# huytieu/COG-second-brain

Self-evolving second brain with 33 AI skills, 10 agents, and people CRM. Closed-loop harness: a V-model verification lifecycle where the worker never grades its own homework. Plus paired anti-slop design skills for marketing and product UI. Works with Claude Code, Cursor, Kiro, Gemini CLI, Codex.

Repository: https://github.com/huytieu/COG-second-brain
Canonical: https://ross.abutalabs.com/products/cog-second-brain
Language: HTML
License: MIT
License Family: permissive
Topics: agentic, ai-agents, claude-code, cursor, garry-tan, gbrain, gstack, knowledge-management, obsidian, productivity, second-brain, self-evolving, worker-agents, people-crm, agent-loop, loop-engineering, closed-loop, verification-harness, agent-plugins, agent-skills
Last push: 2026-08-25T15:32:13+00:00

## Health v2 (maintenance only)
Score: 83/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 99, release rhythm 96, longevity 23
- inputs: {"age_days": 322, "days_push": 8, "days_rel": 26, "gap_med": 10, "n_releases_24m": 6}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1049, forks 127 (observed 2026-08-28T04:03:20.579305+00:00)

## What it is
COG is a self-evolving second brain built from markdown files, Git, and AI agent skills, with 33 skills, 10 agents (6 workers plus 4 read-only verifiers), and a people CRM. It implements a closed-loop V-model verification lifecycle so workers never grade their own work, and integrates with Claude Code, Cursor, Kiro, Gemini CLI, Codex, and other markdown-reading agents.

## Use cases
- manage a personal knowledge base with AI agents
- set up a second brain in obsidian with git sync
- run AI agent workflows with verification loops
- track contacts and relationships with a people CRM
- add reusable AI skills to claude code or cursor
- delegate tasks to worker agents with independent verifiers
- keep notes as plain markdown without vendor lock-in

## When to choose
- you want a markdown-and-git-based second brain that works across multiple AI coding agents
- you need agent task execution with independent verification instead of self-grading
- you already use Obsidian, Claude Code, or Cursor and want agent skills layered on top

## When to avoid
- you need a hosted database-backed knowledge management app
- you don't use any AI coding agents or CLI tools
- you want a turnkey product rather than a skills framework you configure yourself

## Facets
- artifact type: framework
- maturity: active
- function: agent-framework, workflow-automation, documentation, markdown, version-control, chatbot
- domain: developer-tools
- platform: cli, cross-platform
- tags: second-brain, claude-code, cursor, obsidian, people-crm, verification-harness, agent-skills, closed-loop, self-evolving, gemini-cli, ai-agents, knowledge-management, automation, nodejs

## Member repositories
- huytieu/COG-second-brain (main) score 83

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:20.579305+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T07:00:29.308029+00:00, confidence not recorded.
  - readme: https://github.com/huytieu/COG-second-brain (fetched 2026-08-28T04:03:20.579305+00:00, sha 1400e0b26b04)
- Data as of 2026-08-30T08:39:29.467469+00:00.