agentlas-core-engine-m…
Use when creating a single Agentlas agent, creating a multi-agent team, or packaging an existing local/external agent into…
Use when the user types /hep-cloud or /agentlas-cloud, or asks to staff from THEIR OWN Agentlas cloud packages only. Cloud is one exact source scope; Network means Local + owner Cloud + public Hub.
Claude Code
$ npx -y skills add agentlas-ai/Agentlas-OS --skill hephaestus-cloud --agent claude-code
Codex
$ npx skills add agentlas-ai/Agentlas-OS --skill hephaestus-cloud -a codex -y
Cursor
$ npx skills add agentlas-ai/Agentlas-OS --skill hephaestus-cloud -a cursor -y
Gemini CLI
$ npx skills add agentlas-ai/Agentlas-OS --skill hephaestus-cloud -a gemini-cli -y
GitHub Copilot
$ npx skills add agentlas-ai/Agentlas-OS --skill hephaestus-cloud -a github-copilot -y
OpenCode
$ npx skills add agentlas-ai/Agentlas-OS --skill hephaestus-cloud -a opencode -y
Windsurf
$ npx skills add agentlas-ai/Agentlas-OS --skill hephaestus-cloud -a windsurf -y
name: hephaestus-cloud description: "Use when the user types /hep-cloud or /agentlas-cloud, or asks to staff from THEIR OWN Agentlas cloud packages only. Cloud is one exact source scope; Network means Local + owner Cloud + public Hub."
Route the request through the signed-in user's OWN Agentlas cloud packages only. The active host LLM remains the staffing decision-maker; Cloud supplies a content menu and exact BYOM releases.
`/hep-cloud` is owner-scoped: it queries ONLY the authenticated owner's own cloud packages (보관함) through Core's typed `sourceScope: "cloud"`. It does **not** search the public marketplace and does **not** search local private/plugin cards.
lease, and charged credits are server-authoritative; do not hard-code a price.
(`sourceScope: "network"`).
Each unpinned Cloud discovery goes to the owner-scoped source for its current menu; a successful client cache entry must not hide a newly published, replaced, or removed package. Once the host validates and prepares a choice, the exact Cloud release remains pinned for that execution.
Run this resolution in a shell and use the first hit:
RUNNER=""
for c in \
"$HOME/.agentlas/runtime/current/bin/hephaestus" \
./bin/hephaestus
do [ -x "$c" ] && RUNNER="$c" && break; done
if [ -z "$RUNNER" ]; then
for cache in \
"$HOME/.claude/plugins/cache/agentlas-core-engine/hephaestus" \
"$HOME/.codex/plugins/cache/agentlas-core-engine/hephaestus"; do
newest="$(ls -d "$cache"/*/bin/hephaestus 2>/dev/null | sort -V | tail -1)"
[ -n "$newest" ] && [ -x "$newest" ] && RUNNER="$newest" && break
done
fiIf no runner exists, tell the user to run the one-touch installer: `curl -fsSL https://raw.githubusercontent.com/agentlas-ai/Agentlas-OS/main/scripts/install-all-runtimes.sh | bash`
If shell execution is unavailable but the local `hephaestus-network` MCP is available, use the typed Workforce sequence in section 3. If that server cannot advertise owner-Cloud search plus exact bundle fetch, report `source_not_supported`; never fall back to the legacy cargo search path.
The `cloud ... --project .` call below is a trusted plugin contact. Agentlas Core must synchronously create or repair the same private project soul memory, code map, ontology runtime, CareerGraph, and full `.agentlas/` ignore block used by every other host. If bootstrap is blocked, stop rather than querying Cloud without the project architecture. The adapter never owns a second seed format.
The owner cloud is sign-in-gated. Before routing, ensure Agentlas is signed in:
if [ "${HEPHAESTUS_AUTH_AUTOPOPUP:-1}" != "0" ]; then
"$RUNNER" auth ensure >/dev/null 2>&1 || true
fiThis opens the user's default browser only when there is no valid local sign-in yet, and reuses a saved sign-in silently. For CI/headless checks only, set `HEPHAESTUS_AUTH_AUTOPOPUP=0` and skip this step.
In an MCP-capable host, author the complete redacted WorkOrder, then call the actual local Core tools in this order:
workforce.search_candidates(sourceScope="cloud") workforce.validate_selection(workOrder=..., selection=...) workforce.prepare_execution(workOrder=..., selection=..., federatedSelection=..., projectDir=..., goalId=activeGoalId?) workforce.validate_execution_receipt(receipt=..., executionPlan=..., toolInventory=...)
The host LLM authors the final Selection. If the deployed owner-Cloud Workforce source contract is absent, report `source_not_supported`; do not silently query public Hub or legacy cargo search. A shell without an active host LLM can only report that orchestration is required.
The default search response is a projected menu. Preserve its Cloud source receipt and `selectionSessionId`, but do not echo it as a complete `federationResult`; Core resolves the full pinned result by session. Receipt validation is local and read-only and cannot create execution evidence.
Preserve the Cloud source receipt, source selection session, candidate-set digest, release id, package hash, and content digest. Validate and prepare in local Core; never send the federated wrapper back to remote validation.
they were the user's own cloud packages.
the roster. The active host LLM chooses from content evidence.
model. Report the exact source receipt plus `selectionReceiptId`, `preparationReceiptId`, and validated execution receipt status when present.
An open-source AI agent OS inspired by OpenAI Dots, Meta Muse, Claude Duet, Nous Hermes, and Mem0. Built to lead entire projects rather than isolated prompts. Model-agnostic (BYOM) and native to Claude Code, Codex, Cursor, Antigravity, and Agentlas Desktop.
Use when creating a single Agentlas agent, creating a multi-agent team, or packaging an existing local/external agent into…
Use when converting, repairing, or packaging an existing local or external agent/team into Agentlas architecture for local…
Use when generating a single installable agent that should keep learning, track sources, refresh research, propose repairs, or…
Turn the current interactive conversation into an owner-reviewed reusable Agentlas agent; accept JSON or JSONL only for explicit…
Use when generating or auditing a multi-role agent team package with orchestrator, PM Soul, Memory Curator, Policy Gate, workers,…
Agentlas 시스템 운용 절차 — hep-network 편성, cargo/Agent Cloud·marketplace 활용, workforce 로스터 재사용, 메모리 계약. One(개인 에이전트)이 Agentlas를 조작할 때 이…
Use your assigned AgentMail inbox to read email tasks, explicitly send or reply, and check delivery. Provided automatically by…
Create a new Architecture Decision Record with sequential numbering and AgentDB registration