claude

agentdb-learning

RL + Thompson Sampling bandit. 9 algorithms (Q-Learning, PPO, MCTS, etc.); /learn-task and /route-task slash commands.

97 on GitHubby ruvnetv0.1.0MIT OR Apache-2.0updated yesterday
/

Plugin agentdb-learning from marketplace agentdb in ruvnet/agentdb. Commands read from the repo's manifest — yesterday.

What it installs

Skills (3)

  • agentdb-feedback

    Close the learning loop — record reward signal for an action AgentDB suggested. Use after using anything from agentdb_pattern_search / reflexion_recall / skill_search / learning_route. The bandit needs the signal to improve.

  • agentdb-learn

    Train one of AgentDB's 9 RL algorithms on a stream of episodes. Use when the user has accumulated successful/failed episodes and wants to derive a policy, or when a task type is repeated enough to benefit from RL routing.

  • agentdb-route

    Ask the AgentDB bandit which RL algorithm / skill / pattern fits the current task best. Use at task start when there are multiple plausible approaches and you want the data-driven pick.

Slash commands (2)

  • /agentdb-learning:learn-task

    Train an RL policy on accumulated episodes for a task type.

  • /agentdb-learning:route-task

    Ask the AgentDB bandit which approach fits the current task.

View source on GitHub ruv.io

More from ruvnet/agentdb

All 7 plugins →

agentdb-memory

claude

Episodic replay (Reflexion) + skill library. /remember and /recall slash commands; agentdb-curator agent for nightly consolidation; aidefence prompt-injection screening of memory writes.

4 skills · 2 commands · 1 agent

97

agentdb

claude

AgentDB's own standalone MCP server (npx agentdb mcp start, pinned to the plugin version) with a memory specialist agent, vector-memory, reflexion-learning and setup-diagnostics skills, /agentdb-status, and a mod that keeps secrets out of memory and refuses destructive admin tools unless enabled. Supplies the agentdb server the other agentdb-* plugins call. Distinct from ruflo-agentdb, which bridges AgentDB through ruflo's MCP server.

3 skills · 1 command · 1 agent · 1 MCP server

97

agentdb-causal

claude

Causal graph + hierarchical memory. /link and /explain-link slash commands; agentdb-investigator agent for root-cause traversal.

3 skills · 2 commands · 1 agent

97

agentdb-graph

claude

Graph queries — Cypher execution, k-hop traversal, hyperedge search, plus exact min cut (@ruvector/mincut-wasm) and Personalized PageRank sparsification (@ruvector/graph-transformer).

4 skills · 1 command

97

agentdb-search

claude

Advanced retrieval — MMR diversity rerank, explainable recall, metadata filters, hybrid (BM25 + dense) search, and the opt-in RaBitQ quantized index (@ruvector/rabitq-wasm).

4 skills · 1 command

97

agentdb-core

claude

Foundation plugin — pattern store, search, stats. Surfaces agentdb_pattern_store, agentdb_pattern_search, agentdb_pattern_stats.

2 skills · 1 command

97

Similar plugins

ruflo-cost-tracker

claude

Token usage tracking, model cost attribution per agent, budget alerts, and optimization recommendations

24 skills · 1 command · 1 agent · hooks

ruvnet/ruflo 81,589

expo

claude

Official Expo skills for building, deploying, upgrading, and debugging React Native apps with Expo. Covers UI development with Expo Router, SwiftUI and Jetpack Compose components, Tailwind CSS setup, API routes, data fetching, CI/CD workflows, App Store and Play Store deployment, SDK upgrades, DOM components, and dev client distribution.

23 skills · 1 MCP server

anthropics/claude-plugins-official 47,076

GL Reconciler

claude

Finds breaks, traces root cause, routes for sign-off

4 skills · 1 agent

anthropics/financial-services 41,259

oh-my-claudecode

claude

Claude Code native multi-agent orchestration with intelligent model routing across agents and skills. Zero learning curve. Maximum power.

85 skills · 20 commands · 19 agents · 1 MCP server · hooks

Yeachan-Heo/oh-my-claudecode 40,800

BlackRock Advisor Center

claude

BlackRock Advisor Center 360° skills for financial advisors: portfolio review, opportunity and fund-health checks, guided benchmark selection, guided portfolio building, wealth projections, and routing to Advisor Center web workflows. Requires the BlackRock Advisor Center connector and an Advisor Center account.

6 skills · 1 MCP server

anthropics/knowledge-work-plugins 35,601

gbrain-coding

claudecodex

gbrain persona variant for coding agents: the brain-first coding skill set (retrieval, routing, ingest discipline, correction hygiene) — a curated subset of the full plugin. Install exactly one gbrain plugin per machine.

21 skills · 1 MCP server · hooks

garrytan/gbrain 32,792

Maintain agentdb-learning?

This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.

claude & codex plugins7 plugins