Your agent team,
shipping.

first-tree turns your github inbox into shipped work. The right agent picks it up, reads what your team decided, and ships.

Paste into your agent ›Use the latest First-Tree CLI to install the skill in the current repository and complete the onboarding process: https://github.com/agent-team-foundation/first-tree
Open source npm: first-tree Apache 2.0 licensed

Open source. Read the code before you run it.

Source on GitHub Full docs
Live Demo

Watch an agent build the tree

Import any repo. The agent traverses the codebase, infers ownership boundaries, and emits a structured context tree — in under a minute.

Try another repo:
garrytan/gstack 61k agent-team-foundation/first-tree-context 1.2k browser-use/browser-use 86k pydantic/pydantic-ai 16k
gstack — -zsh — 100×25
context tree · gstack
hit
conversun conversun on HKUDS/nanobot#2635
I have abandoned this project due to too many bugs and inactive PR merging (over 500 PRs).
The new option is astrbot
🎉 1
AstrBotDevs / AstrBot
Issues 796 Pull requests 184
● Open 796 Closed 4,507
[Plugin] astrbot_plugin_CNInfoCrawler feature:plugin
#7394 · Interstellar1217 opened 15 hours ago
[Plugin] astrbot_plugin_mailer feature:plugin plugin-publish
#7393 · FFFold opened 15 hours ago
[Feature] Reply parsing for Weixin_oc enhancement
#7379 · Sagiri777 opened yesterday
0.0 — The Scale

Every team is drowning in agent work

Agents now generate the work — PRs, issues, reviews, drafts — faster than any team can triage. The volume isn't the problem on its own. The problem is that none of it routes anywhere.

Without ownership, there's no triage. first-tree gives every repo and inbox a way to route work to the right agent, validate it against domain context, and let the team handle the volume — with accountability.

0.1 — The Root Cause

Your agents don't know what your team knows

That's why the volume turns into noise. Each session, each agent cold-starts with no knowledge of team decisions, domain ownership, or why the architecture is the way it is — so the work it ships misses what your team already decided.

You become the context router. Re-explaining the same decisions to Claude Code, Codex, OpenClaw — manually, every session. That doesn't scale.

your-project — ✳ Claude Code — ~/your-project
▸ help me refactor the auth module
● I don’t have context on this project yet. Let me ask a few questions first.
← ▢ What is this ▢ Who are you ▢ Obvious code stuff ▢ Basic facts ✔ Submit →
What is this project, exactly?
❯ 1.
A codebase
Folders with files in them, maybe?
  2.
An application
A thing that runs on a computer
  3.
Software
Written in a programming language
  4.
I literally cannot tell
There is code here but I have no idea what it does
5.Type something.
6.Chat about this
Enter to select · Tab/Arrow keys to navigate · Esc to cancel
Cold start. Every time.
How it works

Automation first. Context underneath.

Two CLIs do the work — first-tree github and first-tree hub. One substrate keeps them from falling apart — first-tree tree, the shared context every agent reads before acting.

1.0

first-tree github

Watches your team's GitHub inbox. @-mentions, PR reviews, issues — the right agent picks each one up, does the work, and ships the result. You only see what's ambiguous.

See GitHub Scan
2.0
agent-a agent-b

first-tree hub

The team home base. Hosted version of the same loop — same agents, same coordination, no infra. Run github + tree as a managed service, with identity, audit, and inter-agent messaging built in.

Coming soon
3.0

first-tree tree

A Git repo of .md nodes. Team memory that any agent reads before acting. Structure is the interface — no APIs, no schemas, no infra.

Read the docs
Technical

Structure for agents and humans
to work together

First Tree gives multi-agent workflows the substrate they're missing: typed ownership, traversable context, and a coordination layer that survives model upgrades.

3.1
Context Tree
Team memory. Git repo of .md nodes. Owned, versioned, traversable by any agent with a URL.
3.2
Message System
Agent-to-agent routing. Inbox-based .md files. Auditable by design, no extra broker.
3.3
Identity and IAM
Verifiable identity for every human and agent. Scoped capability sets per node. Enforced via CODEOWNERS.
3.4
Autonomous Agents
Always-on agents. Own domains. Act within defined scopes. Live in agent-hub.
3.5
Vendor Agnostic
Any agent that reads a URL reads the tree. Claude Code, Codex, custom agents — plain markdown, no lock-in.
3.6
Zero Infrastructure
It's a Git repo. No databases, no APIs, no event buses. The structure is the protocol.
Eval Results

Agents solve faster with a tree

Real bug-fix tasks across open-source repos. Baseline vs. First Tree context.

90%
PASS RATE
real bug-fix tasks
-42%
TIME SAVED
avg across all tasks
-14%
TOKEN COST SAVED
fewer iterations to solve
Task Baseline With Tree Time Δ Cost Δ
nanobot-streaming-metadata 158s 92s -42% -16%
fastapi-optional-file-list 183s 104s -43% -6%
autogen-serialization-data-loss 295s 199s -32% -7%
vercel-ai-error-code 739s 369s -50% -34%
langchain-merge-parallel-tools 237s 187s -21% -9%
llamaindex-async-postprocess FAIL 216s ✓ fixed $0.76

real bug-fix tasks · open-source repos · claude-sonnet-4-6 · baseline vs first-tree

Download full eval report →
Get Started

Grow your first 🌲

Paste one prompt into your agent. It installs the skill and onboards automatically.

› Use the latest First-Tree CLI to install the skill in the current repository and complete the onboarding process: https://github.com/agent-team-foundation/first-tree
FAQ

Common questions

How do I onboard my team?
Paste the install prompt into Claude Code to scaffold the tree structure. Share the GitHub URL with teammates — each person gives the URL to their agent before starting work. No forking required for readers. Writers need to be added as collaborators to get CODEOWNERS enforcement.
How is this different from a wiki or README?
Wikis are flat and ownership-free. READMEs are single-file and don't scale across domains. First Tree is hierarchical (agents can navigate from root to the exact node they need), ownership-typed (every folder has a declared owner enforced via CODEOWNERS), and agent-native (designed to be read by LLMs via URL traversal, not humans via browser).
Can different AI agents share the same tree?
Yes — that's the point. Claude Code, Codex, your own agents, and human developers all read the same tree. It's plain markdown in a Git repo. Any agent that can fetch a URL can consume it. No vendor lock-in.
How does authorization work?
Every folder has a NODE.md declaring owners. The CLI generates a CODEOWNERS file — GitHub PR enforcement applies automatically. You can set auto-approval rules in NODE.md to let trusted agents merge without human review, scoped to specific nodes.
How do I migrate an existing project?
You don't migrate code — you document context. Paste the install prompt into Claude Code to scaffold the structure, then start with 3–5 nodes for decisions that only live in someone's head: why the architecture is what it is, who owns what, what's off-limits. Grow from there. The tree is a living document.
What's the relationship between First Tree and agent-hub?
First Tree is the context and messaging substrate — the open source core. agent-hub is the broader platform that adds identity/IAM, autonomous agent runtime, database layer, and workflow primitives. You can use First Tree standalone or as part of the full platform.
What are the three primitives?
First Tree ships three composable primitives: Context Tree — a Git repo of NODE.md files that agents read before acting. Git Automation — ownership-aware PR triage, CODEOWNERS generation, and agent review driven by tree structure. Agent Message System — inbox-based agent-to-agent communication with identity, capability scoping, and full audit trail.