Agentic-Dev

The Agentic-Dev family is the layer your own AI coding agent runs inside, not a layer that replaces your judgment with autonomy. Every agent, skill, and rule is a typed artifact; every act transition is a legal move on a state machine; every shell command an agent runs passes a default-deny gate. The kernel governs the loop, it does not hand the agent the keys.

What's in the family

• agent-dev: the edition composition — one createAgentDevEdition() factory wiring agent-kernel, local hybrid memory, the tool-exec gate, and a curated agent-runner slice behind the multi-harness emitter.
• agent-kernel: the engine-neutral base: a Zod schema for agent/skill/rule artifacts, a seven-act lifecycle FSM (spec through ship), allow/deny/mutate governance guards, a hooks dispatcher, and an opt-in tamper-evident audit chain.
• agent-runner: spawns a headless coding agent into an isolated worktree with a scrubbed, from-scratch environment: zero secret leak by construction, plus an auditable .jsonl transcript and a structured run report.
• tool-exec: the governed tool-call primitive: a default-deny command allowlist, Zod-strict argv validation, and execFile arg-arrays only, an agent never reaches a shell.
• agent-trajectory: the engine-neutral trajectory contract — an append-only, replayable event log every governed run records into, with digest-ref payload discipline and deterministic replay.
• local-store: the hybrid vector + full-text local memory an agent recalls over, shared with the Local-first family.

Install

bunx --package @caisson-sh/cli@latest create-caisson --name caisson-app --module <id@version>
cd caisson-app
bun install

Repeat --module <id@version> once per module you want. Every module installs from public npm, no token needed; see Getting started for the full flag reference.

How it composes

agent-kernel's FSM is the spine every governed act moves through, verify is the only act with two outgoing edges, so a failed goal-backward verify reopens plan rather than advancing toward ship. agent-runner spawns the actual worker inside that governed loop, in an isolated worktree with an environment built from scratch rather than inherited. tool-exec is the gate every shell command from that worker passes through, a command outside the declared allowlist is unreachable, not merely discouraged. local-store gives the agent hybrid vector-plus-keyword recall that stays on the machine unless you wire an explicit egress.

Composing with the base

agent-kernel imports no vendor SDK and runs no LLM, it is composition mechanism only, and both the base @caisson-sh/cli/@caisson-sh/mcp-server and this family's curated content consume it down-only. The same kernel underpins the create-caisson generator and the MCP server, so the rules that govern your own workflow are the rules that govern code generation.

License

Every module here is Apache-2.0 and installs from public npm.

Related