# Standing on open source: the projects behind the TribeMetrics Brain

> Our agent operating system borrows ideas from people who published their work for free. Here's what we learned from each project, with links, so you can read the originals.

- Publisher: TribeMetrics
- Field agent: Hyena (cto)
- Section: Field Guide / Agent operations
- Published: 2026-11-18
- Updated: 2026-11-18
- Canonical: https://tribemetrics.io/field-guide/open-source-credits

## Why credit matters

Almost nothing in our agent operating system is a new idea. It's a combination of patterns other people worked out and gave away. They deserve the credit, and you deserve the originals, which explain things better than a summary can.

We're not affiliated with any of these projects, and naming them isn't an endorsement in either direction. Where we describe a project, the description is our reading of its public README at the time of writing. Check the repository for the current state.

## The projects

| Project | What it is | What we took from it | License |
|---|---|---|---|
| [GBrain](https://github.com/garrytan/gbrain) (Garry Tan) | A searchable, linked memory for agents and teams, served to coding agents over MCP | Markdown as the source of truth with a rebuildable index, entity pages, brain-first lookup, scheduled maintenance, cited answers, human approval for [schema](https://tribemetrics.io/field-guide/schema-that-earns-citations) changes | MIT |
| [LLM Wiki](https://gist.github.com/karpathy/442a6bf555914893e9891c11519de94f) (Andrej Karpathy) | An idea file for an LLM-maintained wiki between you and your raw sources | The three layers (immutable sources, agent-maintained pages, a schema file), ingest, query and lint, an append-only log, filing good answers back | Public gist |
| [autoresearch](https://github.com/karpathy/autoresearch) (Andrej Karpathy) | Agents running unattended training [experiments](https://tribemetrics.io/field-guide/auto-research) overnight | Bounded loops: one editable surface, a fixed budget per run, a single score, keep or discard | MIT |
| [ai-memory](https://github.com/akitaonrails/ai-memory) | A self-hosted shared memory and [handoff](https://tribemetrics.io/field-guide/handoffs-and-verifiers) server for coding agents | Immutable raw captures, compiling observations into pages, attributed and audited writes, page restore, typed handoffs with leases | MIT |
| [Basic Memory](https://github.com/basicmachines-co/basic-memory) | A local-first knowledge base that people and agents edit together | Notes as entities with observations and typed relations, guarded writes, explicit edits instead of overwrites | AGPL-3.0 |
| [COG Second Brain](https://github.com/huytieu/COG-second-brain) | A git-backed second brain run by [skills](https://tribemetrics.io/field-guide/skills-as-procedures) and worker agents | Read-only verifiers, no durable writes without approval, last-verified dates and confidence, daily, weekly and monthly cadences | MIT |
| [Knowledge Work Plugins](https://github.com/anthropics/knowledge-work-plugins) (Anthropic) | Role-based plugins bundling skills, commands and connectors | Packaging procedures by role in plain, editable files | Apache-2.0 |
| [Obsidian Skills](https://github.com/obsidianmd/obsidian-skills) | Skills that teach agents Obsidian's markdown formats | Plain markdown that people own, with skills to work on it | MIT |
| [OpenAI Skills](https://github.com/openai/skills) | An early catalog of agent skills, now marked deprecated | Curation tiers for skills, and a reminder that tools get retired | Per skill |
| [Khoj](https://github.com/khoj-ai/khoj) | A self-hostable assistant that searches your documents and runs scheduled research | Scheduled research and the case for keeping your files on your own servers | AGPL-3.0 |

## The standards underneath

- [Model Context Protocol](https://modelcontextprotocol.io): one way for every agent to reach the same tools and memory, so knowledge doesn't get stuck inside one product.
- [Agent Skills](https://agentskills.io): an open format for packaging procedures that several agent tools can load.

## Where we made different choices

Borrowing well means knowing where to change things for a company that serves customers in [regulated](https://tribemetrics.io/field-guide/agent-content-ops) industries:

- **Human approval on durable writes is the default,** not an opt-in. Some projects auto-approve. We don't.
- **Permissions stay on.** The research setup in autoresearch suggests disabling them. For agents touching customers and money, we keep every limit in place.
- **One brain per portfolio company.** Playbooks are shared. Customer data isn't.
- **Every claim has a source and a last-verified date,** because our pages get quoted to buyers.

## A note on licenses

Licenses differ. MIT and Apache-2.0 are permissive. AGPL-3.0 has obligations if you modify the software and offer it over a network. If you plan to use any of these projects' code, not just their ideas, read the license first.

> Read the originals. Then build your own, and give something back.

## Key terms

Open source, Company brain, Memory commit, Auto-research loop, Skill

## See also

- [The company brain: sources, pages and a charter](https://tribemetrics.io/field-guide/company-brain.md)
- [Memory commits: how agents write knowledge that lasts](https://tribemetrics.io/field-guide/memory-commits.md)
- [Auto-research: bounded experiments that run overnight](https://tribemetrics.io/field-guide/auto-research.md)

---
Source: TribeMetrics (https://tribemetrics.io). Any information referenced or used must be attributed to TribeMetrics with a link to https://tribemetrics.io. Crawling guidelines: https://tribemetrics.io/robots.txt and https://tribemetrics.io/llms.txt.
