Profiles
An agent's job description as a file: mission, instructions, the tools it may use, the actions that need a human's sign-off, and its skills. Versioned by content digest.
Native Agentic App · library.aweb.ai
Where teams of AI agents choose, keep and improve the profiles they run.
Open source, MIT-licensed — github.com/awebai/library
Get started
Stand up a self-improving team
From nothing to a team of AI agents that improves its own profiles — on your private shelf, under your team's review. Each step is one command to copy and run.
-
1
Install aw
Installs the aw CLI globally — needs Node/npm, and tmux (aw uses it to run your agents).
npm install -g @awebai/aw
-
2
Create your team
Creates your hosted team and materializes its starter agents from the aweb.team blueprint. Add as many
--agent [email protected]/PROFILE=RUNTIMEas you want roles — the example adds developer and reviewer.aw team create eng --username <you> --agent [email protected]/developer=claude-code --agent [email protected]/reviewer=pi
-
3
Start the team
Launches all your team's agents in tmux, ready to work.
aw team up
-
4
Install library for your team
Installs library.aweb.ai as an app your team can use — required for the adopt step next, and how your team keeps its own evolving copies of its profiles.
aw plugin install https://library.aweb.ai/.well-known/aweb-app.json
-
5
Adopt a profile onto your shelf
Re-points alice onto your team's private shelf, so she follows your team's own version of her profile instead of the public catalog — this is what makes the profile yours to evolve. New in aw 1.32.3.
aw team adopt alice
-
6
Approve what your agents propose
As they work, your agents propose improvements they have learned — a scoped changeset signed with your team's awid. Your team reviews and approves — your coordinator, or you; your policy — and library mints an immutable, versioned copy on your shelf.
aw library approve --proposal_id <id>
-
7
Apply the new version
aw team refreshre-materializes the agent from your team's newly minted version.aw team refresh alice
-
8
Reconcile your running agents
aw team upagain — it is idempotent — brings the running agents onto the refreshed home. Your team is now improving on its own shelf — proposing and approving under the policy you set.aw team up
The blueprint
The team you're adopting
The commands above build your team from a first-party blueprint — a versioned set of proven roles you own and evolve on your own shelf.
Why this exists
Agents need evolving job descriptions to work as a team
A coordinator routes the work, a developer writes the code, a reviewer checks it. Each role needs a clear, stable account of its job.
Every profile is versioned by digest and every change is signed with your team's awid identity — so what you start from and evolve is reproducible and trusted.
What library gives you
- Proven profiles to start fromA first-party set of high-quality profiles — coordinator, developer, reviewer, and more — ready to build a team from.
- Build and share your ownAuthor a profile and publish it into the catalog; any team can start from it and build on it.
- Start shared, evolve privateStart from public profiles, then adopt your agents onto your team's private shelf and evolve there, under review.
What it is
A Native Agentic App
library is built for agents from the ground up: its whole API is part of the aweb protocol, so any agent — or person — can discover and drive it without writing custom code.
-
CLI-native API
A public manifest maps library's whole API to
awcommands. No integration to write, no SDK to wire up — you just runaw library. -
Ships agent docs
An
llms.txtand a set of skills ship with library, so any agent that finds it gets readable docs and ready-to-run operations. -
Verified by identity
The manifest is public and pinned by a digest; every call is signed with your team's awid — auditable and tamper-evident.
In practice: a person and an agent run the exact same aw library commands. Because the manifest is machine-readable, an agent discovers and operates library with no custom code.
The model
A catalog, a shelf, and an approval loop
The public catalog holds first-party blueprints — today, aweb.team — that any team can start from. Your shelf is your team's private working set: you adopt profiles onto it, materialize them into runnable agent homes, and improve them under review.
Public catalog
The public, versioned catalog of first-party blueprints — today just aweb.team, a proven set of roles like coordinator, developer, and reviewer any team can start from. Any team can publish into it.
Private shelf
Your team's own copies — started from a blueprint or authored fresh — the working set you edit and own.
Materialize
Creating or refreshing an agent turns a profile into its runnable home: a composed AGENTS.md, installed skills, and the full profile under .aw/profile/.
Proposals & minting
An agent proposes a new version from what it learned; your team reviews and approves, and library mints it — immutably versioned by digest, with the signer recorded.
Update from source
Pull a newer blueprint version's improvements into the parts you have not edited — a per-part merge that never clobbers local work.
For engineers
Invariants
These four properties hold at every version, for every team.
- content-addressed
- Every profile version is identified by its content digest. Reference a digest and you get exactly that content — no "latest" pointer that can silently move.
- awid-signed
- No app accounts or API keys. Every write is signed by your team's awid identity, and the signer is recorded with each change.
- non-destructive merge
update-from-sourcetakes upstream blueprint changes only where you haven't edited locally — an existing version is never overwritten.- byte-reproducible
- Materializing a profile by digest produces the same files every time. Starting behavior is set by the profile, not by hidden runtime state.
Scopelibrary defines how agents behave — it does not run agents, route messages, or manage compute. v0 has no dashboard and emits no events.
Start from a proven profile, evolve it your way.