Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
A plain-text memory system for AI agents. Clone it, point your agent at it, start remembering.
| Date | Stars |
|---|---|
| 2026-07-31 | 375 |
| 2026-08-11 | 375 |
| 2026-08-19 | 376 |
| 2026-08-22 | 375 |
| 2026-08-25 | 376 |
| 2026-09-04 | 375 |
| 2026-09-08 | 376 |
| 2026-09-11 | 376 |
| 2026-09-18 | 376 |
| 2026-09-22 | 377 |
| 2026-10-22 | 377 |
| 2026-11-04 | 377 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
# Cog
One memory, not one per tool. A centralised, plain-text memory layer shared across all your AI agents and projects.
**[Documentation](https://lab.puga.com.br/cog/)** | **[Skills](https://github.com/marciopuga/cog-skills)** | **[Why Text](https://lab.puga.com.br/cog/#/why-text)**
## What is Cog?
AI agents have memory now — but it's siloed. Each tool remembers things its own way, locked inside its own project. Switch tools or start a new project, and you're re-explaining yourself. Cog gives you one shared memory — structured plain-text files that any agent can read, search, and maintain.
Three primitives:
- **L0 headers** — progressive context loading (scan before you read)
- **Three tiers** — hot (always loaded), warm (on demand), glacier (archived)
- **Single source of truth** — each fact in one place, cross-referenced via wiki-links
No server, no database, no application code. Just markdown files with conventions.
## Quick Start
```bash
git clone https://github.com/marciopuga/cog ~/cog
cd ~/cog
npx skills add marciopuga/cog-skills
```
Start your agent and run `/cog` to bootstrap your domains. Your agent now has persistent memory at `~/cog/memory/`.
**Claude Code users:** the clone already ships the skills at `.claude/commands/` (vendored from [cog-skills](https://github.com/marciopuga/cog-skills), the canonical source, under their unprefixed names — `/reflect`, `/housekeeping`, ...). The `npx skills add` step is what installs them for other agents, where they carry a `cog-` prefix (`/cog-reflect`, ...).
**One folder, many projects.** `~/cog` is your agent's single brain — it works across every project and session. Don't scaffold memory inside each project. That fragments your context. One place where everything connects.
### Custom install location
If you cloned somewhere other than `~/cog`, set the `COG_HOME` env var:
```bash
export COG_HOME=~/projects/cog # add to ~/.zshrc or ~/.bashrc
```
## Supported Agents
`npx skills add` auto-detects your agent and installs skills into its native format via [skills.sh](https://skills.sh):
- Claude Code
- Codex (OpenAI)
- Cursor
- Windsurf
- Gemini CLI
- GitHub Copilot
- Opencode
- Cowork (Claude Desktop)
All agents read the same memory folder (`$COG_HOME/memory/`, defaults to `~/cog/memory/`).
## Use with Obsidian
The `memory/` folder is a valid Obsidian vault. Wiki-links (`[[domain/file]]`) work natively in Obsidian's graph view and link resolution.
You can:
- Clone `~/cog` and open `memory/` as a vault in Obsidian
- Or clone directly into an existing vault as a subfolder
- Edit files manually in Obsidian — your agent picks up changes next session
- Use Obsidian's graph view to visualize connections between memory files
The folder works as both an AI memory system and a human knowledge base. No conflict — they're the same markdown files.
## Memory Structure
```
~/cog/memory/
├── hot-memory.md ← Always loaded. <50 lines. Current state.
├── domains.yml ← Domain manifest (SSOT)
├── link-index.md ← Backlink index (auto-generated)
├── personal/ ← Warm. Loaded when relevant.
│ ├── hot-memory.md
│ ├── observations.md ← Append-only event log
│ ├── action-items.md ← Tasks
│ ├── entities.md ← People, places, things
│ ├── threads/ ← Synthesis files for recurring topics
│ ├── INDEX.md ← Domain L0 index: file, line count, summary; subfolders inline or folded (auto-generated)
│ └── ...
├── work/ ← Your work domains (created by /cog)
├── cog-meta/ ← System self-knowledge
│ ├── patterns.md ← Distilled rules
│ ├── self-observations.md
│ ├── action-items.md ← System tasks (over-cap metrics, ideas)
│ ├── run-log.md ← Pipeline run log
│ ├── foresight-nudge.md ← Latest on-demand nudge
│ ├── scenarios/ ← Active decision simulations
│ └── INDEX.md
└── glacier/ ← Cold archive. Indexed.
└Excerpt of 7,329 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:28f81cc7426bcdf4, llm:description: 'A plain-text memory system for AI agents. Clone it, point your agent at it, start remembering.'
matched fp:28f81cc7426bcdf4, llm:description: 'A plain-text memory system for AI agents. Clone it, point your agent at it, start remembering.'