suneel944/agent-parley

worktree, and records who owns what: every claim, handoff, wake and refusal.
https://github.com/user-attachments/assets/1de399fc-4078-49da-a4f9-116789bccb7d
Try it without an account: agent-parley demo runs the story this
video is cut from, with stub lanes in a throwaway sandbox and no native CLI,
model or network.
See it ·
Install ·
Run ·
Coordination ·
Monitoring ·
Providers ·
Commands ·
Limits
---
- **Lanes keep moving without you.** Idle lanes are woken, planned issues are
dispatched, and a claim whose holder went silent moves to the fittest peer
with its recovery checkpoint.
- **Plans change inside bounds you set.** A lane proposes a change with
plan propose; it applies on its own only inside the plan's [revisions]
envelope, and otherwise waits for plan approve.
- **An optional run budget.** budget enforce caps the tokens, calls or hours
every lane spends together; once reached, nothing new starts until
budget resume.
- **Pull requests wake their lane.** Finished checks, a new review or a merge
conflict reach the owning lane as mail.
- **Unattended integration only by policy.** unattended set names the issues
and the target branch; unattended run, or the service itself when the
policy adds --auto, merges on the same gate as
participant merge, and a failed integration holds every other merge until
it is verified.
- **Churn is caught per issue.** An issue whose verification keeps failing is
flagged in issue show, problems and a notification.
- **Ownership stays explicit.** Atomic claims, accepted handoffs, advisory
reservations that name the blocking owner, and native hooks that refuse a
branch switch before it runs.
- **Readable by people and scripts.** status, top and problems show what
needs you; the readers take --json, and a failure prints one error
document.
See it
Every terminal frame in the launch video at the top is captured command output
from the shipped coordination path; only the native client is a stand-in, so
no model runs. It is re-cut with
docs/video.
make demo-stub records the full nine-chapter walkthrough with
scripts/record_demo.py;
make demo records real claude and codex sessions with
scripts/record_live.py.
agent-parley top reads like Linux top: three summary lines, one row per
lane with its state, issues, mail, leases, denials, idle time and last prompt,
and one note per problem under the table. Read-only, no model call, q quits.
A lane reads working while its session is alive and current, idle once its
activity passes the inactivity threshold, and stopped only when its session
process is gone: a quiet lane is not a lost one. Stopped lanes that hold
nothing are counted in the summary; top --all draws them. top --serve
serves the same view read-only to a browser tab and a Prometheus scraper on
127.0.0.1.
Monitoring
covers the columns, keys, filters, problems, metrics, the web view,
watch and report usage, which lists what each resolved issue used.
Install
You need Git. No clone. The wheel needs no third-party runtime packages. One
command installs everything on Linux, macOS and WSL2:
It installs uv only when uv is missing, then
installs or upgrades agent-parley, adds the plugin to each of claude and
codex found on PATH with agent-parley plugins install, and runs
agent-parley doctor. It never uses sudo, and re-running it upgrades in place.
It ends with the next command for the first of claude, codex, copilot,
gemini, opencode and amp on PATH, such as
Next: cd your-repo && agent-parley run gemini; only claude and codex
take a plugin. With none of them on PATH it says to install one first and
offers agent-parley demo.
To install by hand instead:
**macOS**
**Linux, or Windows through WSL2**
Native Windows is not supported. On WSL2, keep the repository in the Linux
file system, not under /mnt/c.
To track the default branch instead of the latest release, run
uv tool install git+https://github.com/suneel944/agent-parley.
Then add the plugin to whichever of claude and codex you drive:
agent-parley plugins install does it for each one on PATH, or run the
commands yourself. One marketplace serves both. gemini, copilot,
opencode and amp lanes take no plugin; the launcher configures them per
session.
The plugin carries only the coordinate skill, which teaches an agent to read
state, claim issues and hand work off. The launcher does the rest: worktrees,
the coordination service, and per-session MCP configuration and hooks. The
plugin without the launcher has nothing to coordinate through.
For a pinned, checksummed install, take a wheel from