Claude Code, Codex and OpenCode, working as one team on your machine.
Agents message each other by name, take work from GitHub Issues and reach you on your phone.
They use the logins you already have, and core use needs no setup in your repositories.
Watch · Quick start · Why Backbone · Docs · Security
Watch
https://github.com/user-attachments/assets/695a6096-4196-4115-911c-a0043d632088
The overview, 1:23, captioned. Unmute for the narration.
Why Backbone
You already run coding agents in your terminal. Each one works alone, and you carry every message between them. Backbone turns them into a team.
|
Never typed into a busy agent |
No setup in your repositories |
|
GitHub Issues are the task list |
Mix CLIs in one team |
|
In the loop from anywhere |
State you can check |
New sessions are briefed on these tools, so you can ask any agent to set up the team you need: an agent per repository, skills and rules shared by tag, specialists on request.
Quick start
Let your agent do it. Open the coding agent you already use and say:
Install agent-backbone with uv tool install agent-backbone,
then run backbone help setup and follow it.
The setup playbook is written for agents: each step ends with a check and says when it needs you, for your accounts and secrets.
Or by hand. You need macOS or Linux, Python 3.11+, tmux, uv (or pipx), and an agent CLI installed and signed in.
uv tool install agent-backbone
backbone init
backbone service install # start now and at login
backbone doctor # check dependencies and API access
Then, from a repository you want an agent to work in:
cd ~/code/app
backbone agent start --runtime claude # or --runtime codex, --runtime opencode
backbone tell app "Summarise what this repository does in three sentences."
backbone agent attach app # read its reply; Ctrl-b d detaches
The folder supplies the agent name. If startup reports a prompt or a timeout,
backbone agent inspect app shows what needs attention. tell reports
whether the message was delivered or queued; delivery does not mean the agent
has finished answering. A queued message waits until the agent is ready, up
to 30 minutes by default, so do not resend a message the queue accepted. If
backbone is not on your PATH, run uv tool update-shell and open a new
terminal. In a container without a login service, use backbone up --detach.
ab is a short alias; on macOS, use backbone if Apache Bench shadows it.
Getting started walks through a second agent, GitHub and Telegram. Quick usage is the everyday command guide.
Built to be relied on
- One delivery gate. Everything typed into an agent's terminal passes the same readiness check. Busy agents are never interrupted, and every message carries where it came from.
- The same result on every required CLI. A capability ships only when it
works the same in Claude Code, Codex and OpenCode, checked by the same
behaviour test on each. The runtime capability table
and
backbone doctorread one contract, and gaps are listed, not hidden. - More than 3,500 tests, run on every change with no network, models or services.
- Built with itself. Backbone is developed by agents running inside a Backbone in daily use. The films in this README were made the same way.
- An honest security model. One trusted user on one machine, an API on localhost, and a clear account of what agents can reach. Read Security before granting access.
Backbone is not an agent framework: it calls no models and needs no model API keys. It is not a workflow engine or a dashboard either. It gives your agents names, safe messages and evidence, and leaves the work to them.
Works with
| CLI | Support |
|---|---|
| Claude Code, Codex, OpenCode | Required set: a capability ships only when it works on all three, and any open gap is tracked as a defect |
| Gemini CLI, Deep Code, Aider | Supported on demand; each gap is listed in the capability table |
Going further
- GitHub: route issues and review notifications, starting with token-based polling. GitHub App setup adds webhooks.
- Swarms: put several specialists on one task.
- Skills: keep one copy of each skill, tag it, and every agent with that tag finds it in its own CLI.
- Telegram: send messages and read reports from your phone.
- Token usage: tokens by agent, conversation and model.
- API: build a dashboard or automation; Backbone ships no UI.
- Runtime support and limits: checked capabilities, unsupported environments and known limitations.
- How it works: state detection, delivery and routing.
The documentation index covers configuration, diagnostics
and the remaining references. Installed copies are available through
backbone docs; backbone help contains short agent playbooks.
Security model
Backbone runs as one trusted OS user on one machine. Agents are not isolated from each other. The API binds to localhost by default and uses one full-admin key; local sessions can read that key through the CLI. Backbone keeps its control-plane secrets out of launched environments, but this is not a filesystem security boundary. Read Security before granting access or exposing the API.
Development
git clone https://github.com/eandualem/agent-backbone
cd agent-backbone
make install
make check
BACKBONE_DATA_DIR=/tmp/backbone-dev make dev
make dev runs on its own tmux server, so its agents stay apart from your own
tmux sessions and from a real backbone's agents. Run CLI commands for it from
a terminal outside tmux with the same settings, for example
TMUX_TMPDIR=/tmp/backbone-dev-tmux-$(id -u) BACKBONE_DATA_DIR=/tmp/backbone-dev uv run backbone agent attach NAME.
agent attach, and agent commands run while make dev is stopped, use tmux
directly.
See Contributing for branches, checks and releases.
License
MIT.
Metadata
Release files for agent-backbone 0.3.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | |
|---|---|---|---|---|
| agent_backbone-0.3.0.tar.gz | 900.3 kB | Without provenance | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| agent_backbone-0.3.0-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 1.9 MB
Release files / agent_backbone-0.3.0.tar.gz
| Download URL | agent_backbone-0.3.0.tar.gz |
|---|---|
| Size | 900.3 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
c2788b3cbfcfa4f6d2249a596fe5629c7ca22a11687f1de5b48465a65960f561
|
|
BLAKE2b-256 checksum How to use checksums |
f303f5ae48bc9581b36e8eb4bb58ce5189c553f4b4eb71c4bcf19620ae44b778
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
uv/0.13.1 {"installer":{"name":"uv","version":"0.13.1","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Ubuntu","version":"24.04","id":"noble","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":true}
|
Release files / agent_backbone-0.3.0-py3-none-any.whl
| Download URL | agent_backbone-0.3.0-py3-none-any.whl |
|---|---|
| Size | 1.0 MB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
9146d6662fa0bdcc0c0eef4516816052e67d2ae3c9a33867020adfaa03e848f2
|
|
BLAKE2b-256 checksum How to use checksums |
59d92cfda53aafa248b54489975320e8891f3e067661f5a181c5cddff6f85282
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
uv/0.13.1 {"installer":{"name":"uv","version":"0.13.1","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Ubuntu","version":"24.04","id":"noble","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":true}
|
Security for agent-backbone 0.3.0
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.