🌊 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
release: 3.63.0 (#4476)
rUve2dae2f701f9
diff --git a/CHANGELOG.md b/CHANGELOG.mdindex 024574a73f..87364911bd 100644--- a/CHANGELOG.md+++ b/CHANGELOG.md@@ -5,6 +5,26 @@ All notable changes to the Ruflo project (formerly Claude Flow) are documented hThe format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).+## [3.63.0] - 2026-10-25++Minor release: `@claude-flow/cli`, `claude-flow`, `ruflo` 3.63.0. Adds four MCP tools for Anthropic Claude Managed Agents (`managed_agent_capabilities`, `managed_agent_control`, `managed_agent_learning`, `managed_agent_interrupt`). No leaf package changed, so no standalone publishes.++### Added++- **Managed cloud agents: dynamic workflows, controls and verified advisory learning** (`ruflo-agent` 0.4.0, `ruflo-workflows` 0.7.0, `ruflo-console` 0.49.0; ADR 0003 and 0004). Everything is opt-in. A cloud agent can run bounded dynamic workflows (`dynamicWorkflows: true` with a mandatory `budgetCents`, limited networking, optional `predefinedAgents`); provider completion is reported as `verification: "unverified"`. Managed sessions show up in the console's Workflows page with their budget, blockers and worker counts, with zero provider traffic from the panels. `managed_agent_control` inspects, interrupts or terminates one session only when the host sets `RUFLO_MANAGED_CONTROL=1` and lists the session in `RUFLO_MANAGED_CONTROL_SESSIONS`, after a fresh read of the provider's state. With `RUFLO_MANAGED_LEARNING=1` and a host-configured `RUFLO_MANAGED_VERIFIER_PUBLIC_KEY`, `managed_agent_learning` admits signed outcomes (unsigned ones stay quarantined), recommends a strategy and evaluates paired holdouts; nothing changes routing on its own.+- User guide: a "Managed cloud agents" section in `docs/USERGUIDE.md`.++### Fixed++- `memory_search_unified` dropped an entry whenever the same key existed in two namespaces; it now deduplicates on namespace and key (#4470, thanks @kevin9327).+- Before this release shipped, an independent review of the managed-agent change found and fixed: `managed_agent_interrupt` had no host policy gate (it now uses the `managed_agent_control` path, and `managed_agent_terminate` obeys the same allowlist, deleting only the session's own environment, once `RUFLO_MANAGED_CONTROL=1`); `managed_agent_prompt` could report the previous turn's answer as finished on a later poll; several valid base64 spellings of one verifier signature were stored as separate ledger records; and the console showed rescheduling, budget-stopped and action-blocked sessions as finished.++### Notes++- **Known limits (ADR 0004):** the verifier signs with a key in the same user account as the checks it runs, so run only host-authored checks, never ones an agent produced; evidence is only partly bound to what ran; a crashed process can leave a lock file that needs removing by hand; a session in an `error` state cannot be controlled. Live execution against the Anthropic Managed Agents beta has **not** been exercised (it needs an executor key), so treat the cloud runtime as unproven in production.+- `ruflo-ai-team` 0.3.5 (#4475) also changed in this tree.+- `RUFLO_MANAGED_AGENTS_BASE_URL` is an operator-only override of the API origin (an HTTPS origin, no credentials, path or redirects); it is never a tool argument.+## [3.62.0] - 2026-10-24Minor release: `@claude-flow/cli`, `claude-flow`, `ruflo` 3.62.0. Adds one MCP tool (`rure_cuda_launch_plan`). No leaf package changed, so no standalone publishes.diff --git a/package-lock.json b/package-lock.jsonindex 36d5166a83..7cafd7b8ed 100644--- a/package-lock.json+++ b/package-lock.json@@ -1,12 +1,12 @@{"name": "claude-flow",- "version": "3.62.0",+ "version": "3.63.0","lockfileVersion": 3,"requires": true,"packages": {"": {"name": "claude-flow",- "version": "3.62.0",+ "version": "3.63.0","bundleDependencies": ["@claude-flow/codex","@claude-flow/mcp",diff --git a/package.json b/package.jsonindex e64efff583..8b81b5f509 100644--- a/package.json+++ b/package.json@@ -1,6 +1,6 @@{"name": "claude-flow",- "version": "3.62.0",+ "version": "3.63.0","workspaces": ["v3/@claude-flow/codex","v3/@claude-flow/mcp",diff --git a/ruflo/package.json b/ruflo/package.jsonindex 01ad900395..70647521c8 100644--- a/ruflo/package.json+++ b/ruflo/package.json@@ -1,6 +1,6 @@{"name": "ruflo",- "version": "3.62.0",+ "version": "3.63.0","description": "Ruflo - Enterprise AI agent orchestration platform. Deploy 60+ specialized agents in coordinated swarms with self-learning, fault-tolerant consensus, vector memory, and MCP integration","main": "bin/ruflo.js","type": "module",@@ -40,7 +40,7 @@"package:rvf": "bash src/scripts/package-rvf.sh"},"dependencies": {- "@claude-flow/cli": "3.62.0"+ "@claude-flow/cli": "3.63.0"},"optionalDependencies": {},"overrides": {diff --git a/v3/@claude-flow/cli/package.json b/v3/@claude-flow/cli/package.jsonindex 4daad266dc..5f229aedca 100644--- a/v3/@claude-flow/cli/package.json+++ b/v3/@claude-flow/cli/package.json@@ -1,6 +1,6 @@{"name": "@claude-flow/cli",- "version": "3.62.0",+ "version": "3.63.0","type": "module","description": "Ruflo CLI - Enterprise AI agent orchestration with 60+ specialized agents, swarm coordination, MCP server, self-learning hooks, and vector memory for Claude Code","main": "dist/src/index.js",