A git-native, review-gated knowledge base for AI agents: they propose writes, you approve them. Every claim cites a source, every change is a diff in your repo. MCP + CLI.
-
Updated
Aug 23, 2026 - Python
A git-native, review-gated knowledge base for AI agents: they propose writes, you approve them. Every claim cites a source, every change is a diff in your repo. MCP + CLI.
Soul: The Persistent Memory Layer for Multi-Agent Systems. High-performance session orchestration with SQLite-based KV-Cache for MCP. Give your AI agents a soul that never forgets.
AI-powered second brain for Claude Code that builds itself. Extract knowledge from every session—past and present—into auto-organized Markdown. Local-first, queryable, learns your patterns.
Borg Internet Operating System - Just something I dreamed up. To try it out clone the client borgHUI. https://github.com/bitmonky/borgHUI
Biomimetic autonomous cognitive AI brain — never forgets, self-learning, hallucination-resistant, desktop-controllable
Your personal AI memory, connected to all your AI tools
A git repo that is your brain — markdown + Claude Code skills. Local-first, served online by BrainOutside.
The core belief layer for AI agents. MnemeBrain Lite stores structured beliefs instead of text memories — enabling contradiction detection, belief revision, and explainable reasoning.
AI brain for Non-Player Characters (NPCs) in video games. Built on Gemma-2 2B + Coqui XTTS-v2 with full support for Unity, Unreal Engine 5, and Godot 4.
The memory layer. Stores the FCL validation archive, routing event history, and the permanent record of everything the brain has learned. What survives here shapes how the whole system routes next time.
The relay station. Every signal enters here first — classified, routed, and dispatched to the correct brain region before processing begins. The thalamus does not think. It decides where thinking goes.
The right hemisphere. Domain knowledge, synthesis, and pattern recognition across disciplines. What the left hemisphere reasons about, the right hemisphere knows — science, history, culture, and emerging fields.
The security layer. Every output clears here before it exits. Threat detection, adversarial pattern recognition, red-team archive, and the Go/No-Go authority that can halt the entire system. Nothing bypasses it.
让Agent组成大脑——RollarTimerAgent
Provide AI agents with continuous identity and persistent memory across sessions and devices using a Git-native, open framework without proprietary APIs.
The corpus callosum. Bridges left and right hemispheres, holds the master manifest of the entire architecture, and serves as the single external communication channel — the CAPCOM of the AION brain.
The limbic layer. Personality, register, and internal state monitoring. ALBEDO lives here — the session instrument that governs tone, emotional signal detection, and the felt layer of every response.
Rust SDK for MnemeBrain — a belief memory system for AI agents. Supports MnemeBrain Lite and Full APIs.
The refinement layer. Precision after clearance. Every output passes through here for LAV gate validation, density calibration, and roughness preservation — the layer that makes the output worthy of the input.
A persistent memory system for AI agents using the Model Context Protocol (MCP). . Enables AI agents like Roo & Codex to store, share, and retrieve contextual knowledge across sessions.
Add a description, image, and links to the ai-brain topic page so that developers can more easily learn about it.
To associate your repository with the ai-brain topic, visit your repo's landing page and select "manage topics."