InnerVault

Library

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

Results

  1. claude-skills

    Skills

    Reference-backed ERP assistants for Claude Code — Sage 300 (Accpac), Sage 200 Evolution (Pastel), and SAP Business One. A Claude Code plugin marketplace for consultants and integrators.

    Stale GitHub, fdtaljaard 10 ★MITUpdated 26 days ago

    git clone https://github.com/fdtaljaard/claude-skills.git
  2. GDPevo

    Datasets & benchmarks

    A Benchmark for Evaluating Agent Self-Evolution on Real Business Tasks

    Stale GitHub, Prism-Shadow 119 ★Apache-2.0Updated 18 days ago

    git clone https://github.com/Prism-Shadow/GDPevo.git
  3. Recuris

    Skills

    Recursive Experiential–Working Memory Evolution for Long-Horizon Agent Harnesses

    Stale GitHub, Gen-Verse 238 ★Apache-2.0Updated 2 months ago

    git clone https://github.com/Gen-Verse/Recuris.git
  4. agentdescent

    Agents & frameworks

    Gradient descent, but the parameters are agents — a parallel, asynchronous framework for self-evolving agents (skills, prompts, harnesses). Diffs are the gradients; the aggregator is the optimizer.

    Indexed GitHub, ThinkFlowLab 221 ★MITUpdated today

    git clone https://github.com/ThinkFlowLab/agentdescent.git
  5. database-lab-engine

    Agents & frameworks

    DBLab enables 🖖 database branching and ⚡️ thin cloning for any Postgres database and empowers DB testing in CI/CD. This optimizes database-related costs while improving time-to-market and software quality. Follow to stay updated.

    Stale GitHub, postgres-ai 2,795 ★Apache-2.0Updated 5 days ago

    git clone https://github.com/postgres-ai/database-lab-engine.git
  6. 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
  7. evolving-agents

    Agents & frameworks

    A director agent that learns how your team works: it plans by walking your CLAUDE.md and memory as linked statements, delegates to Claude Code or local models, and keeps each lesson as a gated, versioned patch. Measured: 0.929 vs 0.589.

    Stale GitHub, EvolvingAgentsLabs 456 ★Apache-2.0Updated 27 days ago

    git clone https://github.com/EvolvingAgentsLabs/evolving-agents.git
  8. LLM-driven evolution of prompts and pipelines. Evolves the prompt and the pipeline's parameters together against your labeled data, cuts losing candidates early, and shows every measurement behind the winner. Open source.

    Indexed GitHub, PromptPotter 7 ★Custom licence (see repository)Updated yesterday

    git clone https://github.com/PromptPotter/prompt-potter-optimizer.git
  9. ScienceClaw

    AI repositories

    Verifiable program-level self-evolution for AI-for-Science agents: Skills and typed Operators grow from replay-verified executions.

    Stale GitHub, beita6969 1,022 ★MITUpdated 16 days ago

    git clone https://github.com/beita6969/ScienceClaw.git
  10. 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
  11. 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
  12. minitok

    MCP servers

    Verified coding workflows with planning, verification, bounded retries, evidence, and evolution.

    Stale Official MCP Registry, dev.minitok Updated 23 days ago 2 notes

    @flotic/minitok@1.5.4
  13. AstroWay Forecasting

    MCP servers

    Transits, progressions, directions, returns, cosmobiology and evolutionary technique.

    Stale Official MCP Registry, info.astroway Updated 3 days ago 1 note

  14. StratEvo

    MCP servers

    Quantitative trading: quotes, backtesting, screening, and genetic algorithm strategy evolution.

    Stale Official MCP Registry, io.github.NeuZhou Updated 7 months ago 1 note

    stratevo@6.0.3
  15. KIP

    MCP servers

    Knowledge Graphs to enable memory persistence, knowledge evolution, explainable interaction.

    Stale Official MCP Registry, io.github.ldclabs Updated 10 months ago 2 notes

    @ldclabs/kip-mcp-server@1.0.1
  16. quantum-mcp

    MCP servers

    GPU-accelerated MCP server: quantum mechanics, wavefunction evolution, Schrodinger simulations

    Stale Official MCP Registry, io.github.andylbrummer Updated 10 months ago 1 note

    scicomp-quantum-mcp@0.1.6
  17. 让 Agent 的工作方式可组合、可审查、可持续改进,最终实现 Agent Self Evoling。 DeepSeek Harness Web plugin with composable task controls and isolated, human-reviewed self-evolution.

    Stale GitHub, GraySilver 200 ★MITUpdated 11 days ago

    git clone https://github.com/GraySilver/dsh-evolve-modes.git
  18. evo-nexus

    Agents & frameworks

    The open source operating system for AI-powered businesses

    Stale GitHub, evolution-foundation 546 ★Custom licence (see repository)Updated 6 months ago

    git clone https://github.com/evolution-foundation/evo-nexus.git
  19. Circuitarium MCP

    MCP servers

    MCP tools for CRUMB artifacts and Logisim-evolution analysis and non-interactive simulation.

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

    circuitarium-mcp@0.3.1
  20. Skill Maintenance

    MCP servers

    技能库维护 MCP server:损坏扫描/改前备份/决策日志/体检(skill-evolution 机械环节工具化),uvx 一行接入

    Stale Official MCP Registry, io.github.mo9652962-ai Updated 47 days ago 1 note

    skill-maintenance-mcp@0.1.2
  21. Atlas-MultiAsset-Advisor

    Agents & frameworks

    Atlas - a DeepSeek-driven multi-asset investment advisor agent: risk profiling, strategy allocation, factor self-evolution, macro/geopolitics fusion, family-office global basing.

    Indexed GitHub, Bruce848647703 91 ★Apache-2.0Updated 6 days ago

    git clone https://github.com/Bruce848647703/Atlas-MultiAsset-Advisor.git
  22. 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
  23. cognitive-substrate

    MCP servers

    28-layer cognitive substrate with cross-session ToT evolutionary memory and self-telemetry tools

    Stale Official MCP Registry, io.github.JaysonAIOnline Updated 2 months ago 1 note

    mcp-cognitive-substrate@1.0.1
  24. SkillHone

    Skills

    Continual agent skill evolution through persistent decision history. Whole-skill optimisation (SKILL.md + scripts + references) with every decision landing as a local Git issue / PR / wiki. Runs on any agentskills.io runtime — Claude Code, Codex, OpenClaw, Hermes.

    Stale GitHub, Tencent 172 ★Custom licence (see repository)Updated 13 days ago

    git clone https://github.com/Tencent/SkillHone.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.