π The original agent harness. Deploy intelligent multi-player swarms, coordinate autonomous workflows, and build conversational AI systems. Features adaptive memory, self-learning intelligence, federation, vector RAG integration, and native Claude Code / Codex / Hermes and many more Integrated
TypeScript agentic-aiagentic-frameworkagentic-workflowagentsai-agentsai-assistantai-skillsautonomous-agentsclaudecodexdsh-pluginharnessmcp-servermulti-agentmulti-agent-systemsnpmskillsswarmswarm-intelligencetypescript
docs(adr): name the agentic protector Project Anatole (this feature only)
ruvddce80ec3ad7
diff --git a/v3/docs/adr/ADR-453-agentic-protector.md b/v3/docs/adr/ADR-453-project-anatole.mdsimilarity index 96%rename from v3/docs/adr/ADR-453-agentic-protector.mdrename to v3/docs/adr/ADR-453-project-anatole.mdindex 7aa56fb992..4def20f22a 100644--- a/v3/docs/adr/ADR-453-agentic-protector.md+++ b/v3/docs/adr/ADR-453-project-anatole.md@@ -1,4 +1,4 @@-# ADR 453: The agentic protector: an optional, learning watchdog for unattended agents+# ADR 453: Project Anatole: an optional, learning watchdog for unattended agentsStatus: Proposed (default off; nothing here is built when this is merged)@@ -22,7 +22,7 @@ An anti-virus for agents has the same two jobs as the desktop kind: known-bad si## 2. Decision-Add an **optional** plugin, `ruflo-protector`, a mod in the ADR-404 pattern, plus a **Protector** section in the console's Security & Doctor page for listing, running and editing it. It is not part of any default install.+**Project Anatole** is the name of this feature, and of nothing else: the mod system, the console and the other plugins keep their names. Anatole is an **optional** plugin, `ruflo-protector`, a mod in the ADR-404 pattern, plus a **Project Anatole** section in the console's Security & Doctor page for listing, running and editing it. The technical identifiers below (`ruflo-protector`, `/protector`, `.claude-flow/protector-mod/`, rule ids `PR-###`) stay descriptive; "Project Anatole" is what a person sees. It is not part of any default install.1. **Two kinds of signal, never mixed up.** *Rules* are deterministic, mapped to OWASP, and the only thing that can ever block. *Anomalies* come from a learned baseline and can only notify, and only when corroborated by a risky action. A baseline can never turn a rule off or whitelist a rule's class.2. **Four modes, no automatic escalation to blocking.** `off`, `learn` (the default once installed: record the baseline, say nothing), `notify` (alert, never block), `enforce` (rules marked `block` deny, everything else still only notifies). The plugin may graduate `learn` to `notify` when the baseline is mature. It never enables `enforce` by itself.@@ -133,9 +133,9 @@ Directory `.claude-flow/protector-mod/` (the `-mod` suffix is what the console's| `allow <fp>` | allow a fingerprint without an alert || `reset-baseline` | forget the baseline and start learning again |-## 9. The console: a Protector section in Security & Doctor+## 9. The console: a Project Anatole section in Security & Doctor-The Security & Doctor page (`secure` view) gets a collapsible **Protector** section, in the page's existing list / run / edit style:+The Security & Doctor page (`secure` view) gets a collapsible **Project Anatole** section, in the page's existing list / run / edit style:- **Status row**: mode, baseline maturity as a bar ("learning 62%"), open alerts by severity, blocked count, `degraded` if set. When the plugin is not loaded, one line says how to install it, and nothing else shows.- **List**: one row per rule: id, OWASP refs, severity, current mode (a three-way chip: off Β· notify Β· block), hits, acked share. A rule that was auto-demoted says so.diff --git a/v3/docs/adr/INDEX-mod-system.md b/v3/docs/adr/INDEX-mod-system.mdindex fe2cf747ca..89e29c837e 100644--- a/v3/docs/adr/INDEX-mod-system.md+++ b/v3/docs/adr/INDEX-mod-system.md@@ -17,7 +17,7 @@ Two files carry the number 430 (the menu's accents, and the menu-design amendmen| 450 | Threat model of the mod system | Proposed (T1 part, T6, T8, T12 done; T19 recorded; T9 and default confirm await a human) | 10-05 (see note) | 404, 444, 445, 446, 447, 448; related 449, 451, 452 | β | merged: #3717 (console 0.33.3: T1 truthful classes incl. dt-term-exec, T3 plain()); T8+T12 in #3720 (0.33.4), T8 install class in #3730 (0.33.5); T6 guards #3727, #3734, #3745, #3764; T19 (`http.fetch` read path, recorded without a fix) in #3740 | ruflo-console `threat-model.spec.ts`, `control-guards.spec.ts` | `threat-model.spec.ts`, `threat.test.ts` || 451 | Mod capability roadmap | Proposed (items 1β3, 5β7 shipped, all default off; 4, 8, 9, 10 not built) | 10-04 | 404, 445, 446, 447; related 449, 450, 452 | β | #3716 (ADR + `toolHints`, 0.3.0); `agentTrim` item 2 (0.3.1, `33a60c715`); `deliveryScreen` item 3 (0.3.3, `cd01a4aea`); `capabilityProbe` item 5 #3763 (0.3.7); `sessionRollup` item 6 #3766 (0.3.8); `compactCarry` item 7 #3768 (0.3.9); agentTrim live fixes #3733 and measurement #3760; fixes 0.3.2, 0.3.4 | ruflo-mods 0.3.9 | `describe`, `agents`, `delivery`, `probe`, `rollup`, `compact` tests || 452 | Mod-system overnight hardening: findings, changes, open items | Accepted (record) | 10-05 | 404, 444, 445, 446, 450, 451 | β | #3735; records #3706, #3711, #3713, #3714, #3715, #3717, #3719, #3727, #3732, #3733, #3734 (all merged) | no code of its own | `probe-mod-guards`, `sync-mod-screen --check` |-| 453 | The agentic protector: an optional, learning watchdog for unattended agents | Proposed | 10-05 | 404, 444, 445, 446, 450, 451, 452; related 449 | β | this PR (ADR only) | not built | β |+| 453 | Project Anatole: an optional, learning watchdog for unattended agents | Proposed | 10-05 | 404, 444, 445, 446, 450, 451, 452; related 449 | β | this PR (ADR only) | not built | β |## Console: mission control and Claude control