Micro Actinf — AI skill for Claude Code
⚡ Ultra-fast O(1) Active Inference & Bayesian Cognitive Governor for AI Agents (Antigravity, Claude, Cursor) & Embedded Systems.
How to install Micro Actinf
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open naderloocodelab/micro-actinf and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Micro Actinf does
⚡ Ultra-fast O(1) Active Inference & Bayesian Cognitive Governor for AI Agents (Antigravity, Claude, Cursor) & Embedded Systems. Zero-alloc C11 core (<36KB) + FastMCP server.
Alternatives in AI
- Pixel Agents — Compressed Reference — VS Code extension with embedded React webview: pixel art office where AI agents (Claude Code terminals) are an 6.5k ★
- Inference Serving — ai-research-skills vLLM, SGLang, TensorRT-LLM, llama.cpp 5.4k ★
- Deepreasoning — A high-performance LLM inference API and Chat UI that integrates DeepSeek R1's CoT reasoning traces with Anthr 5.4k ★
README
🧠 Micro-ActInf: Ultra-Fast $O(1)$ Active Inference & Bayesian Cognitive Governor
[](LICENSE) []() [-cyan.svg)]() []() []() []() []()
**Eliminate context drift, hallucination loops, and conversational token bloat in AI agents (Antigravity, Claude Desktop, Cursor) with Karl Friston's Free Energy Principle and an ultra-lightweight 20KB C11 POMDP engine.**
📑 Table of Contents
- Why Micro-ActInf? (The Problem & Solution)
- Feature Comparison vs Existing Frameworks
- Dual-Target Architecture
- How It Works: The Active Inference Loop
- The 6 Cognitive Regimes & 4 Action Policies
- Quickstart: Plug into AI Agents in 60 Seconds
- Embedded Systems & Game Engines (C11 Core)
- Mathematical Rigor
- Empirical Benchmarks
- [🇮🇷 راهنمای جامع فارسی (Persian Technical Guide)](#-راهنمای-جامع-فارسی-persian-technical-
Related Skills
AI Hook
Ultra-fast AI-agent hook dispatcher & autonomous rule engine (Rust + embedded QuickJS). Write guardrail rules
Fast File Search
Ultra-fast file search toolkit for AI agents, Neovim, and code editors. MCP server for Claude Code/Cursor/Code
Bayesian Reasoning
A cognitive base that shifts reasoning from binary judgments to calibrated probability thinking. Works with an
SynapseCode
Ultra-fast Code Graph & AST Pruning MCP Server for LLMs. Reduces context token consumption by 75%-90% in Claud
Kuzu Memory
Lightweight, embedded graph-based memory system for AI applications. Fast (<3ms recall), offline-first, with M
Ultimate MCP Server
Comprehensive MCP server exposing dozens of capabilities to AI agents: multi-provider LLM delegation, browser
Related Agents
Bnb Breaker
Heavy-cognitive-load agent that transforms a raw user prompt plus scout report into a layered spec directory u
Risk Assessor
Bayesian pre-mortem before risky changes or when choosing between approaches.
Model Reviewer
Use this agent to review a Bayesian model for correctness and best practices