claude

learning-agents

Auto-improving AI sub-agents that learn from their mistakes across sessions

51 on GitHubby DeepWorkv0.1.0MITupdated 3 months agolearning
/

Plugin learning-agents from marketplace deepwork-plugins in Unsupervisedcom/deepwork. Commands read from the repo's manifest — 1 month ago.

This plugin runs code on your machine — its hooks fire automatically on events like tool use. The exact commands are listed below; read them before installing.

What it installs

Skills (9)

  • create-agent

    Creates a new LearningAgent with directory structure, core-knowledge.md, and Claude Code agent file. Guides the user through initial configuration.

  • identify

    Reads a session transcript and identifies issues where a LearningAgent made mistakes, had knowledge gaps, or underperformed. Creates issue files for each problem found.

  • incorporate-learnings

    Takes investigated issues and incorporates the learnings into the LearningAgent's knowledge base by updating core-knowledge.md, topics, or learnings files.

  • investigate-issues

    Investigates identified issues in a LearningAgent session by reading the transcript, determining root causes, and updating issue files with investigation reports.

  • learn

    Runs the learning cycle on all LearningAgent sessions with pending transcripts. Identifies issues, investigates root causes, and incorporates learnings into agent definitions.

  • learning-agents

    Dispatch entry point for the LearningAgents plugin. Routes to sub-commands for creating agents, running learning cycles, and reporting issues.

  • prompt-review

    Reviews a prompt/instruction file against Anthropic prompt engineering best practices. Use when evaluating skill files, agent definitions, or instruction chunks for quality.

  • report-issue

    Creates an issue file tracking a problem observed in a LearningAgent session. Used by the identify skill and can be invoked directly to report issues in real-time.

  • setup

    Configures project permissions for the LearningAgents plugin. Adds required Bash and file access rules to .claude/settings.json.

Subagents (1)

  • learning-agent-expert

    Expert on the LearningAgent system. Operates on LearningAgent files: identifies issues in transcripts, investigates root causes, and incorporates learnings into agent definitions.

Hooks (2)

  • PostToolUse

    ${CLAUDE_PLUGIN_ROOT}/hooks/post_task.sh

  • Stop

    ${CLAUDE_PLUGIN_ROOT}/hooks/session_stop.sh

View source on GitHub

More from Unsupervisedcom/deepwork

All 2 plugins →

deepwork

claude

Framework for AI-powered multi-step workflows with quality gates

8 skills · 1 agent · 1 MCP server · hooks

51

Similar plugins

mattpocock-skills

claude

Matt Pocock's agent skills for real engineering (grilling, spec/ticket flows, TDD, code review, domain modelling and more).

39 skills

mattpocock/skills 323,108

claude-mem

claudecodex

Persistent memory for Claude Code: the next session starts where the last one left off.

29 skills · 1 MCP server · hooks

thedotmack/claude-mem 116,618

mem0

claudecodex

Cross-session memory and token savings for coding agents.

6 skills · 1 agent · 1 MCP server · hooks

mem0ai/mem0 68,893

context7

claudecodex

Up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your coding agent's context.

1 MCP server

upstash/context7 64,709

agent-browser

claude

Automates browser interactions for web testing, form filling, screenshots, and data extraction

12 skills

vercel-labs/agent-browser 50,373

pensyve

claude

Universal memory runtime for Claude Code with cross-session memory, entity-aware recall, lifecycle hooks, skills, commands, and memory-curator agents

7 skills · 7 commands · 2 agents · hooks

wshobson/agents 42,461

Maintain learning-agents?

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 plugins2 plugins