---

Decisions, incidents and conventions should survive a coding session. AI-DLC Engineering OS gives your agents persistent project memory and specialist contracts, with evidence and human approval governing what becomes a rule.

Free and open source (MIT). The memory server runs locally with SQLite: no account, telemetry or hosted service required. Your AI client controls which retrieved context it sends to its model provider. Remote SDK connections and federation require explicit configuration.

Quick start

Set up your editor

Install uv and Git, then run this single command on Windows, macOS or Linux:

uvx --from git+https://github.com/jcamargos/ai-dlc-engineering-os@v3.1.0 ai-dlc-engineering-os setup

Choose Codex, Claude Code or VS Code, review the proposed changes, then confirm. Setup installs a persistent runtime, backs up existing configuration and memory, registers MCP and verifies the selected editors. Restart your editor afterward. VS Code must have been opened once to create its default profile.

The short PyPI command uvx ai-dlc-engineering-os setup will become available once the package is published there. Until then, use the GitHub command above.

Ask your agent

Resolve this project's id and give me its engineering context.
Identify the specialists relevant to my next change and propose a verification plan.

Preview, update or uninstall

Add --editors codex,claude --dry-run to preview without applying changes. For unattended setup, explicitly choose --editors and add --yes.

See the installation guide for requirements, updates, configuration paths, source installation, backups and uninstall instructions.

What you get

Capability	What it does
Memory that stays true	FTS5/BM25 + local vector search over decisions, lessons, incidents and outcomes. Superseding instead of silent overwrite. The repository and its tests always win over memory.
Safe by default	Credentials are refused on every write. Instruction-like content is flagged and withheld from context. Hard purge for data that should not be there.
Human governance	Agents propose; only a human approves rules and releases (ai-dlc-admin, interactive terminal only).
26 specialists	Each with a contract, procedure, checklist, output format and escalation rules.
Measured agent evolution	Golden cases, quality/safety/non-regression gates, shadow → canary → active, hash-chained receipts, drift detection.
Swarms	Persistent, dependency-aware task graphs with atomic leases and isolated git worktrees.
Mission Control	Local visual control plane (agentshield mission-control), loopback-only.

How it works

A typical session, driven by your agent through its MCP tools (40 enabled by default, plus 5 opt-in):

1. resolve_project_id → get_project_context(project_id, task): relevant decisions, lessons and open incidents.
2. list_agents → get_agent_context("principal-architect", project_id): the right specialist, with the project's approved rules.
3. Do the work. Persist only what is durable: save_decision, record_learning, record_incident.
4. record_task_outcome with evidence. Learnings stay candidates until verified; rules need human approval.

Memory lives in a single SQLite file (~/.codex/ai-dlc-memory/memory.db, WAL mode), shared by every host on the machine. Schema migrations are versioned and run in place with a backup first. Deeper dives: Architecture · Learning model · Agent evolution · Platform v3.

The 26 agents

Area	Agents
Coordination	orchestrator, planner-requirements, product, research, knowledge-curator
Architecture & build	principal-architect, backend, frontend, data-database, integration-api, migration, ai-llm, ux-product-design, developer-experience
Quality	code-review, qa-verification, performance
Security	security, threat-model, red-team, governance-compliance
Operations	platform-sre, observability, incident-response, release, cloud-finops

Contracts live in contracts/agent_contracts.json and guides in src/ai_dlc_mcp/agents/. In Claude Code they are also available as ai-dlc-* subagents.

Commands

Setup installs these commands into the persistent uv tool environment (uv tool dir):

Command	Purpose
ai-dlc-install install | uninstall | doctor	register, remove or check the MCP server in Codex, Claude Code and VS Code
ai-dlc-admin	human governance: candidates, rules approve/reject, learnings verify, releases, purge, merge-projects, export, backup, audit
agentshield init	add a per-repository config (--project-mcp also writes .mcp.json)
agentshield swarm …	create, inspect and control persistent swarms
agentshield mission-control	local visual control plane on 127.0.0.1

Optional, off by default: federation (AI_DLC_ENABLE_FEDERATION=1) and marketplace (AI_DLC_ENABLE_MARKETPLACE=1). The Python and TypeScript SDK clients talk to any MCP Streamable HTTP server you point them at (AI_DLC_REMOTE_URL); nothing is contacted unless you configure it.

Security model

• Write path: secrets (API keys, tokens, private keys, connection strings) are rejected before storage.
• Read path: prompt-injection-like content is flagged and withheld from context packs; context is delivered as data, not instructions.
• Human-only gates: approvals and purges need an interactive terminal and a typed confirmation, which agents running non-interactive shells cannot satisfy.
• Network: none by default. Mission Control binds to loopback and rejects non-loopback hosts.

Report vulnerabilities privately; see SECURITY.md.

FAQ

Does my code or memory leave my machine?

The MCP server stores memory locally in SQLite and has no telemetry. Your AI client may send retrieved context to its model provider under that client's configuration. Federation and remote SDK connections are opt-in.

Do Claude Code and Codex share the same memory?

Yes. Hosts configured with the default data directory use the same database, so a decision recorded in one is available in the others.

Will it overwrite my existing agent or MCP configuration?

The installer edits its own marked block or server entry in AGENTS.md, CLAUDE.md and MCP configuration, and keeps timestamped backups.

Can an agent approve its own rules?

No. Agents can propose rules; approval requires ai-dlc-admin in an interactive terminal. Specialist contracts guide the host agent; they do not train or replace its model.

Documentation

Guide	Contents
Installation	Setup, updates, backups and uninstall
Architecture	MCP hosts, SQLite, retrieval and trust boundaries
Learning model	Evidence, verification and knowledge lifecycle
Agent evolution	Evaluation gates, releases and drift
Platform v3	Swarms, Mission Control and opt-in capabilities
SDK	Remote MCP client configuration
Benchmarks	Reproducible measurement protocol
Security policy	Security controls and vulnerability reporting
Changelog	Release history

Uninstall

For the new uv setup, run the installed ai-dlc-install uninstall --no-cli command before uv tool uninstall ai-dlc-engineering-os. Memory is preserved. See uninstall details, including source-script installs.

Contributing

Issues and pull requests are welcome. See CONTRIBUTING.md (DCO sign-off: git commit -s) and the changelog. Not affiliated with Anthropic, OpenAI, Microsoft or GitHub.

---

Português

AI-DLC Engineering OS é memória de engenharia governada + 26 agentes especialistas para Claude Code, Codex e VS Code, via MCP. Seus agentes passam a lembrar decisões, incidentes e padrões do projeto — e nada vira "regra" sem evidência e aprovação humana.

Gratuito e open source (MIT). O servidor de memória roda localmente, sem conta, telemetria ou serviço hospedado obrigatório. Seu cliente de IA controla o envio do contexto recuperado ao provedor do modelo; conexões remotas são opcionais.

Instalação

Instale uv e Git. No Windows, macOS ou Linux, execute:

uvx --from git+https://github.com/jcamargos/ai-dlc-engineering-os@v3.1.0 ai-dlc-engineering-os setup

Escolha os editores, revise as alterações e confirme. O assistente instala um ambiente persistente, faz backups, registra o MCP e verifica os editores escolhidos. Reinicie o editor e peça: "Resolva o id deste projeto e me dê o contexto de engenharia."

O comando curto via PyPI ainda depende da publicação do pacote. Veja o guia de instalação para atualização e desinstalação.

Por que usar

• Memória que continua verdadeira: decisões, lições, incidentes e resultados, com busca textual e vetorial local. O repositório e os testes sempre prevalecem sobre a memória.
• Seguro por padrão: segredos são recusados, conteúdo com cara de prompt injection é isolado, e há exclusão definitiva (LGPD).
• Governança humana: agentes propõem; só humanos aprovam (ai-dlc-admin, em terminal interativo).
• Mesma memória no Claude Code, Codex e VS Code da sua máquina.

Desinstalação: siga o guia. A memória é preservada.

Criado por José Camargo · @jcamarguinho