Enso OS — AI skill for Claude Code
The first AI plugin that speaks first.
How to install Enso OS
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open amazinglvxw/enso-os and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Enso OS does
The first AI plugin that speaks first. Code-enforced learning + active forgetting + PAC (Proactive Accountability Challenge). Works with Claude Code, Gemini CLI, Hermes, OpenClaw.
Alternatives in AI
- Iai Personal Memory Engine — A cyber brain for your AI 866 ★
- OpenMobius Skill — ICT/SMC trading-knowledge skill for AI coding agents (Claude Code / Codex / OpenClaw / Hermes) 660 ★
- Metaharness — 🛠️ The meta-harness for AI agents — scaffold your own focused, branded agent harness with its own npx CLI, MC 616 ★
README
Quickstart • PAC 🪞 • What Enso Adds • Works With • How It Works • 中文
**Enso is the first AI plugin that speaks first.**
Every LLM product today — ChatGPT, Claude, Gemini, Perplexity — is built on the same anti-pattern: **AI responds, AI never initiates.** It observes your mistakes and stays silent. It sees your self-limiting patterns and waits for you to ask.
Enso breaks that silence. It is a discipline plugin that adds three things no mainstream AI product has by default:
- Code-enforced learning — errors become hooks, not prompts. No third strike.
- Active forgetting — stale knowledge is pruned. Not all memory is worth keeping.
- 🪞 PAC (Proactive Accountability Challenge) — AI that raises the issue you haven't asked about.
Install in 30 seconds. Just bash + python3 (pre-installed on macOS/Linux). Wraps around Claude Code, Hermes, OpenClaw, Gemini CLI. Your data stays local.
Session 2 learned" width="
Related Skills
Hicortex
Self-learning memory for AI agents — experience captured automatically, distilled into lessons overnight, shar
Heard
Jarvis for your coding agents — the voice layer for Claude Code, Codex, OpenClaw, Hermes & any AI workflow. Yo
Genesys
Open-source causal graph memory for AI agents. 89.9% on LoCoMo. MCP server with ACT-R scoring, spreading activ
Lastmemory
Persistent, token efficient memory network for coding agents: a neural network of markdown files anchored to r
Writing Style Skill
Writing style skill template with built-in auto-learning. AI writes → you edit → rules auto-extracted → SKILL.
Kitty Bridge
Universal LLM bridge for AI agents. Use Claude Code with MiniMax, Codex with GLM, or Gemini CLI with OpenRoute
Related Agents
Daedalai Lesson Scribe
Dispatch when a correction, gotcha, or non-obvious mistake has just been fixed in a DaedalAI-managed project a
Ad Attack Planner
Reasons about low-privilege-to-Domain-Admin paths in an authorized Active Directory assessment. Takes the enum
Rebalance Agent
Propone come allocare il PAC mensile (~400€) tra gli strumenti target per ridurre gli scostamenti dall'allocaz