Library
85,340 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
claude-skills
SkillsReference-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.
git clone https://github.com/fdtaljaard/claude-skills.git -
GDPevo
Datasets & benchmarksA Benchmark for Evaluating Agent Self-Evolution on Real Business Tasks
git clone https://github.com/Prism-Shadow/GDPevo.git -
Recuris
SkillsRecursive Experiential–Working Memory Evolution for Long-Horizon Agent Harnesses
git clone https://github.com/Gen-Verse/Recuris.git -
agentdescent
Agents & frameworksGradient 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.
git clone https://github.com/ThinkFlowLab/agentdescent.git -
database-lab-engine
Agents & frameworksDBLab 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.
git clone https://github.com/postgres-ai/database-lab-engine.git -
awesome-rsi
Docs & tutorialsA curated research map of Recursive Self-Improvement (RSI): models, agents, harnesses, embodied systems, automated AI R&D, benchmarks, and safety.
git clone https://github.com/lobehub/awesome-rsi.git -
evolving-agents
Agents & frameworksA 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.
git clone https://github.com/EvolvingAgentsLabs/evolving-agents.git -
prompt-potter-optimizer
SkillsLLM-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.
git clone https://github.com/PromptPotter/prompt-potter-optimizer.git -
ScienceClaw
AI repositoriesVerifiable program-level self-evolution for AI-for-Science agents: Skills and typed Operators grow from replay-verified executions.
git clone https://github.com/beita6969/ScienceClaw.git -
gbase
Agents & frameworksGBase — Recursive Self-Improvement Agent Framework. Memory, evolution, quality gates, identity system, and 40+ auto-registered tools.
git clone https://github.com/garyqlin/gbase.git -
Proteus
Agents & frameworksSelf-evolution for any agent harness. Plug in. Evolve. Measure.
git clone https://github.com/proteus-evolve/Proteus.git -
minitok
MCP serversVerified coding workflows with planning, verification, bounded retries, evidence, and evolution.
@flotic/minitok@1.5.4 -
AstroWay Forecasting
MCP serversTransits, progressions, directions, returns, cosmobiology and evolutionary technique.
-
StratEvo
MCP serversQuantitative trading: quotes, backtesting, screening, and genetic algorithm strategy evolution.
stratevo@6.0.3 -
KIP
MCP serversKnowledge Graphs to enable memory persistence, knowledge evolution, explainable interaction.
@ldclabs/kip-mcp-server@1.0.1 -
quantum-mcp
MCP serversGPU-accelerated MCP server: quantum mechanics, wavefunction evolution, Schrodinger simulations
scicomp-quantum-mcp@0.1.6 -
dsh-evolve-modes
Prompts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.
git clone https://github.com/GraySilver/dsh-evolve-modes.git -
evo-nexus
Agents & frameworksThe open source operating system for AI-powered businesses
git clone https://github.com/evolution-foundation/evo-nexus.git -
Circuitarium MCP
MCP serversMCP tools for CRUMB artifacts and Logisim-evolution analysis and non-interactive simulation.
circuitarium-mcp@0.3.1 -
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
skill-maintenance-mcp@0.1.2 -
Atlas-MultiAsset-Advisor
Agents & frameworksAtlas - a DeepSeek-driven multi-asset investment advisor agent: risk profiling, strategy allocation, factor self-evolution, macro/geopolitics fusion, family-office global basing.
git clone https://github.com/Bruce848647703/Atlas-MultiAsset-Advisor.git -
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 -
cognitive-substrate
MCP servers28-layer cognitive substrate with cross-session ToT evolutionary memory and self-telemetry tools
mcp-cognitive-substrate@1.0.1 -
SkillHone
SkillsContinual 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.
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.