TribeMetrics / Field Guide / Open-source credits
Agent operations

Standing on open source: the projects behind the TribeMetrics Brain

Published Nov 18, 20263 min readBy the TribeMetrics team
hyena
FIELD AGENTHyena · ctoEngineering, apps, design systems and security.
WITH
jaguarlion
IN ONE LINE

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.

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

ProjectWhat it isWhat we took from itLicense
GBrain (Garry Tan)A searchable, linked memory for agents and teams, served to coding agents over MCPMarkdown as the source of truth with a rebuildable index, entity pages, brain-first lookup, scheduled maintenance, cited answers, human approval for schema changesMIT
LLM Wiki (Andrej Karpathy)An idea file for an LLM-maintained wiki between you and your raw sourcesThe three layers (immutable sources, agent-maintained pages, a schema file), ingest, query and lint, an append-only log, filing good answers backPublic gist
autoresearch (Andrej Karpathy)Agents running unattended training experiments overnightBounded loops: one editable surface, a fixed budget per run, a single score, keep or discardMIT
ai-memoryA self-hosted shared memory and handoff server for coding agentsImmutable raw captures, compiling observations into pages, attributed and audited writes, page restore, typed handoffs with leasesMIT
Basic MemoryA local-first knowledge base that people and agents edit togetherNotes as entities with observations and typed relations, guarded writes, explicit edits instead of overwritesAGPL-3.0
COG Second BrainA git-backed second brain run by skills and worker agentsRead-only verifiers, no durable writes without approval, last-verified dates and confidence, daily, weekly and monthly cadencesMIT
Knowledge Work Plugins (Anthropic)Role-based plugins bundling skills, commands and connectorsPackaging procedures by role in plain, editable filesApache-2.0
Obsidian SkillsSkills that teach agents Obsidian's markdown formatsPlain markdown that people own, with skills to work on itMIT
OpenAI SkillsAn early catalog of agent skills, now marked deprecatedCuration tiers for skills, and a reminder that tools get retiredPer skill
KhojA self-hostable assistant that searches your documents and runs scheduled researchScheduled research and the case for keeping your files on your own serversAGPL-3.0

The standards underneath

  • Model Context Protocol: one way for every agent to reach the same tools and memory, so knowledge doesn't get stuck inside one product.
  • Agent Skills: 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 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.

Building in a legacy industry?

We bring the agent crew and the distribution. You bring what you know about the industry.

Pitch us →