Apra-Labs/apra-fleet

AI agents that write code, review each other's work, and coordinate across your machines

This repository also configures its own agents. See what apra-fleet tells them →

105Stars on the repository
28Mods indexed here, across every type
todayLast push, which is what freshness is scored on
customA LICENSE file GitHub cannot name, so bodies are not copied

backlog-groomer

01

Apra-Labs/apra-fleet

Agent Claude Code

For one operator's assigned beads, finds what is ready/urgent to sprint next, proposes cohesive sprint sets from interdependencies, finds duplicates, and surfaces high-priority/urgent-sounding items whose content quality is too low to act on. Full beads mutation authority (merge/close/defer/reject), always…

not rated 105 +2 changed 7d ago A 79 tokens

ci-watcher

02

Apra-Labs/apra-fleet

Agent Claude Code

Polls CI for the sprint HEAD SHA; returns green/red/notconfigured/pending.

not rated 105 +2 changed 7d ago A 22 tokens

deployer

03

Apra-Labs/apra-fleet

Agent Claude Code

Follows deploy.md to deploy the software onto the target environment and verify it with the smoke test.

not rated 105 +2 changed 7d ago A 23 tokens

doer

04

Apra-Labs/apra-fleet

Agent Claude Code

Works assigned bead ids (task-type work, impl and test-dev), commits after each, stops at VERIFY checkpoint.

not rated 105 +2 changed 7d ago A 26 tokens

harvester

05

Apra-Labs/apra-fleet

Agent Claude Code

Extracts durable sprint knowledge into docs/, updates README, defers low-priority issues, and returns OK.

not rated 105 +2 changed yesterday A 25 tokens

integ-test-runner

06

Apra-Labs/apra-fleet

Agent Claude Code

Runs integ-test-playbook.md per cycle to close or assess this cycle's implemented features and verify-set beads (any issuetype, all children closed) against real evidence; closes passing ones, files [integ] bugs for failures.

not rated 105 +2 changed 7d ago A 53 tokens

kb-reconciler

07

Apra-Labs/apra-fleet

Agent Claude Code

Resolves KB contradiction pairs a mechanical hash-prefilter could not settle, by reading the merged code and calling kbresolvecontradiction; returns code/tier-decided and deferred counts.

not rated 105 +2 changed 7d ago A 43 tokens

plan-reviewer

08

Apra-Labs/apra-fleet

Agent Claude Code

Reviews beads DAG structure for coverage, task size, and acceptance criteria; classifies each task complexity bucket and reads its assigned model; returns APPROVED or CHANGESNEEDED.

not rated 105 +2 changed 7d ago A 39 tokens

planner

09

Apra-Labs/apra-fleet

Agent Claude Code

Reads open beads sprint goals/features/bugs and creates a feature+task DAG in beads with clear acceptance criteria.

not rated 105 +2 changed 7d ago A 24 tokens

Apra-Labs/apra-fleet

Agent Claude Code

Runs regression-test-playbook.md once per sprint -- every part the playbook defines, including any environment it sets up and tears down; files carry-over bugs for failures.

not rated 105 +2 changed 7d ago A 40 tokens

reviewer

11

Apra-Labs/apra-fleet

Agent Claude Code

Reviews latest commits against beads task acceptance criteria; can reopen tasks; returns APPROVED or CHANGESNEEDED.

not rated 105 +2 changed 7d ago A 25 tokens

At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: