The flow, at a glance
Conflicting agents in → one guardian layer → clean, audited context out
aienvmap gives every AI coding agent sharing a machine the same environment map and light SBOM. What runtime and package manager is live, what changed, what's still pending — no more agents each guessing their own answer.
$ npx aienvmap start
$ npx aienvmap reconcile
or try npx aienvmap demo — see the multi-agent conflict flow without touching your workspace
Conflicting agents in → one guardian layer → clean, audited context out
Illustrative — aienvmap reconcile reports the Python/Node/Java/Go versions actually visible on the machine, side by side
Three commands make up the loop
$ npx aienvmap start
Boot in one command
Creates the env map, light SBOM, status, and dashboard when missing or stale — plus a copy-paste prompt any agent can pick up immediately.
$ aienvmap context --json
Agents ask first
Any agent reads the same AI decision contract — env state, next command, coordinationRevision — before touching anything. Facts, not guesses.
$ aienvmap intent / checkpoint
Intent, then checkpoint
What an agent plans to change is logged first (intent). checkpoint records the outcome, re-syncs the env map, and hands off to the next agent.
What an agent plans to change (intent) and how it's resolved (resolve, checkpoint) are
appended to .aienvmap/intents.jsonl and timeline.jsonl.
Non-blocking by default — it records, it doesn't stop you.
aienvmap doctor checks the same drift for vulnerable dependencies, policy
rules, and conflicting agent intents. Warn-only locally; add
--strict security|policy|coordination|all to fail CI or a release gate on it.
# AIENV.md (illustrative)
runtime node@22.4.0, python@3.12
package_manager pnpm@9
# timeline.jsonl
intent codex → upgrade test runner
intent claude → replace package manager
resolve human → keep pnpm, drop upgrade
.aienvmap/dashboard.html shows the current environment state and the
agents' recent intent/checkpoint history, right in the browser.
aienvmap reconcile is read-only