Declarative AI Agents: Spec Once, Generate Everywhere with ACEL

A developer introduced ACEL (Agent Capability Expression Language), a declarative language for defining AI agents, built on the Rectified Pentachoron Framework (RPF). The language models agents as five aspects plus an autonomy modal, and includes a generator tool, acel-generator, that produces artifacts like AGENT.md and MCP configuration. The projects are MIT-licensed and aim to make agents governable, auditable, and portable.

Most agent frameworks still force you to write imperative code: wire tools, manage memory, hard-code oversight logic, and re-implement the same patterns for every new runtime. The result is brittle agents that are hard to review, version, audit, or port. A cleaner path is emerging: treat the agent as a declarative contract . ACEL Agent Capability Expression Language is a small, focused language for defining AI agents. It is built on the Rectified Pentachoron Framework RPF and models an agent as exactly five aspects plus a global autonomy modal: | Aspect | Role | Neglect pathology | |---|---|---| telos | The objective pursued | Aimless reactivity | world model | Present apprehension of environment state | Ungrounded action hallucination | memory | State retained across time | Amnesia | deliberation | Mapping situation → action | Thrashing / myopia | actuation | Effecting change on the environment | Paralysis | Autonomy is not a sixth aspect. It is a modal that qualifies every aspect supervised perception, supervised deliberation, etc. . Oversight rules sit alongside it as first-class triggers uncertainty thresholds, irreversible actions, cost limits, etc. . A minimal example looks like this: agent research assistant { autonomy: SUPERVISED telos { goal: ACHIEVE "comprehensive report" AND MAINTAIN "factual accuracy" priority: HIGH } world model { grounding: REQUIRED percept web search { type: RETRIEVE protocol: MCP freshness: 1h } } memory { type: HYBRID store short term { capacity: 10000 ttl: 1h retrieval: RECENCY } store long term { capacity: 1000000 retrieval: RELEVANCE } } deliberation { mode: HYBRID plan { strategy: HIERARCHICAL depth: 4 replan on failure: true } decide { strategy: MONTE CARLO TREE SEARCH risk: 0.4 explore: 0.2 } reflect { trigger: ON ERROR over: long term } } actuation { effect document store { type: MODIFY protocol: REST permissions: READ, WRITE } } oversight high stakes { trigger: UNCERTAINTY ABOVE 0.3 action: ASK APPROVAL escalate to: lead } } The language enforces clean separations percepts are read-only; effects are write; reflection must bind to a declared memory store and produces a conformance report against the five-aspect basis. The .acel file becomes the single source of truth — versionable, reviewable, and enforceable in CI. Writing the contract is only half the story. acel-generator OpenAPI-Generator-style tooling for ACEL turns that contract into concrete artifacts. Pipeline: .acel → parse + validate + RPF conformance → IR → generators → artifacts Current built-in generators include: AGENT.md + Mermaid architecture diagram .well-known/agent-card.json for discovery and delegation mcp.json with percepts as read tools and effects as write tools plus destructiveHint annotations Governance details that current interoperability protocols do not express autonomy level, oversight, grounding, retention shape are emitted under namespaced extensions so the gap stays visible rather than being papered over. Design principles of the generator: ACEL is deliberately not a runtime. It is the contract that binds the layers you already run agent loop, control plane, gateway, tools/MCP, memory . Author-time validation shifts left; runtime enforcement compiles autonomy and oversight into gateway rules. Both are MIT-licensed with a narrow patent non-assertion on the language itself . The projects are early alpha , but the conceptual clarity is already strong. If you are tired of re-implementing the same agent skeleton for every framework, try writing the contract once and generating the rest. Declarative agents are not just cleaner code — they are a practical step toward agents that are governable, auditable, and portable by design.