Agentdb Learning Plugins
Create and train AgentDB learning plugins with nine reinforcement-learning templates so agents improve behavior from experience using WASM-accelerated inference.
Overview
AgentDB Learning Plugins is an agent skill for the Build phase that creates and trains AgentDB learning plugins using nine RL algorithms and CLI scaffolding for self-improving agents.
Install
npx skills add https://github.com/ruvnet/ruflo --skill agentdb-learning-pluginsWhat is this skill?
- 9 reinforcement learning algorithms via AgentDB plugin system (Decision Transformer, Q-Learning, SARSA, Actor-Critic, an
- CLI wizard: npx agentdb@latest create-plugin with templates, dry-run, and custom output paths
- npx agentdb@latest list-templates for discoverable plugin starting points
- WASM-accelerated neural inference cited for 10–100x faster training versus naive loops
- Targets self-learning agents, offline RL, and behavior optimization through experience
- Train models 10–100x faster with WASM-accelerated neural inference (per SKILL.md)
- AgentDB v1.0.7+ prerequisite
Adoption & trust: 624 installs on skills.sh; 58.5k GitHub stars; 1/3 security scanners passed (skills.sh audits).
What problem does it solve?
You want agents that adapt from experience but lack a structured way to pick RL algorithms, scaffold plugins, and train them inside AgentDB.
Who is it for?
Solo builders on agentic-flow/AgentDB stacks experimenting with offline RL or policy improvement from trajectories and rewards.
Skip if: Teams who only need static tool-calling integrations with no reinforcement learning or plugin training loop.
When should I use this skill?
Building self-learning agents, implementing RL, or optimizing agent behavior through experience with AgentDB plugins.
What do I get? / Deliverables
You produce AgentDB learning plugins from named templates, trained with WASM-accelerated inference, ready to plug into autonomous agent workflows.
- AgentDB learning plugin scaffold from a named RL template
- Trained plugin artifact ready for agent deployment
Recommended Skills
Journey fit
Building self-learning agent plugins is core agent-tooling work during product construction, not a launch or ops monitoring task. AgentDB CLI create-plugin flows, RL templates, and deployment of learning plugins sit squarely in agent-tooling for autonomous systems.
How it compares
RL plugin scaffolding on AgentDB—not a generic vector-memory skill or a one-shot prompt template.
Common Questions / FAQ
Who is agentdb learning plugins for?
Developers building self-learning or autonomous agents on AgentDB who understand basic RL concepts and want CLI-driven plugin templates.
When should I use agentdb learning plugins?
Use it in Build/agent-tooling when implementing RL, creating learning plugins, or optimizing agent behavior from logged experience.
Is agentdb learning plugins safe to install?
Training plugins runs local CLI and may execute WASM inference code—review the Security Audits panel on this Prism page before running npx agentdb in sensitive environments.
SKILL.md
READMESKILL.md - Agentdb Learning Plugins
# AgentDB Learning Plugins ## What This Skill Does Provides access to 9 reinforcement learning algorithms via AgentDB's plugin system. Create, train, and deploy learning plugins for autonomous agents that improve through experience. Includes offline RL (Decision Transformer), value-based learning (Q-Learning), policy gradients (Actor-Critic), and advanced techniques. **Performance**: Train models 10-100x faster with WASM-accelerated neural inference. ## Prerequisites - Node.js 18+ - AgentDB v1.0.7+ (via agentic-flow) - Basic understanding of reinforcement learning (recommended) --- ## Quick Start with CLI ### Create Learning Plugin ```bash # Interactive wizard npx agentdb@latest create-plugin # Use specific template npx agentdb@latest create-plugin -t decision-transformer -n my-agent # Preview without creating npx agentdb@latest create-plugin -t q-learning --dry-run # Custom output directory npx agentdb@latest create-plugin -t actor-critic -o .$plugins ``` ### List Available Templates ```bash # Show all plugin templates npx agentdb@latest list-templates # Available templates: # - decision-transformer (sequence modeling RL - recommended) # - q-learning (value-based learning) # - sarsa (on-policy TD learning) # - actor-critic (policy gradient with baseline) # - curiosity-driven (exploration-based) ``` ### Manage Plugins ```bash # List installed plugins npx agentdb@latest list-plugins # Get plugin information npx agentdb@latest plugin-info my-agent # Shows: algorithm, configuration, training status ``` --- ## Quick Start with API ```typescript import { createAgentDBAdapter } from 'agentic-flow$reasoningbank'; // Initialize with learning enabled const adapter = await createAgentDBAdapter({ dbPath: '.agentdb$learning.db', enableLearning: true, // Enable learning plugins enableReasoning: true, cacheSize: 1000, }); // Store training experience await adapter.insertPattern({ id: '', type: 'experience', domain: 'game-playing', pattern_data: JSON.stringify({ embedding: await computeEmbedding('state-action-reward'), pattern: { state: [0.1, 0.2, 0.3], action: 2, reward: 1.0, next_state: [0.15, 0.25, 0.35], done: false } }), confidence: 0.9, usage_count: 1, success_count: 1, created_at: Date.now(), last_used: Date.now(), }); // Train learning model const metrics = await adapter.train({ epochs: 50, batchSize: 32, }); console.log('Training Loss:', metrics.loss); console.log('Duration:', metrics.duration, 'ms'); ``` --- ## Available Learning Algorithms (9 Total) ### 1. Decision Transformer (Recommended) **Type**: Offline Reinforcement Learning **Best For**: Learning from logged experiences, imitation learning **Strengths**: No online interaction needed, stable training ```bash npx agentdb@latest create-plugin -t decision-transformer -n dt-agent ``` **Use Cases**: - Learn from historical data - Imitation learning from expert demonstrations - Safe learning without environment interaction - Sequence modeling tasks **Configuration**: ```json { "algorithm": "decision-transformer", "model_size": "base", "context_length": 20, "embed_dim": 128, "n_heads": 8, "n_layers": 6 } ``` ### 2. Q-Learning **Type**: Value-Based RL (Off-Policy) **Best For**: Discrete action spaces, sample efficiency **Strengths**: Proven, simple, works well for small$medium problems ```bash npx agentdb@latest create-plugin -t q-learning -n q-agent ``` **Use Cases**: - Grid worlds, board games - Navigation tasks - Resource allocation - Discrete decision-making **Configuration**: ```json { "algorithm": "q-learning", "learning_rate