Self-evolving memory system for Claude Code — observes your behavior, extracts behavior patterns (instincts), and automatically applies them in future sessions
Self-evolving memory system for Claude Code.
/plugin marketplace add littleCareless/homunculus
/plugin install homunculus
~/.claude/homunculus/)See plugin/README.md for full documentation.
[Session] Tool calls
↓ Hooks (Pre/PostToolUse)
Layer 1: Observation Engine → observations.jsonl
↓ SessionEnd
Layer 2: Instinct Engine (statistical + semantic)
↓
instincts/personal/*.md
↓ filter confidence ≥ 0.7
~/.claude/rules/auto-evolved.md
↓ Claude Code natively loads
Layer 3: Injection → next session starts with learned rules
MIT
Executes bash commands
Hook triggers when Bash tool is used
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
npx claudepluginhub littlecareless/homunculus --plugin homunculusMemory compression system for Claude Code - persist context across sessions
Ultra-compressed communication mode. Cuts ~75% of tokens while keeping full technical accuracy by speaking like a caveman.
Multi-model consensus engine integrating OpenAI Codex CLI, Gemini CLI, and Claude CLI for collaborative code review and problem-solving.
Curate auto-memory, promote learnings to CLAUDE.md and rules, extract proven patterns into reusable skills.
Harness-native ECC operator layer - 67 agents, 271 skills, 92 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses