

    Datasets & benchmarks

    Updated weekly — until humanity achieves AI4AI. 1148 curated papers across Benchmarks, Harness Design, and Model Design — from long-horizon agents to recursive self-improvement. Citation rankings, GitHub stars, and source-verified weekly news.

    Stale GitHub, KaiWU5 218 ★MITUpdated 8 days ago

    git clone https://github.com/KaiWU5/Awesome-AI4AI.git
  8. text generation model by Teriminal-RSI · transformers

    Indexed Hugging Face Hub, Teriminal-RSI 34 ♥apache-2.0Updated 26 days ago

    Teriminal-RSI/Terminal-RSI-27B
  9. RSI-Jev

    Agents & frameworks

    Typed-decision models (noul / choice / score) trained by a self-improving loop of AI agents — checkpoints, the code that produced them, and every version that failed.

    Indexed GitHub, Shanghua-Gao 137 ★MITUpdated today

    git clone https://github.com/Shanghua-Gao/RSI-Jev.git
  10. rutis

    Agents & frameworks

    A plugin runtime for software that iterates on itself — the substrate where agents write, swap and hot-reload their own plugins in Rust, TypeScript, Python and Go, across processes and machines.

    Indexed GitHub, arcships 173 ★MITUpdated today

    git clone https://github.com/arcships/rutis.git
  11. gbase

    Agents & frameworks

    GBase — Recursive Self-Improvement Agent Framework. Memory, evolution, quality gates, identity system, and 40+ auto-registered tools.

    Stale GitHub, garyqlin 115 ★MITUpdated 4 months ago

    git clone https://github.com/garyqlin/gbase.git
  12. lrsi

    MCP servers

    Local recursive self-improvement OS MCP with fail-closed governance and gated mutation tools.

    Stale Official MCP Registry, io.github.ANAMIZED Updated 2 months ago

  13. honey-stack

    Skills

    Always-on workflow layer for Claude Code and Codex: right-sized tasks, smallest complete change, proof before done, plus RSI that learns from every session.

    Indexed GitHub, umararshad4 5 ★MITUpdated 2 days ago

    git clone https://github.com/umararshad4/honey-stack.git
  14. amfs

    Agents & frameworks

    Recursive Self-Improvement for AI agents and models, helping your agents self-improve with every run

    Stale GitHub, raia-live 92 ★Apache-2.0Updated 6 days ago

    git clone https://github.com/raia-live/amfs.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.