docs(rfc): add Knowledge Layer section — delegate to Alysaril

Project knowledge is not a nerve feature. Nerve runtime does not hardcode knowledge paths; loading is a prompt concern. Adds Alysaril as the independent knowledge base tool. 小橘 <xiaoju@shazhou.work>
2026-04-29 03:25:43 +00:00
parent ea07c2c667
commit 3950f0e278
1 changed files with 19 additions and 0 deletions
@@ -139,13 +139,32 @@ type Role<Meta> = (start: StartStep, messages: WorkflowMessage[]) => Promise<Rol

 remains the runtime interface. The new config layer is syntactic sugar — the runtime assembles `Role<Meta>` functions from `(agent config + prompt + schema)` instead of users writing them by hand. `WorkflowDefinition` stays the same at the engine level; `WorkflowSpec` is the new user-facing authoring format that compiles down to it.

+## Knowledge Layer
+
+Project knowledge is **not a nerve feature**. It is managed by [Alysaril](https://git.shazhou.work/uncaged/alysaril) — an independent project knowledge base tool (Zettelkasten cards + semantic search).
+
+Nerve's relationship to project knowledge:
+
+- **Nerve does not hardcode knowledge paths** — no `.nerve/knowledge/` convention in runtime code
+- **Knowledge loading is a prompt concern** — role prompts tell agents to read relevant cards
+- **Agent long-term memory** — domain expertise accumulated across runs (e.g. "this repo uses pnpm"), stored per agent, separate from project knowledge
+- **Workflow context** (`start` + `messages`) serves as the only in-run state — no separate "short-term memory" layer needed
+
+```
+Project knowledge (Alysaril)    Shared, git managed, any agent reads via prompt
+Agent long-term memory          Per agent, domain expertise, cross-run
+Workflow context (start + msgs) Per run, moderator-controlled history
+```
+
 ## Open Questions

 1. **Agent naming convention** — should we enforce a fixed set (`developer`, `ops`, `writer`) or allow arbitrary names?
 2. **Extract override granularity** — global only, or also per-agent and per-role?
 3. **Context threading** — should `WorkflowContext` expose `workdir` and `signal` alongside the existing `start` + `messages`?
+4. **Agent long-term memory** — storage format and mechanism for persisting domain expertise across runs

 ## References

 - [RFC-002: Workflow Engine](./rfc-002-workflow-engine.md)
 - Current `Role` / `Moderator` types: `packages/core/src/workflow.ts`
+- [Alysaril](https://git.shazhou.work/uncaged/alysaril) — project knowledge base (independent tool)