Scaleups of 50–500 engineers
When 7 products start cracking at the seams and context falls apart. One loop — pulls the SDLC back together into a system.
Not an "AI feature" bolted onto your existing stack and not a portal-of-portals — a connected system where catalog, specs, reviews, builds, releases, incidents, and metrics live in one context. The team and AI agents share rules, practices, and knowledge. Not across 7 repos and Notion — in a single product.
Community OSS · Enterprise self-hosted · Cloud managed on h3llo
When AI agents show up on every SDLC stage, time-to-market drops several fold and quality climbs. But only if humans and agents share the same context, rules, and practices. Not across 7 repos and Notion pages — in a single product.
Each stage's artifact automatically becomes the next stage's input: issue → spec → ADR → PR → image digest → release → SLO → incident → action item → next issue.
Ideas from chats, tickets, and calls are aggregated into a single backlog with semantic embeddings. RFCs are machine-readable.
Spec-driven: spec before code. Epic → story decomposition by an analyst agent. AC in Gherkin or structured YAML.
Architecture-as-code. ADR is mandatory. C4 from text + code analysis. SLOs are defined here, not after prod.
Trunk-based. Golden paths: a new microservice in 30 seconds. Agent runs in firecracker/gVisor with MCP access.
AI reviewer as the first line: style, security smells, missing tests. Human review — for intent and architecture.
Contract tests are mandatory. Self-healing flaky tests. Ephemeral envs per PR. Mutation testing on critical paths.
Hermetic builds, distroless/Wolfi bases, SLSA L3+, Cosign-signed images, SBOM per artifact.
GitOps everywhere. Progressive delivery with auto-analysis against SLO. DB migrations expand/contract. Auto-rollback.
OTel is the only standard. SLO-based alerting. AI agent summarizes alerts (logs + traces + recent deploys).
Blameless postmortems. An incident commander agent spins up a war room, ChatOps commands → actions, action items land in the tracker.
DORA from git/CI/incidents. DevEx surveys. AI clusters feedback into roadmap themes. Every action item has a trace.
No separate AGENTS.md in one place, RFCs in another, runbooks in a third. Service context and rules live in .l1ve/ right next to the code, readable by humans and agents alike.
# .l1ve/context.md — shared context for humans and agents service: payments-api team: billing tier: prod on-call: @alice (primary), @ivan (backup) rules: - PR > 400 LOC requires a split (the splitter agent will suggest one) - migrations via Atlas, separate from deploy (expand/contract) - protected paths: infra/prod/, billing/secrets/ agents: - codegen: sandboxed · MCP[git, fs, lsp, run-tests, docs] - reviewer: read-only · MCP[git, semgrep, sast] - rca: on incident · MCP[loki, prom, tempo, runbooks] slo: - availability: 99.95%/30d → burn alert >2%/h - p99-latency: 250ms → page if >500ms 5min
# .l1ve/agent.yaml — agent-as-catalog-entry
apiVersion: l1vestack.dev/v1
kind: Agent
metadata:
name: codegen-payments
spec:
base: openhands # or aider, cline
model:
provider: h3llo-ai # or anthropic, openai, ollama
model: llama-3.1-70b
context:
rag: # corp knowledge layer
- service:payments-api
- adr:billing/*
- runbook:billing/*
spec_path: docs/specs/
sandbox:
runtime: firecracker
network:
egress: [github.com, registry.h3llo.cloud]
mcp:
- git # scoped: read-only
- filesystem # scoped: ./
- test-runner
- docs-search # ./docs/**
budget:
monthly_tokens: 10_000_000
monthly_rub: 30_000When 7 products start cracking at the seams and context falls apart. One loop — pulls the SDLC back together into a system.
Banks, public sector, healthcare. Tamper-evident audit log, air-gapped install, ready-to-use FZ-152/FSTEC/PCI policy bundles.
If AI agents are first-class citizens in your process. Sandboxed runtime, RAG, MCP gateway, evals — non-negotiable.
Internal teams as customers. Self-service over tickets, golden paths, measurable DevEx and DORA out of the box.
No crippleware. Community — a full SDLC for teams up to 20 people. Enterprise — when you need multi-tenancy and compliance. Cloud — network effects and premium agents that can't be reproduced locally.
Real practices from the h3llo platform team: how we write specs for agents, how AGENTS.md is structured, what we measure once the SDLC is closed.
RFC and PRD templates, YAML frontmatter, machine-readable AC, contract tests as the outcome of a spec. PDF · ~40 min.
→Checklist · PDFDomain rules, MCP servers, what NOT to touch, dev commands, test fixtures. With real examples. 12 pp · ~15 min.
→Case · h3lloFull breakdown of the architectural shift. Which 3 backend plugins we kept, what we rewrote, before/after numbers. case · ~30 min.
→Guide · 32 ppIsolation, network egress policies, scoped tokens, audit log, evals. How we run agents in production. PDF · ~30 min.
→Benchmark · 2025Lead time, deploy frequency, MTTR, change failure rate. What changes when the SDLC closes. report · ~25 min.
→Templates · GitHubReady chart: catalog, scaffolder, agents, MCP gateway, observability. Air-gapped overlay included. repo · 5 charts.
→Helm install → ingest git → wire in agents → artifacts are connected automatically. No portal-builder and no 800 lines of YAML.
`helm install l1vestack h3llo/l1vestack` · one command, up in 4 minutes.
`l1ve catalog ingest --from git@github.com/your/repos` · services show up automatically from `catalog-info.yaml`.
Drop `.l1ve/agent.yaml` into the repo · the agent registers itself in the catalog with its runtime and MCP access.
Spec → code → review → release → operate → feedback → next spec. Artifacts are linked automatically.
An army of AI agents on every stage · DORA through the roof · TTM through the floor. Not across 7 SaaS tools, but in a single product — bring your own model and your own perimeter.